AU2022482293A1

AU2022482293A1 - Intelligent grid power management for fleet vehicle charging

Info

Publication number: AU2022482293A1
Application number: AU2022482293A
Authority: AU
Inventors: Jonas Hellgren
Original assignee: Volvo Truck Corp
Current assignee: Volvo Truck Corp
Priority date: 2022-10-14
Filing date: 2022-10-14
Publication date: 2025-04-24
Also published as: WO2024078728A1; EP4602688A1

Abstract

A fleet vehicle charging management system for a fleet comprising a plurality of electric vehicles 100a,b,c comprises an apparatus 102, for example, a server (102) configured to communicate with each vehicle of the fleet of vehicles, a plurality of soft-switches (104a,b,c) and a plurality of battery chargers (106a,b,c) configured to be connected to a grid power supply (110, 120). Each respective one of the battery chargers is configured to provide a charging power supply to a connected electric vehicle (100a,b,c) of the plurality of vehicles (100a,b,c) via a respective one of the soft-switches (104a,b,c) based on a self-learning charging model, wherein the self-learning charging model is configured to minimise a financial cost and/or a power demand of implementing a connection policy control variable for charging the vehicle fleet.

Description

INTELLIGENT GRID POWER MANAGEMENT FOR FLEET VEHICLE CHARGING [0001] The present disclosure relates to a method of power management for charging a plurality of electric vehicles, for example, a fleet of electric vehicles, and to various related aspects. [0002] Electric vehicles are periodically connected to the electric grid or other charging sources, which may themselves draw power from the grid, in order to recharge their on-board battery systems. Battery charging systems found on electric vehicles may store anything from a few kWs to more than a 100kWs of electrical energy depending on their intended range and what other systems may draw from the on-board vehicle battery. In addition, certain types of vehicles may be connected to vehicle accessories. Such accessories may draw from the vehicle battery system or have their own on-board battery systems which may be charged directly or via a connected vehicle. Such accessories may accordingly further increase the demand for power when recharging an electric vehicle to which they are electrically connected. [0003] Typically charging an on-board vehicle battery charging takes several hours. To minimize the operating cost, the electric energy consumed from the grid should ideally be managed so that the charging is managed in a way that avoids excessive power demands from the grid and ideally also reduces the cost per electrical energy unit used in the battery charging process. This is particular important where a number of vehicles operating on a site may require charging, especially if they are large heavy vehicles which may have substantial battery storage capacity on-board to recharge. [0004] Determining when to recharge one or more electric vehicles is not just a question of plugging in a vehicle outside at some point in time outside a peak demand periods to avoid being charged for electricity at a higher cost per kWh level. Whilst by using electrical energy when costs are lower, the demand on the grid at peak times of day is reduced, it may not always be possible to avoid recharging a vehicle battery at a more expensive times of the day as this will in part depend on how fast the battery can be recharged, how depleted the battery is at the beginning of charging, when the electric vehicle is next going to be used, and how much energy will be needed from the battery for the next use of the vehicle. [0005] Another factor is that some electrical power providers may use dynamic pricing which may change during the course of a battery charging period according to changing environmental conditions. For example, if electricity is generated using wind, wave, or solar generation systems, the price per kW/h unit may vary according to conditions which affect the output of electricity from these systems. For example, the price may be less if the wind is blowing more strongly or be higher if there is no wind, less if the waves are the right height, but more or less if they are not, and also depend on the prevailing amount of solar flux. Such adaptations may be in real-time or delayed. [0006] There is accordingly a need for an intelligent battery charging system which avoids a user having to try to predict when to connect and disconnect their vehicle to have the battery charged for a future use of that vehicle in a way that manages the times when power is drawn for charging purposes. There is also a need for an intelligent battery charging system for power management when charging a plurality of vehicles so that their collective charging power demands do not exceed any local grid power supply constraints or adversely impact the available electrical power supply to other devices and/or affect users of such devices which use grid power at the same time. [0007] Some embodiments of the disclosed technology provide a method of controlling in an adaptive and optimal manner when a plurality of electric vehicles should be charged or not. A related charging algorithm for determining when an electric vehicle should be charged or not charged using a charging model is set out in the inventor’s related International Patent Application PCT/EP2022/078719, the contents of which are hereby incorporated in their entirety. [0008] In particular, but not exclusively the disclosed technology relates to a method of charging a fleet of electric vehicles which uses a self-learning charging model to determine when to charge individual vehicles in the fleet of electric vehicles. The charging models may be implemented using reinforcement learning algorithms which are configured to determine when an action to charge one or more vehicles in the fleet should be taken. [0009] In particular, but not exclusively the disclosed technology relates to a self-learning method of grid power management for charging an electric vehicle which seeks to control in an adaptive and optimal manner when one or more or all electric vehicles of a plurality of electric vehicles should be charged or not charged. [00010] The method is particularly useful for electric vehicles which are automated in some way, for example, they may be autonomous or semi-autonomous and/or remote-controlled. The disclosed invention will be described mainly with respect to vehicles, however, such vehicles may include heavy-duty vehicles, such as semi-trailer vehicles and trucks as well as other types of vehicles such as cars. [00011] The disclosed technology seeks to mitigate, obviate, alleviate, or eliminate various issues known in the art which affect how to manage power consumption when charging an electric vehicle to avoid drawing power at times where power availability is lower due to demand. For example, in times of peak demand, to deter some customers from using electrical power distributed from a power grid, tariffs set for power consumption from the grid may be punitive. It is therefore helpful if power can be managed to avoid such periods of peak demand. [00012] Determining when to charge an electric vehicles, EVs, in a residential charging environment, may also be complicated by the maximum amp of the residential supply and the amount of power it will take to charge the electric vehicle as other devices such as a dishwasher or washing machine etc., may also need to draw power at the same time. Even if a grid power supply is supplemented or replaced by a local power generation source, for example by a solar source, there will be limits as to how much power may be consumed at the same time. Residential single phase systems are often limited to a certain number of KWs per hour, and if the demand for power exceeds this then a three- phase supply may be needed. This requires additional infrastructure to be installed as well as having cost. Accordingly, it is important to be able to control how much power is used and when it is used to charge an electric vehicle. [00013] A. O. Erick and K. A. Folly disclose in their paper "Power Flow Management in Electric Vehicles Charging Station Using Reinforcement Learning," 2020 IEEE Congress on Evolutionary Computation (CEC), 2020, pp.1-8, doi: 10.1109/CEC48606.2020.9185652 describe an example of optimal power flow management problem in an electric vehicle charging station. The charging station is powered by solar PV and is tied to the grid and a battery storage system through necessary power conversion interfaces for DC fast charging. The optimal power management problem for EV charging is solved via reinforcement learning (RL). Unlike classical optimization methods such as dynamic programming, linear programming (LP) and mixed-integer linear programming which are limited in handling stochastic problems adequately and are slow due to the curse of dimensionality when used for large dynamic problems, RL does not have to iterate for every time step as learning can be done completely offline and optimal solutions saved in a lookup table, from which optimal control actions can be retrieved almost instantaneously. [00014] Electric vehicle charging stations known in the art however do not take into account issues such as peak demand and dynamic pricing where the price per unit of electricity, for example, the price per kWh varies during a given time period, such as over the course of 24 hours or weekly or seasonally, or as a result of environmental conditions changing such as wind and solar radiation, all of which may affect the amount of power available to be delivered to a vehicle. SUMMARY STATEMENTS [00015] Whilst the invention is defined by the accompanying claims, various aspects of the disclosed technology including the claimed technology are set out in this summary section with examples of some preferred embodiments and indications of possible technical benefits. [00016] A first aspect of the disclosed technology comprises a computer-implemented method of power management for charging a plurality of batteries of a fleet of vehicles, each vehicle comprising at least one battery, the method comprising: determining a set of variables for each vehicle in the fleet, the set of variables including a current battery state of energy variable and a target battery state of energy at the end of a charging period; and determining if power should be provided to charge one or more vehicles in the fleet via or using at least one external power source based on output from a self-learning charging model configured to map a set of variables input to the model to an output comprising an action to charge the vehicle battery or not to charge the vehicle, based on one or more charging constraints for the fleet of vehicles. [00017] Some embodiments of the model are configured to take into account the one or more charging constraints when mapping an input set of variables to an output from the model. The output may be stored output generated by previously training the self-learning model in some embodiments. [00018] Advantageously, the power management method may enable a fleet of vehicles to be intelligently charged in a way that reduces electricity demand on a local power grid during peak hours. Advantageously, by reducing electricity demand on a local power grid during peak hours the financial cost of recharging a fleet of vehicles can be better managed. [00019] In some embodiments, a charging constraint for the fleet of vehicles comprises a cost constraint for charging the fleet of vehicles. [00020] In some embodiments, a charging constraint for the fleet of vehicles comprises a power constraint representing a power limit for the amount of power that can be transmitted to the fleet of vehicles at any given point in time. [00021] In some embodiments, the charging model is configured to minimize a standard deviation of battery state of energy levels across the fleet of vehicles. [00022] In some embodiments, the charging policy is configured to minimize a total deviation from a target battery state of energy level across the fleet of vehicles. [00023] In some embodiments, for each vehicle in the fleet, the current battery state of energy is determined when that vehicle is connected to an external power supply and the method further comprises, if that vehicle is determined to receive power using the charging policy, configuring the external power supply to provide power to charge the vehicle. [00024] In some embodiments, configuring the external power supply to provide power to charge that vehicle comprises actuating a soft switch or relay. [00025] In some embodiments, for each vehicle in the fleet, the charging model policy is configured to determine, for each of a plurality of charging periods, electricity cost and probable risk of a battery state of energy not meeting a target charged battery energy state at the end of each charging period. [00026] Advantageously, by providing an intelligent power management method which allows for multiple charging periods to start and stop whilst an electric vehicle is connected to a battery charger until a desired level of charge is achieved by a certain point in time, battery degradation over multiple charging cycles may be reduced and the maximum battery charge capacity may be better maintained for each vehicle and/or across the fleet of vehicles. [00027] In some embodiments, the set of variables include a current time of day, a charging tariff for the current time of day, the target charged battery energy state and the current energy state of the battery. [00028] In some embodiments, using the self-learning model includes performing, for each vehicle of the fleet of vehicles, a method for charging an electric vehicle at a charging power source, wherein the method comprises: detecting a current state of energy of a battery of a vehicle, determining a target charged state of energy of the battery at a future point in time, and determining a point in time when power should be provided to charge the vehicle from the charging power source based on the detected current state of energy of the battery and the determined target charged state of energy of the battery so that the future point in time is a predicted end of a charging time period. The future point in time may be determined using a vehicle battery charging model configured to determine the target charged battery energy state based on a predicted user demand for power from the charged vehicle at the end of the charging period and at least one charging constraint for the charging power source. [00029] In some embodiments, the method further comprises training the vehicle battery charging model to: map input to the model comprising a set of power load variables of the charging power source to an output representing a charging action to charge the battery or a non-charging action to not charge the battery by rewarding for long-term and short-term consequences of the charging or non-charging actions. [00030] In some embodiments, the method further comprises: when the battery is determined to start charging at the future point in time, based on the determined current state of energy of the battery and a determined charging action of the dynamic vehicle battery charging model, configuring the external charging power supply to automatically provide power to charge the vehicle by actuating a soft switch. [00031] In some embodiments, based on the predicted future point in time for achieving the determined target charged battery state, the method further comprises, responsive to determining when power should start to be provided to charge the vehicle to achieve the predicted target charged battery state by the determined future time, causing an alert to be provided to a user to connect the vehicle to a power supply if the vehicle is not already connected at or in advance of the determined start time. The alert may also be provided for multiple vehicles in some embodiments. [00032] In some embodiments, at least one charging constraint is a charge or not condition based on an objective to minimize long term energy costs. [00033] In some embodiments, the set of power load variables of the external power source includes a power load variable of an external power supply to the charging power source, wherein the external power supply is connected to one or more other power-consuming devices consuming power in a charging period. [00034] In some embodiments, the charging constraint comprises a maximum available power constraint for the external power supply to provide power to the charging power supply. [00035] In some embodiments, the one or more power-consuming devices include one or more devices which are not battery operated. [00036] In some embodiments, the charging model is trained to determine, for each of a plurality of charging periods, electricity cost and a probable risk of a battery state of energy not meeting a target charged battery energy state at the end of that charging period. [00037] In some embodiments, the method further comprises varying the amount of charging power used by the charging power supply to charge the vehicle battery based on the current vehicle battery state of energy. [00038] In some embodiments, the method further comprises: obtaining data generated by implementing the dynamic vehicle battery charging model at the charging power supply, using the gathered data as a training data set for training the dynamic battery vehicle charging model, wherein the gathered data comprises, for each charging period, data representing the start time, the end time, the initial battery charge state, the end battery charge set, the power consumed charging the battery and the cost of the power consumed charging the battery to the charging model, and re- training the trained dynamic battery vehicle charging model by inputting the gathered data into the trained model. [00039] In some embodiments, the self-learning charging model is trained using reinforcement learning for use in a method according to the first aspect, the trained model being configured to determine when to charge each vehicle based on predicted charging costs for an end state of battery energy to meet a predicted target charged battery energy state at the end of the one or more charging periods, the method comprising: inputting training data to the charging policy model; and iteratively processing the input training data to provide iterative output representing a charging cost, wherein each iteration comprises: comparing a charging cost with a target charging cost or with a charging cost from a previous iteration; and maximising cumulative rewards for reducing the charging cost to achieve the target battery charge state. [00040] In some embodiments, each reward, r, of the maximised cumulative rewards, can be represented for each charging period as either: a charge power consumption per unit time multiplied by a duration of time over which charge power is consumed multiplied by the energy consumption cost per unit of power in the case where the end of the charging period is reached and the target battery energy state is reached, or, if the target battery energy state is not reached at the end of the charging period, a total energy consumption cost for the duration of time the battery was charged plus a penalty term comprising the energy deficiency at the end of the charging period multiplies by a penalty constant. [00041] In some embodiments, each reward r of the maximised cumulative rewards is determined using a reward function based on a charge power consumption per unit time, a duration of time over which charge power is consumed, a battery energy deficiency comprising a difference between a target state of battery energy and a current state of battery energy, an energy consumption cost, and wherein the reward function indicates if an end of a charging episode is reached or not, and includes a penalty term defining how a violation from a target state of energy is to be penalised. [00042] Another, second, aspect of the disclosed technology comprises an apparatus comprising a computer-program product comprising a set of instructions stored in a memory and comprising one or more modules or circuitry which, when loaded from the memory for execution by one or more processors or processing circuitry of the apparatus cause the apparatus to implement a method according to the first aspect or any combination of one or more of the above embodiments disclosed herein. [00043] Another, third, aspect of the disclosed technology comprises a fleet vehicle charging management system, the fleet comprising a plurality of electric vehicles 100a,b,c, wherein the charging management system comprises: an apparatus according to the second aspect, a plurality of soft-switches, a plurality of battery chargers configured to be connected to a grid power supply, where each respective one of the battery chargers is configured to provide a charging power supply to a connected electric vehicle of the plurality of electric vehicles via a respective one of the soft- switches based on a self-learning battery charging model, for example, a self-learning battery charging model as disclosed herein, wherein the battery charging model is configured to minimise a financial cost and/or a power demand of implementing a connection policy control variable for charging the vehicle fleet. [00044] Example of the grid power supply may comprise, for example, a site or premises distribution system, or a local distribution transformer source, or a distribution sub-station. The plurality of vehicles accordingly may, for example, be connected to battery chargers which are powered via the same site or premises distribution system, or via the same local distribution transformer source, or via the same distribution sub-station. Unless a power management scheme is employed such as that of the disclosed technology, it is possible to draw too much power from grid at the same time. This may lead to shortages in supply and/or power out-ages which may not be limited to just the battery charging apparatus, but which could also affect other devices and consumers connected to the same distribution equipment of the local power grid. [00045] In some embodiments, for each electric vehicle connected to a respective one of the battery chargers via a soft-switch the system is configured, the apparatus implements a battery charging model policy which selectively determines which of the plurality of connected electric vehicles is to be charged based on a SoE deviation from the average SoE of the vehicle fleet, and if a vehicle is determined to be charged, which determines a charging period for charging that vehicle’s battery system. The charging period for each battery may be individually started by the apparatus causing a respective one of the soft-switches to be actuated so as to control a supply of electrical power to start charging the battery system of the connected electric vehicle. [00046] In some embodiments, the battery charging module is configured to minimise a connection policy control variable min cost⁽u⁾ so that ^∑ _^^^..^ P_{^^ ^} (u)< P_{^^ ^^^ ^^^^^}, where n is the number of vehicles in the fleet, Pch i is the Power consumed to charge the ith vehicle in the fleet, and Pch max fleet is the maximum power allowed to charge the fleet of vehicles. [00047] In some embodiments, at least one electric vehicle is a heavy duty electric vehicle. [00048] In some embodiments, at least one or more or all of the electric vehicles comprise an autonomous or semi-autonomous or remote controlled electric vehicle. [00049] Another, fourth, aspect of the disclosed technology comprises a computer-implemented method for charging an electric vehicle at a charging power source, the method comprising: detecting a current state of energy of a battery of a vehicle, determining a target charged state of energy of the battery at a future point in time, and determining a point in time when power should be provided to charge the vehicle from the charging power source based on the detected current state of energy of the battery and the determined target charged state of energy of the battery so that the future point in time is a predicted end of a charging time period, wherein the future point in time is determined using a vehicle battery charging model configured to determine the target charged battery energy state based on a predicted user demand for power from the charged vehicle at the end of the charging period and at least one charging constraint for the charging power source. [00050] In some embodiments, the at least one charging constraint may include a charging constraint derived from the power demands for recharging batteries of or more other electric vehicles, for example, other electric vehicles whose battery chargers are connected to the same local electrical grid power distribution sub-station as those of the electric vehicle. [00051] In some embodiments, the method according to the fourth aspect includes a constraint for charging a plurality of electric vehicles including the electric vehicle. The method may include training the vehicle battery charging model to map input to the model comprising a set of power load variables of the charging power source to an output representing a charging action to charge the battery or a non-charging action to not charge the battery by rewarding for long-term and short- term consequences of the charging or non-charging actions. [00052] The battery charging models disclosed herein, including those used for the first to fourth aspects disclosed above, may be a dynamically trained reinforcement algorithm based charging model which uses cumulative rewards in some embodiments. [00053] In some embodiments, the fourth aspect provides a computer-implemented method of power management for charging an electric vehicle of a fleet of electric vehicles, the method comprising determining a current state of energy of a battery of a vehicle determining a target desired charged state of energy of the battery at the end of a charging period, determining if power should be provided to charge the vehicle from a charging power source using a charging model for the power source based on the current state of energy of the battery and the determined target charged state of energy of the battery, wherein the dynamic charging model is trained to map input comprising a set of power load variables of the charging power source to an output comprising an action to charge the vehicle battery or not, wherein the model is trained using rewards for long-term consequences of the action and rewards for short-term consequences of the action. In some embodiments, the trained charging model determines a target charged battery energy state for each vehicle of a plurality of vehicles based on a predicted user demand for power from the charging power source at a predicted end of the charging period based on a cost of charging constraint for each vehicle and/or the fleet of vehicles. [00054] Advantageously the disclosed method may be implemented using a soft-switch so that a battery may be connected but only charged a subsequent point in time and still achieve a desired end state of energy. [00055] In some embodiments, the battery is determined to start charging at the future point in time, based on the determined current state of energy of the battery and a determined charging action of the dynamic vehicle battery charging model, configuring the external charging power supply to automatically provide power to charge the vehicle by actuating a soft switch or relay (S208). [00056] Advantageously, the method does not need to perform a forecast for a supply load profile and day-ahead tariff. [00057] Advantageously, the method may learn over time the optimal time to recharge a vehicle based on its use history and charging history so that its down-time for recharging is minimised. Consequently, the method has the potential to improve the overall use of an electric vehicle by improving the likelihood that it will have a desired battery state of energy for a predicted desired use at a particular point in time. The technology may also improve the charging performance of the battery of an electric vehicle as the soft-switch can also turn off power to prevent over-charging. The soft-switch may disconnect a battery from charging using grid power due to peak power demands. In some embodiments, by discontinuing the battery from charging using the soft-switch, the soft- switch may permit the battery to discharge to provide power to replace grid power in a local installation. In some embodiments, instead or alternatively, it may also prevent discharge or limit discharge from a vehicle battery if the grid power would otherwise draw from a vehicle battery to satisfy grid power demands. In this way, if the soft-switch is aware that a vehicle may be used at a future point in time and would have sufficient time to recover, it may allow more of the battery to be discharged to the grid than it would do if the vehicle battery needs to reserve more energy for use at a later point in time. [00058] In other words, in some embodiments, the disclosed charging models are configured in some embodiments to allow for energy consumption to begin and end at multiple different times without the need for direct human intervention so as to take advantage of demand and dynamic pricing. For example, if the price per kWh of electricity is dependent on environmental factors such as the wind speed and/or solar radiation, increases in either or both may result in locally at that charging station and/or regionally within a grid, the cost of energy changing at various times which may not be intuitive for a human user to know when to plug their vehicle in. Also, in some countries, lower prices are charged for each kWh of electricity consumed during off-peak demand periods than are charged during peak demand periods. This may also influence when an electric vehicle is charged or not. [00059] In some embodiments, based on the predicted future point in time for achieving the determined target charged battery state, the method further comprises, responsive to determining that power should start to be provided to charge the vehicle to achieve the predicted target charged battery state by the determined future time, causing an alert to be provided to a user to connect the vehicle to a power supply if the vehicle is not already connected (S210). [00060] In some embodiments, at least one charging constraint is a charge or not condition based on an objective to minimize long term energy costs. In some embodiments, at least one charging constraint is a cost of charging constraint and/or an available power constraint. For example, if power cuts occur when demand exceeds a limit, this may be taken into account in the form of a charging constraint. [00061] In some embodiments, the set of power load variables of the external power source includes a power load variable of an external power supply to the charging power source, wherein the external power supply is connected to one or more other power-consuming devices consuming power in a charging period. [00062] In some embodiments, the charging constraint comprises a maximum available power constraint for the external power supply to provide power to the charging power supply. [00063] In some embodiments, the power-consuming devices include one or more devices which are not battery operated. [00064] In some embodiments, the charging model is trained to determine, for each of a plurality of charging periods, electricity cost and a probable risk of a battery state of energy not meeting a target charged battery energy state at the end of that charging period. [00065] In some embodiments, the method further comprises varying the amount of charging power used by the charging power supply to charge the vehicle battery based on the current vehicle battery state of energy. [00066] In some embodiments, the method further comprises obtaining data generated by implementing the dynamic vehicle battery charging model at the charging power supply, using the gathered data as a training data set for training the dynamic battery vehicle charging model, wherein the gathered data comprises, for each charging period, data representing the start time, the end time, the initial battery charge state, the end battery charge set, the power consumed charging the battery and the cost of the power consumed charging the battery to the charging model, and re- training the trained dynamic battery vehicle charging model by inputting the gathered data into the trained model. [00067] Another, fifth, aspect of the disclosed technology comprises a method of training a charging model using reinforcement learning, the charging model being configured for use in a method of the first aspect or any one of its embodiments disclosed herein, the trained model being configured to determine when to charge the vehicle based on predicted charging costs for an end state of battery energy to meet a predicted target charged battery energy state at the end of the one or more charging periods, the method comprising inputting training data to the charging policy model, and iteratively processing the input training data to provide iterative output representing a charging cost, wherein each iteration comprises comparing a charging cost with a target charging cost or with a charging cost from a previous iteration and maximising cumulative rewards for reducing the charging cost to achieve the target battery charge state. [00068] In some embodiments, each reward, r, of the maximised cumulative rewards, can be represented for each charging period as either a charge power consumption per unit time multiplied by a duration of time over which charge power is consumed multiplied by the energy consumption cost per unit of power in the case where the end of the charging period is reached and the target battery energy state is reached; or, if the target battery energy state is not reached at the end of the charging period, a total energy consumption cost for the duration of time the battery was charged plus a penalty term comprising the energy deficiency at the end of the charging period multiplies by a penalty constant. [00069] In some embodiments, wherein each reward r of the maximised cumulative rewards is determined using a reward function based on a charge power consumption per unit time, a duration of time over which charge power is consumed, a battery energy deficiency comprising a difference between a target state of battery energy and a current state of battery energy, an energy consumption cost, and wherein the reward function indicates if an end of a charging episode is reached or not, and includes a penalty term defining how a violation from a target state of energy is to be penalised. [00070] Another, sixth, aspect relates to an apparatus comprising a computer-program product comprising a set of instructions stored in a memory and comprising one or more modules or circuitry which, when loaded from the memory for execution by one or more processors or processing circuitry of the apparatus cause the apparatus to implement a method according to the first and/or second aspects or any of their embodiments disclosed herein. [00071] In some embodiments, the apparatus is configured to be connected to a grid power supply and comprises a charging power supply outlet configured to be connected to an actuatable a soft- switch 104, wherein, when an electric vehicle 100 is connected to the apparatus, the apparatus is configured to actuate the soft-switch to control a supply of electrical power to at least start charging a battery of the connected electric vehicle based on the apparatus implementing a method according to the first aspect or any one of its embodiments disclosed herein to determine an action to charge a connected vehicle should be performed. [00072] In some embodiments, wherein actuating the soft-switch 104 also controls the supply of electrical power to stop charging a battery of the connected electric vehicle when the target charged state of energy of the battery is reached. [00073] In some embodiments, wherein the apparatus comprises a battery charger. [00074] Another, seventh, aspect of the disclosed technology comprises a computer-readable storage medium comprising computer-program code which, when executed by one or more processors or processing circuitry of an apparatus, causes the apparatus to implement a method according to the first aspect. [00075] Another, eighth aspect of the disclosed technology comprises a computer program carrier carrying a computer program comprising computer-program code, which, when loaded from the computer program carrier and executed by one or more processors or processing circuitry of an apparatus causes the apparatus to implement a method according to the first aspect, wherein the computer program carrier is one of an electronic signal, optical signal, radio signal or computer- readable storage medium. [00076] Another, ninth, aspect of the disclosed technology comprises a computer program product comprising computer-code which when loaded from memory and executed by one or more processors of a control circuit of an apparatus causes the vehicle to implement a method according to any one of the above disclosed method aspects and/or one or more of their disclosed embodiments. [00077] Another, tenth, aspect of the disclosed technology comprises computer code for causing an apparatus to perform the method of the first aspect when said computer code is loaded from memory and run on one or more processors or on processing circuitry of a an apparatus. [00078] The disclosed aspects and embodiments may be combined with each other in any suitable manner which would be apparent to someone of ordinary skill in the art. BRIEF DESCRIPTION OF THE DRAWINGS [00079] Some embodiments of the disclosed technology are described below with reference to the accompanying drawings which are by way of example only and in which: Figures 1A and 1B schematically illustrate example power cost models over a 24 hour period; Figure 1C schematically illustrates a power management system for charging an electric vehicle according to some embodiments of the disclosed technology; Figures 2A and 2B schematically illustrate example charging episodes according to some embodiments of the disclosed technology; Figure 3A schematically illustrates a charging model according to some embodiments of the disclosed technology; Figure 3B schematically illustrates a charging policy based on a charging model to some embodiments of the disclosed technology; Figure 4A schematically illustrates an example of a method of power management for charging an electric vehicle according to some embodiments of the disclosed technology; Figure 4B schematically illustrates an example method of training a charging model using reinforcement learning according to some embodiments of the disclosed technology; Figure 5 illustrates schematically an example of an apparatus configured to perform a method of power management for charging an electric vehicle according to some embodiments of the disclosed technology; Figure 6 illustrates schematically an example of an apparatus configured to train a charging model according to some embodiments of the disclosed technology; and Figure 7 shows an example data flow when training a reinforcement learning charging model according to some embodiments of the disclosed technology; Figure 8 shows schematically a power management system for charging a plurality of vehicles according to some embodiments of the disclosed technology; Figures 9A and 9B show schematically examples of how a charging policy affects the deviation of the SoE of vehicle batteries of a fleet of electric vehicles according to some embodiments of the disclosed technology; and Figure 10A shows an example method of power management for charging the batteries of a fleet of vehicles according to some embodiments of the disclosed technology; Figure 10B shows an example of a method for implementing a charging policy for power management when charging a plurality of batteries of a fleet of vehicles; Figure 11A shows schematically an example of an apparatus configured to implement a method according to Figure 10A; and Figure 11B shows schematically an example of an apparatus configured to implement a method according to Figure 10B. DETAILED DESCRIPTION [00080] Aspects of the present disclosure will be described more fully hereinafter with reference to the accompanying drawings. The apparatus and method disclosed herein can, however, be realized in many different forms and should not be construed as being limited to the aspects set forth herein. Steps, whether explicitly referred to a such or if implicit, may be re-ordered or omitted if not essential to some of the disclosed embodiments. Like numbers in the drawings refer to like elements throughout. [00081] The terminology used herein is for the purpose of describing particular aspects of the disclosure only, and is not intended to limit the disclosed technology embodiments described herein. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. [00082] Electric vehicles require battery charging and usually to charge their batteries they are periodically connected to a mains electricity supply, often referred to as “the grid” which is provided using a power distribution network from an electrical power station which may, for example, comprise a hydro-electric, wind, nuclear or other type of electrical energy source. The demand for electrical energy from a mains electricity supply has well-known peaks and lows, and electrical energy providers often try to incentivise the use of electrical energy at off-peak times by offering favourable tariffs. So, for example, 1 kWh of electricity consumed during a peak demand time period may cost twice as much as 1kWh of electricity consumed during an off-peak demand time period. [00083] Electric vehicle batteries may be configured to store several 10s or more of kWhs of electrical energy. Typically battery charging is performed over long time-periods last several hours and in order to minimize the operating cost of the vehicle, it is advantageous if the cost of any electric energy bought from the grid is as cheap as possible. [00084] The present disclosure relates to an intelligent system for charging one or more electric vehicles. One solution seeks to use a charging policy for each vehicle based on historic use of an electric vehicle providing an indication of when at a future point in time a vehicle is likely to be required for use, and which may also determine, based on historic use, a minimum level of a state of energy, SoE, of a vehicle battery which would be required until the next point in time when battery charging is likely to take place. By determining for one or more charging periods when an electric vehicle is connected a battery charger that charging is to start and end, it is possible to intelligently charge the battery to reach a desired SoE by a point in time when the vehicle is predicted to be required for use whilst seeking to reduce the cost of charging the vehicle based on historic pricing data for electric power consumed by the battery charger. Building on this solution, another solution disclosed below seeks to reduce the amount of power consumed by a plurality of electric vehicles at any given time, for example, to manage the power consumption for charging the batteries of a fleet of electric vehicles. Such a plurality of electric vehicles may be of the same or different types, and some may comprise heavy vehicles. [00085] Examples of electric vehicles which may require more intelligent charging of their on-board battery systems include a plug-in electric vehicles as well as vehicles with a full electric powertrain, in other words, vehicles whose propulsion systems are solely powered using on-board battery systems. Such vehicles may be convention vehicles driven by a human operator, with or without additional assistance, or semi- or fully autonomous vehicles. Electric vehicles in a fleet may also include remote-operated electric vehicles in some embodiments of the disclosed technology. The term “electric vehicle” as used herein may include a vehicle with an accessory which is electrically connected or connectable to a vehicle. Where such a vehicle accessory is capable of being electrically charged in the same manner as an electric vehicle, the term “electric vehicle” may be extended to include a vehicle accessory for charge modelling purposes. [00086] Figures 1A and 1B schematically illustrate example power pricing models over a 24 hour period for charging a battery 101 of an electric vehicle 100 using a mains power accessed via a battery charger 104. As shown, the cost of charging the battery 101 of the electric vehicle varies over a 24 hour period. Electric vehicles, particularly when the vehicles are heavy-duty electric vehicles which may have larger battery capacity and require higher voltages to charge their batteries than smaller vehicles, may take several hours to fully charge depending on the battery power capacity and the rate at which the battery charger can recharge the battery. [00087] As shown in Figure 1A, charging the electric vehicle battery 101 begins at time T0 and the battery 101 finishes charging at time T_end. The battery will be charged over a period of time that crosses a plurality of charging tariffs as shown in Figure 1A where a examples of 1kWh pricing is between prices or costs #1, cost #2, and a final cost #3. These costs reflect in part the supply demand on the power distribution network which is illustrated schematically in Figure 1B. [00088] In order to improve the management of the power supply so that the cost of charging a vehicle battery 101 using the power supply 106, see for example, Figure 1C, is minimised, it is advantageous to be able to control when the electric vehicle starts to have its battery 101 charged, i.e. to control time T0 and also to limit the power used to charge the battery 101, which may be by limiting the time taken overall or just the time taken during periods of time when the charges are not the lowest. [00089] Determining when the optimum time is to charge an electric vehicle battery 101 however may not be straight-forward. For example, grid-based pricing for electricity may vary geographically and may be adjusted depending on local micro-generation. Costs may also vary between cities, regions, and countries. [00090] Figure 1A shows an example plot of an electrical energy price model where the price of electricity is shown a function of time. In the example shown, it is more expensive to use electricity at evenings when cost #3 applies and demand is high (as shown in Figure 1B) than in the early morning when cost #1 applies. Figures 1A and 1B accordingly show an example of a pricing model where a customer gets “punished” for using power during peak periods of demand. The power during a period is tracked and the electricity price is related to the peak power. This incentives householders and businesses for example to use electricity during off-peak rates and to avoid during peak-rates charging a vehicle battery. Moreover, it is also advantageous to avoid battery charging when there are other demands on the power being supplied, for example, made by machinery or household appliances. [00091] Sometimes, however, in order to be certain a vehicle battery will be fully charged or sufficiently charged by a certain time, a user may connect a vehicle to a battery charger regardless of the demand or cost at a particular time of day. This is not desirable as it increases the demand for power to be delivered over the power network infrastructure during a peak rate as well as increasing the cost of the power supplied to charge the vehicle battery. [00092] Figure 1C schematically illustrates a power management system for charging an electric battery 1010 of an electric vehicle 100 according to some embodiments of the disclosed technology which seeks to control if a vehicle should be charged or not in an adaptive and optimal manner. As shown in Figure 1C, the electric vehicle 100, for example, is a heavy-duty electric vehicle, whose battery 101 may be connected to a battery charger 106 via a soft-switch 104 which may be controlled either by the battery charger 106 or remotely by a server 102 configured to control operation of the battery charger and/or the soft-switch. [00093] As shown in Figure 1C, the soft-switch may comprise a relay which enables a battery of the electric vehicle 100 to be connected and/or disconnected from the electrical power supply provided by the battery charger. In some embodiments, the soft-switch is controlled using switch control software which sets the relay state of the switch according to one or more inputs the switch control software receives. The relay of the soft-switch may according be fairly simple and not require any sophisticated power electronics. Advantageously, this results in a soft-switch which may require little maintenance. [00094] The disclosed technology uses a self-learning battery charging and power management system that seeks to manage power demands and/or grid electricity costs when charging a battery of an electric vehicle to find the optimal balance between energy cost and the risk of not ending up in a satisfying battery state of energy in a given charging episode. The self-learning battery charging and power management system is implemented so that there is a minimum amount of user input and/or user awareness of the decision process the management system performs knowledge and so that during a charging episode, is a trade of between the electricity cost and the risk of not ending up in a satisfying battery state of energy. [00095] Figures 2A and 2B schematically illustrate example charging episodes according to some embodiments of the disclosed technology where power is illustrated as a solid line and the battery state of energy SoE is shown as a dashed line. For both illustrated charging episodes, the target SoE of the battery is 100%. In Figure 2A, however, the charging policy implemented was too risk adverse, in other words, it was too careful and overly prioritized short term energy cost savings and as a result, was exposed to higher energy costs later in order to reach the target SoE by the target future point in time, which is 8:00am in the example illustrated. In contrast, in the example charging episode shown in Figure 2B, a better balance between electricity cost and the risk of not ending up in a satisfying battery state of energy is achieved. [00096] As used herein, the battery state of energy, in other words, the battery SoE is a normalised number which is 100% for a fully charged battery. The SoEerror is the target SoE minus the actual SoE. “action” is a Boolean decision taken by a charging policy which is true if charging is recommended and t_norm is normalized time, the spend charging time divided by the time in the day of the charging. [00097] In some embodiments, the charging apparatus 106 uses a non-rule-based charge policy, for example a charge policy configured to use one or more pattern recognition techniques or machine learning algorithms to determine an action to perform, for example, an action which determines when charging should start and/or end in order to charge a battery of an electric vehicle to a target SoE at a future point in time. [00098] In some embodiments, the policy maps a set of variables, for example SoE_^^^^^ and t_^^^^, to an optimal action comprising whether the vehicle charger shall receive charging power or not. The charging power is referred to as grid connected power or grid power in embodiments where electrical energy is received from a power distribution network or grid mains power supply. In some embodiments, however, the charging power may be partly or wholly indirectly grid powered if a storage battery configured to be grid powered for back-up purposes is used. In some embodiments, such a battery may also be connected to a local power generation source such as photo-voltaic array of solar panels or a wind turbine. [00099] Figure 3A illustrates schematically an example embodiment of such a charge policy. In Figure 3A, input to the charging model is processed by the charging model and the model generates output in the form of an action to charge a battery or to not charge the battery in a way that optimizes a reward function, r, and which updates a state transition function, s̅. [000100] In some embodiments, the reward function uses cumulative rewards, for example, as follows: The terms used in the above reward function, r, are defined in the table below as follows: [000101] In some embodiments, the transition function of the charging model which expresses how a state s̅ is to be updated is defined by: 1) ^̅ ← ^⁽^̅, ^^^^^^⁾ For the specific problem of charging it includes, for example, the relation 2) ^^^ ← ^^^ + ∆^^⁄ ^_^^^^^^^ [000102] In some embodiments, using the cumulative reward and transition functions as defined above in a suitable reinforcement learning algorithm the value of an action in a particular state can be used. Reinforcement learning involves an agent, a set of states, S, and a set of actions A per state. By performing an action a ∈A, the agent transitions from state to state, and the agent is rewarded each time an action is executed in a particular state, where the reward is a numerical score. [000103] Some embodiments of the charging model may use a reinforcement learning algorithm where the agent seeks to maximize its total cumulative reward by adding the maximum potential reward attainable from future states to its reward for achieving its current state, where the potential reward is a weighted sum of expected values for the rewards in all future steps starting from the current step. This influences the current action by the potential future reward. So, for example, using such a charging model could learn that, even if initially for a given set of input variables where the reinforcement learning algorithm output an action to charge the battery starting from a time tx which resulted in a negative reward, for example, as the target SoE is not reached at the end of a charging period, that repeatedly charging the battery starting at that time tx results in in the long term that starting at time tx is better than at other start times, as the over-all reward is better with the start time tx. [000104] In some embodiments, a model-free reinforcement learning algorithm may be used such as, for example, a Q-learning reinforcement learning algorithm is used which does not require a model of an environment and which can handle stochastic transitions and rewards without requiring adaptations. The “Q” being learnt is the reward function computed by the learning algorithm for an action in a given state. A Q-learning reinforcement learning algorithm seeks to find an optimal policy starting from a current state S for any finite Markov decision process which maximizes the expected value of the total reward over any and all successive steps, starting from a current state. In other words, by repeating possible actions for which a reward is provided a sufficient number of times, actions which result in optimum rewards can be learnt. [000105] Advantageously, embodiments of the charging model which use reinforcement learning do not have to iterate for every time step as learning can be done offline and optimal solutions stored in memory, for example, in a look-up table such as that shown in Figure or such as in a neural network, from which optimal control actions can be retrieved almost instantaneously. Such offline learning may provide a technical effect as by needing to iterating every time-step and learning off line, computational resources can be managed in a more energy efficient way. [000106] When steps are repeated using a Q-learning algorithm by an agent, after a certain number of steps the next step will be weight calculated as γ^Δt, where γ is a discount factor between 0 and 1 which determines the importance of future rewards for a given time step period Δt. The Q- learning algorithm has a function that calculates the quality of a state-action combination as follows: Q: S × A → ℝ Q is initialised to a value before learning begins and then each time t the agent selects an action at ^ A, a reward, rt, is calculated and the agent enters a new state st+1, which may depend on both the previous state st and the selected action, and Q is updated. For example: where r_t is the reward received when moving from state s_t to state s_t+1 and α is the learning rate. Some Q-learning algorithms may use a Bellman equation to provide value iteration updates using the weighted average of the current Q value and new information. An episode of the algorithm ends when st+1 reaches a final state. The temporal difference is the time-step. [000107] Some embodiments of the invention use a simple tabular Q-learning algorithm which can be expressed in pseudo-code by: [000108] The “Q” which is being learnt, in other words, the reward function computed by the learning algorithm for an action in a given state, provides an indication of how good or bad it is to take a specific action. If Q(S^{^},1)>Q(S^{^},0), then it is better to take action 1, then 0, in state S^{^}. Q expresses the long-term consequence of an action, the cumulative reward, while r is the short term reward. A simple look-up table can be used as memory for holding the Q values learnt for each new state s’ after taking an action a for the tabular Q-learning algorithm. [000109] Some embodiments of the invention, however, may use a more complex Q-learning algorithm, for example, one using neural networks acting as memory may be expressed in pseudo- code as: Initialize primary network Qθ, target network Qθ’, replay buffer D, τ << 1 for each iteration do for each environment step do Observe state s_t and select α_t̴ π (α_t, s_t) Execute α_t and observe next state s_t+1 reward r_t = R(s_t,α_t ) Store (s_t, α_t, r_t, s_t+1 ) in replay buffer D for each update step do Sample et = (st, αt, rt, st+1 )~ D Compute target Q value: Q*(s_t, α_t) ≈ r_t + γQ_θ (s_t+1,argmax_α’*Q_θ’ (s_t+1, α’ )) Perform gradient descent step on (Q*(s_t, α_t)- Q_θ(s_t, α_t))2 Update target network parameters: θ’ ←τ* θ + (1-τ) * θ’ [000110] An embodiment which uses tabular Q-learning may result in a charging policy such as that shown in Figure 3B. This shows for each state the actions performed and the result in each square or “tab” of the chart shown. For the charging policy illustrated in Figure 7, the following assumptions were made: 1) a grid with 1 hour resolution, in other words, each cell in the grid corresponds to a time-step Δt which represents 1 hour- see also assumption 5) below, 2) 25% SoE resolution 3) 15-hour charge episode time, 4) the model being trained using the pricing shown in Figure 1A which has electricity being more expensive in the first half of each charge episode, and where 5) a time step parameter ∆t which corresponds to the width of an entire cell in the grid. [000111] In Figure 3B darker shaded squares correspond to when implementing the charging model resulted in an action to charge the vehicle, in other words a true action variable. On the y-axis is the SoEerror which is positive when the actual SoE is lower than the target SoE. If zero or negative, charging is not rewarded. In the example shown in Figure 3B the policy shows that charging is done for small SoE deviations only when electricity is cheap. [000112] By using such a policy which is based on data and facts, trial and error human intuition about when to start charging a vehicle, which could either lead to an SoE_error when the battery 101 does not reaching its target charge state or to reaching its charge state but at a price cost which is too high is avoided. [000113] In some embodiments, to avoid a reinforcement learning algorithm testing new random actions which may result in a poor SoE after a charging episode, the model algorithm is trained off-line using recorded data. For example, a buffer may be provided with recorded price data, rpdb. For every charging episode, almost once per day for daily commuters using an eV, a price data trajectory is added and stored in rpdb. Until an adequate amount of data is present in rpdb, a naive policy may be used in some embodiments, for example, a policy which always recommends charging. After some price data collection has occurred, the initial training may start and a draft policy may be recommended based on the initial training. Training can be repeated so that a draft policy is recommended, maybe after 20-30 charge episodes. [000114] In some embodiments of the charging policy or model, the action is not restricted to be true or false, but rather, for example, a floating point number within a range, for example, within a normalised range of [0,1]. [000115] Figures 4A and 4B show example embodiments of how the server 102 or the battery charger apparatus 106 may implement a method which uses a charging policy model such as one of the above examples which use a Q-learning algorithm to determine when to supply charging power so that a battery is charged to a target SoE by a target future point in time, for example, by the server 102 or battery charger 106 activating the soft-switch 104 shown in Figure 1C to charge a battery of a vehicle 100. The vehicle 100 may be any type of electric vehicle with a battery that can be recharged from an external battery charger. Examples of vehicle 100 include a heavy-duty vehicle or accessory having an electric battery, which may be a plug-in hybrid battery or a battery for an electric vehicle which does is the main or sole source of power for propelling the vehicle. [000116] Figure 4A shows an embodiment of a computer-implemented method 200 for charging an electric vehicle at a charging power source where the method comprises detecting a current state of energy of a battery of a vehicle (S202) determining a target charged state of energy of the battery at a future point in time (S204) and determining a point in time when power should be provided to charge the vehicle from the charging power source based on the detected current state of energy of the battery and the determined target charged state of energy of the battery (S206) so that the future point in time is a predicted end of a charging time period, wherein the future point in time is determined using a dynamic vehicle battery charging model configured to determine the target charged battery energy state based on a predicted user demand for power from the charged vehicle at the end of the charging period and at least one charging constraint for the charging power source. [000117] Method 200 is performed by the battery charger 106 and the detected vehicle state is a measured of sensed battery vehicle state which may be obtained via the soft-switch 104 in some embodiments. The future point in time may be learnt by the charging algorithm of the charging model or input by a user of the vehicle to the battery charger in some embodiments. In other words, given a known future point in time when the vehicle is to be driven, the goal of the charging model is to minimise the financial cost of charging the battery so that it is ready for use with a minimum desired state of energy of the vehicle battery at that point in time. The dynamic vehicle battery charging model may use a reinforcement learning algorithm with cumulative rewards such as one of the above mentioned examples which may use tabular Q-learning or neural-network Q-learning to provide a cumulative reward for actions which charge the battery SoE to the target SoE by a particular future point in time, which may be user specified or which may learnt from historic charging cycles. [000118] In some embodiments the charging model receives a set of power load variables for the charging power source and processes these to determine an action to charge the battery or a non-charging action to not charge the battery by rewarding for long-term and short-term consequences of the charging or non-charging actions. [000119] By learning usage patterns for the electric vehicle it allows the charging system to be a self-learning system in some embodiments that minimizes grid electricity expenses for battery charging without risking the vehicle not having a sufficient amount of charge when it is needed to be used. [000120] In some embodiments, as shown in Figure 4A, the method 200 further comprises, if the model determines an action that battery is to be charged based on the determined current state of energy of the battery and the charging model, configuring the external charging power supply to automatically provide power to charge the vehicle by actuating a soft switch or relay S208. Based on the predicted target charged battery state being required at a time of day, in some embodiments, the method may further comprise, responsive to determining that power should be provided to charge the vehicle to reach the predicted target charged battery state by the required time of day, causing an alert to be provided to a user to connect the vehicle to a power supply if the vehicle is not already connected S210. In other words, to ensure that actuating the soft-switch 104 will result in the vehicle being charged from the battery charger 106. [000121] The charging model used by method 200 may in some embodiments be trained and/or retrained by using a set of power load variables for the battery charger, a term which may also refer to any other suitable form of external power source 106 which takes grid power directly or indirectly and uses it to charge the vehicle. For example, in some embodiments the set of variables include a power load variable on the external power supply for each of one or more other power- consuming devices such as household appliances or machinery consuming power from the electrical installation connected receiving grid power as the battery charger 106in a charging period. By modelling the power load on the electrical installation in a way that takes into account the use of other power consuming devices drawing power at the same time as the battery charger 106 is charging the battery of the electric vehicle, the maximum grid power drawn via the electrical installation can be managed and any limits not exceeded. This may help prevent overloading and/or one or more appliances, including the battery charger to failing to operate normally. The power- consuming devices may be battery-operated and connected to battery chargers connected to grid- power in some embodiments. One or more power-consuming devices may use the same battery charger 106 used to charge the battery of the vehicle 100 in some embodiments. However, the power-consuming devices may include one or more devices which are not battery operated and directly connected to the grid in some embodiments. [000122] The method 200 uses charging model which is trained to determine, for each of a plurality of charging periods, electricity cost and a probable risk of a battery state of energy not meeting a target charged battery energy state at the end of that charging period. The amount of charging power used by the charging power supply to charge the vehicle battery based on the current vehicle battery state of energy may be varied in some embodiments, for example, based on the price cost of the electricity consumed and/or responsive to other demands on the electrical installation to which the battery charger is attached and/or to other demands on grid power. For example, in periods of peak consumption, grid power may be limited to avoid cutting-out supply to other installations for example, on premises such as hospitals and the like. [000123] To account for the electricity cost varying over a plurality of charging periods, the charging model is configured to modify the reward function to disincentivise the use of power during peak periods in some embodiments. For example, the charging model vary the amount of charging power to minimise the electricity cost for charging the battery over one or more charging periods. For example, a charging model which uses Q-based learning algorithm where Q represents cumulative rewards comprising short and long term rewards based on the consequences of charging the battery meeting the cost constraints or not may be used in some embodiments. [000124] In such embodiments, the charging model which is implemented using the method 200 shown in Figure 4A is configured to use a Q-based learning algorithm configured to determine whether to charge the battery or not using cumulative rewards for reducing the charging cost whilst still achieving a target SoE by a desired future point in time. Unless trained, however, in other words, until the charging model has learnt what battery charger behaviours are likely to lead to the target SoE being reached in time, the battery charger may cause the battery to not be charged when a user wants to use the vehicle. To avoid this happening, it is useful to pre-train the charging model. Training may use historic user behaviour data obtained via the charging station 106 or another charging station and/or historic vehicle use data obtained from the vehicle or a remote data repository in some embodiments. [000125] Accordingly, in some embodiments, method 200 implements a dynamic charging model configured to be retrained from time to time using data gathered from implementing the model at a charging power supply and sends data for each charging period representing the start time, the end time, the initial battery charge state, the end battery charge set, the power consumed charging the battery and the cost of the power consumed charging the battery to the charging model S212. [000126] Figure 4B illustrates an example of how the charging model may be trained or retrained according to some embodiments of the disclosed technology in which the charging model is trained using a method 300 which implements a reinforcement learning algorithm. The training data may take the form of electrical energy pricing and demand data over a given time period such as 24 hours, sampled over a longer time period, for example, weeks or months or longer. The data shown in Figures 1A and 1B shows schematically examples of data which may be used to train the charging model. [000127] The charging model which is configured using method 300 may be used as a trained charging model in an embodiment of method 200. The trained charging model is configured to determine when to charge the vehicle based on predicted charging costs for an end state of battery energy to meet a predicted target charged battery energy state at the end of the one or more charging periods by inputting training data to the charging policy model S302 and iteratively processing the input training data to provide iterative output representing a charging cost S304. Each iteration performed comprises: comparing a charging cost with a target charging cost or with a charging cost from a previous iteration S306 and maximising cumulative rewards for reducing the charging cost S308 to achieve the target battery charge state. [000128] Each reward, r, of the maximised cumulative rewards, can be represented for each charging period as either a charge power consumption per unit time multiplied by a duration of time over which charge power is consumed multiplied by the energy consumption cost per unit of power in the case where the end of the charging period is reached and the target battery energy state is reached or, if the target battery energy state is not reached at the end of the charging period, by a total energy consumption cost for the duration of time the battery was charged plus a penalty term comprising the energy deficiency at the end of the charging period multiplies by a penalty constant. [000129] In some embodiments, each reward r of the maximised cumulative rewards can be represented by a reward function comprising the following expressions or computationally equivalent expressions: ∆E ∙ cost (notEnded 30] r = − ⁽s̅ ) [0001 ^ _{^^^^ ^^^^^^} ⁾ cost_{^^^^ ^^^^} + penalty(s̅) (else) [000131] where (action = true) [000132] (else) (SoE > 0) [000133] _^^^^^ (else) [000134] where P_ch is the charge power consumption per unit time, Δt is the duration of time over which charge power is consumed, SoEerror represents an energy deficiency defined as a difference between a target state of energy, SoE, of the battery and a current state of energy,, where costelec energy is the energy consumption cost, where notEnded(s̅) is a function returning true if the end of a charging episode is reached and t_norm >=1, and CP is a penalty constant which defines how a violation from target SoE is penalised. The state of battery energy may be normalised to 100% for a fully charged battery. [000135] In some embodiments, as shown in Figure 4B by the S302-S304-S306-S308-S310 dashed lines, method 300 may comprise a method 300a which initially trains the self-learning charging model off-line using training data comprising price data trajectories for a plurality of historic charging episodes/events. The method 300a may also, after each battery charging episode, gather as new training input data the input data to the charging model associated with the charging episodes and the charging model data associated with each charging episode ending which is output in S310, and, after a number of battery charging episodes, updating the training data S301 and retraining the charging model using method 300b. [000136] In charging model may be implementing using a computer-program product in some embodiments by an apparatus comprising the server 102 and/or battery charger 106. For example, in some embodiments, the computer-program product may comprise a set of instructions stored in a memory and comprising one or more modules or circuitry which, when loaded from the memory for execution by one or more processors or processing circuitry cause a charging model trained using an embodiment of one or more of the methods 300, for example as shown in Figure 4B, and then once trained, implemented in an embodiment of method 200 as shown in Figure 4A. In some embodiments, the trained charging model includes a set of power load variables for a charging power supply which comprise the following variables: a variable representing a current time of day, a variable representing a charging tariff for power drawn based on the current time of day, a variable representing a target charged battery energy state, and a variable representing a current energy state of the battery. [000137] In some embodiments, executing the instructions causes the charging model to map a current battery state of energy, a target battery energy state, and the duration of battery charging divided by the time of day spent charging to determine a charging cost to reach the target battery energy state. The charging model may comprise a self-learning model trained using a reinforcement machine learning to determine when to charge an electric vehicle based on predicted charging costs for an end state of battery energy to meet a predicted target charged battery energy state at the end of the one or more charging periods. For example, in some embodiments, the reinforcement learning model is configured to maximise cumulative rewards for reducing the charging cost, and may comprise a Q-learning algorithm such as one of the example Q-learning algorithms disclosed herein above. Such a reinforcement learning model is configured to maximise cumulative rewards for reducing the charging time. [000138] In some embodiments of the disclosed technology, the charging model is a dynamic charging model which is configured to be retrained from time to time using data gathered from implementing the model at a charging power supply, such as Figures 4A and 4B show collectively. [000139] The battery charger 106 may be referred to herein as a battery charger or charging apparatus may be used to implement the charging model in some embodiments. In some embodiments, however, server 102 is used to implement the charging model. Each of the battery charger 106 and/or the server, also referred to herein as server apparatus, 102 comprise suitable memory, one or more processors or processing circuitry, and computer code stored in the memory, so that by executing the computer code loaded from the memory the battery charger and/or server apparatus may be respectively configured to implement a method of charging a battery 101 using a trained learning charging model which uses a cumulative reward system according to the disclosed embodiments. [000140] In some embodiments, the computer code comprises a set of instructions stored in the memory, the set of instructions comprising one or more modules or circuitry such as Figure 5 shows schematically for the battery server 106 and Figure 6 shows schematically for the server 102. [000141] In Figures 6 and 7 it is assumed that method 200 is performed by the battery charger 106 and the training method(s) 300(a,b) are performed by the server 102. However, as mentioned above, it may be possible for the training method 300a to be initially performed by server 102, which then sends an initially trained charging model to the battery charger 106 such as Figure 5, described in more detail below shows, but later for the charging model to self-learn in some embodiments. In other embodiments, the initial pre-training may not take place, and the battery charger 106 only learns what is the best cause of action to follow. This may result in some inconvenience to users until the charger learns when use of the electric vehicle requiring a certain minimum level of battery charge is likely, as the user may have to adapt their journey to allow for recharging and/or use more conventional fuels in the case where hybrid vehicles are used. In some embodiments, the battery charger 106 may from time to time, receive retrained charging models from server 102 and/or may receive variables to update its charging model. [000142] In the example embodiment of the battery charger apparatus 106 shown in Figure 5, the apparatus comprises at least one or more processors or processing circuitry 402, memory 404 which holds computer code configured when executed to implement a method of charging a battery as disclosed herein. The method of charging the battery be implemented by executing code in the form, for example, of modules M202, M204, M206, M208, M210, and M212 where each module causes a corresponding method feature S202, S204, S206, S208, S210, S212 as shown in Figure 4A and described hereinabove to be implemented in some embodiments. For example, module S202 may be used to detect a current state of energy of a battery of a vehicle for example such as a battery of a vehicle which may be recharged using a battery charging to implement an embodiment of method 200 as disclosed herein. Accordingly, in some embodiments collectively modules S202- S212 cause the method 200 comprising method features S202, S204, S206, S208, S210, S212 as shown in Figure 4A and described herein above to be implemented. In Figure 6, the battery charger 106 is a communications enabled battery charger including a suitable communications module and receiver/transmitter circuitry 406 and may include an antenna to support wireless communications using one or more communications protocols with at least server 106 and soft-switch 104. For example, cellular or Wi-Fi communications protocols may be used to communicate with server 102 via a suitable cellular network or Wi-Fi network access point in some embodiments whereas Wi-Fi or Bluetooth™ communications protocols may be used to communicate with soft-switch 104. As shown in Figure 5, executing the charging model algorithm to implement the method 200 may result in an action to charge or stop charging the electric vehicle at a particular point in time, and this decision may be actuated by a soft-switch controller 408 is some embodiments causing the relay of the soft- switch to be actuated. In some embodiments, the controller 408 may cause a control signal to be sent to the soft-switch using either as a wireless signal or over a wired communications link. In some embodiments, the soft-switch 104 may be provided as a component part within the battery charger 106 however, in some embodiments, the soft-switch 104 may be retrofitted and configured as a separate component. [000143] Figure 6 shows an example embodiment of server apparatus 102 comprising one or more processor(s) or processing circuitry 502, memory 504 which holds computer code 510 which, when executed, causes the apparatus 102 to implement one or more training methods 300, 300a, 300b for configuring a charging model for a battery charger according to any of the disclosed embodiments. As shown in Figure 6, the charging model is configured to be trained using computer code provided in the form of one or more modules M301,M302,M304,M306, M308, and M310, where each module comprise code configured to implement the corresponding S301, S302,S304, S306, S308, and S310 features of the training method shown in Figure 4B and described hereinabove. [000144] Figure 5 shows schematically an example data flow when training a reinforcement learning charging model according to some embodiments of the disclosed technology. In Figure 5, the charging model Q-learning algorithm is initially trained by the server 102. [000145] This initial training may be advantageous as it helps limit or avoid any inconvenience to a user whose vehicle battery is less likely to reach a target SoE in the early stages of the battery charger’s self-learning unless the self-learning model is pre-trained to some extent. [000146] The server 102 sends the trained model to the battery charger 100 which provides charging power supply to vehicle 100 via a soft-switch 104. Base on the variables and model parameters determined by the training performed, for example, using a method such as method 300 shown in Figure 4B, the server 102 is able configure and reconfigure the charging model which is hosted on the battery charger 106 configured to provide a charging power supply to a connected vehicle 100 whenever the charging model outputs an action to charge the vehicle. Whenever the charging model determines an action to charge an electric vehicle should be taken by the battery charger 106, the battery charger 106 sends an actuation control signal to actuate the soft-switch to allow the vehicle (assuming it is connected) to be charged. In some embodiments, prior to starting charging, a check is performed to confirm if a vehicle is connected or not and an alert may be generated to flag to a user associated with the battery charger and/or vehicle to connect the vehicle for charging. [000147] As shown in Figure 7, the soft switch 104 may be configured to detect when a vehicle connects for subsequent charging and it may be configured to obtain the current state of battery energy. Alternatively, these steps may be performed by the battery charger via the soft- switch and the soft-switch only actuated to provide a power supply when actuated by the battery charger’s soft-switch controller 408. which is actuated by the charging power supply according to the model. [000148] As shown in Figure 7, the soft-switch 104 sends connected vehicle battery information to the battery charger 106 which inputs this into the trained charging model. The charging model then processes the input and outputs an action to charge or not charge the vehicle, or for example, when to start charging the connected vehicle. Once conditions are met to start charging, the battery charger generates a control signal to actuate the soft-switch 104 and once the soft-switch receives the control signal it actuates and allows the vehicle 100 to charge. [000149] In some embodiments, the vehicle may be an autonomous electric vehicle with an ADS configured to make tactical decisions for a control system, for example, it may determine when to dock at the battery charger for recharging. [000150] In some embodiments, the electric vehicle may be a heavy, also known as a heavy- duty, electric vehicle. A heavy-duty electric vehicle may comprise a wide range of different physical devices, such as combustion engines, electric machines, friction brakes, regenerative brakes, shock absorbers, air bellows, and power steering pumps. These physical devices are commonly known as Motion Support Devices (MSD). The MSDs may be individually controllable, for instance such that friction brakes may be applied at one wheel, i.e., a negative torque, while another wheel on the vehicle, perhaps even on the same wheel axle, is simultaneously used to generate a positive torque by means of an electric machine. The operation, particularly the autonomous operation, of a heavy- duty electric vehicle is accordingly more complex than the operation of a more light-weight vehicle such as a car and the power requirements more complex. [000151] Moreover, a heavy-duty vehicle may be electrically connected to a vehicle accessory which may also be charged via the battery charger 106. In some embodiments, the charging model may also monitor separately and/or collectively the state of charge of a connected vehicle accessory to the vehicle connected to the soft-switch and may also charge a battery of the connected vehicle accessory using a separate charging model for that vehicle accessory or using the same charging model as for the vehicle the accessory is electrically coupled to. [000152] Some, if not all, of the above embodiments may be implemented using computer program code which may be provided as software or hardcoded, for example, as a computer program product configured to be used by a device mounted on or integrated in the battery charger 106 or server 102. [000153] For example, the methods 200, 300 described above may be at least partly implemented through one or more processors, such as, the processors or processing circuitry 402, 502 shown in Figures 5 and 6 together with computer program code 410, 510 for performing the functions and actions of the embodiments herein. The program code mentioned above may also be provided as a computer program product, for instance in the form of a data carrier carrying computer program code or code means for performing the embodiments herein when being loaded into the processing circuitry in a suitable controller or control unit of the apparatus 106, 104. [000154] The data carrier, or computer readable medium, may be one of an electronic signal, optical signal, radio signal or computer-readable storage medium. [000155] Those skilled in the art will also appreciate that the processing circuitry and the memory or computer readable storage unit described above may refer to a combination of analog and digital circuits, and/or one or more processors configured with software and/or firmware, e.g. stored in a memory, that when executed by the one or more processors such as the processing circuitry perform as described above. One or more of these processors, as well as the other digital hardware, may be included in a single application-specific integrated circuit (ASIC), or several processors and various digital hardware may be distributed among several separate components, whether individually packaged or assembled into a system-on-a-chip (SoC). [000156] The controllers 408, 508 may also comprise or be capable of controlling how signals are sent wirelessly via antenna 70 in order for the vehicle 12 to communicate via one or more communications channels with remote entities, for example, a site back office. [000157] The communication channels may be point-to-point, or networks, for example, over cellular or satellite networks which support wireless communications. The wireless communications may conform to one or more public or proprietary communications standards, protocols and/or technologies, including but not limited to Global System for Mobile Communications (GSM), Enhanced Data GSM Environment (EDGE), high-speed downlink packet access (HSDPA), wideband code division multiple access (W-CDMA), code division multiple access (CDMA), time division multiple access (TDMA), Bluetooth, Wireless Fidelity (Wi-Fi) (e.g., IEEE 802.11a, IEEE 802.11b, IEEE 802.11g and/or IEEE 802.11n), voice over Internet Protocol (VoIP), Wi-MAX, a protocol for email (e.g., Internet message access protocol (IMAP) and/or post office protocol (POP)), instant messaging (e.g., extensible messaging and presence protocol (XMPP), Session Initiation Protocol for Instant Messaging and Presence Leveraging Extensions (SIMPLE), and/or Instant Messaging and Presence Service (IMPS)), and/or Short Message Service (SMS)), or any other suitable communication protocol, including communication protocols not yet developed as of the filing date of this document. [000158] The operating systems of the apparatus 106, 108 and of the soft-switch 104 may further various software components and/or drivers for controlling and managing general system tasks (e.g., memory management, storage device control, power management, etc.) and for facilitating communication between various hardware and software components. [000159] Figure 8 shows an example embodiment of a further aspect of the disclosed technology which relates to a charging model which seeks to control, in an adaptive and optimal manner, which electric vehicles of a plurality of electric vehicles shall have their batteries 101a,b,c charged or not charged in any given time period. [000160] In Figure 8, a very simple example of a grid power distribution network 110 is shown schematically where a power source 118, for example, a gas or coal or nuclear power plant, or hydroelectric or wind-powered source, is configured to supply electricity which is distributed via a series of transmission sub-stations 116 (only one is shown in Figure 8 for clarity) to a distribution sub-station 114 configured to provide power to one or more sub-areas 120 of the grid network 110. As the distribution station 114 may receive electrical power at a higher voltage to that used in a local power distribution area 120, one or more transformers 112a,b may be used to step- down the voltage to a level where it can be more safely distributed to premises and/or appliances such as battery chargers 106a,b,c within the local power distribution area 120. [000161] As shown in Figure 8, an example of a local power distribution area 120 comprises a server 102, and a plurality of battery chargers 106a,b,c, each controllable via a software switch 104a,b,c for recharging a battery system 101a,b,c, of an attached electric vehicle such as an electric heavy vehicle 100a,b,c. The plurality of electric vehicles 100a, 100b, 100c may form a fleet of electric heavy vehicles and/or electric heavy vehicle accessories in some embodiments of the disclosed technology which are configured to communicate with the server 102, for example, a back-office server for the fleet of vehicles. [000162] In some embodiments, an electric heavy vehicle may have one or more connected accessories such as a trailers or container attached and electrically coupled to the electric heavy vehicle. Such accessories may be configured to share the vehicle’s battery energy resource and/or use their own separate batteries An electric vehicle with one or more such electrically connected accessories is connected to battery charger 106 via soft-switch 104, it may accordingly charge both its own on-board battery 101 as well as the battery of a connected vehicle accessory in some embodiments. Of course, if the vehicle battery is fully charged, in some embodiments, it may be possible to only recharge the battery of a connected accessory via the electric vehicle or by directly connecting the accessory’s battery system to the electric battery charger 106. [000163] A charging model may be used to generate a charging policy for determining when each vehicle’s battery (and/or the battery of any connected accessories in some embodiments) should be charged in a given time-period. In some embodiments, the charging model may treat a battery of a connected vehicle accessory as part of a battery system including the vehicle battery 101. Alternatively, however, in some other embodiments, the accessory may be regarded as just another electric vehicle and the accessory’s battery may be regarded as a battery of another electric vehicle in the fleet of vehicles by the charging model. [000164] It is also possible for the electric vehicles 100a,b,c to be autonomous or semi- autonomous electric vehicles or remotely operated electric vehicles in some embodiments. Such electric vehicles 100a,b,c, will also need to be charged from time to time to ensure their battery systems have sufficient energy for them to go about their allocated tasks at allocated times. [000165] Each electric vehicle may each be connectable via a soft-switch or similar relay apparatus 104a, 104b, 104c to a corresponding individual battery charger 106a, 106b, 106c. Each of one or more or all of the vehicles 100a-100c may be concurrently connected to a respective one of the plurality of battery chargers 106a, 106b, 106c via a respective one of the soft-switches 104a- 104c, however, being connected does not automatically actuate the soft-switch 104a-104c so that electrical power is provided to charge the vehicle batteries by the battery chargers 106a-106c. Instead, each soft-switch or relay 104a, 104b, 104c functions in a similar away to soft-switch 104 illustrated in Figure 1C described above in that it can be actuated using an electrical control signal to allow a connected vehicle battery 101a,b,c, to be charged from grid power by each respective vehicle 100a, 100b, 100c. Each soft-switch 104a,b,c can also be actuated using an electrical control signal to disconnect a battery 101a,b,c, from the grid power distribution network 110. [000166] As shown schematically in Figure 8, a software agent executing on a remote server 102 may be configured to commanding the soft-switches or similar relays 104a,104b,104c based on data communicated from the battery charging apparatus 106a, 106b, 106c. Server 102 may communicate with the soft-switches or relays 104a,b,c directly and/or via the battery charging apparatus, using a suitable wired or wireless communications protocol so as to control actuation of the soft-switches or relays depending on the charging actions determined by the charging model executing on server 102. [000167] The dashed line between battery chargers 106b, 106c and transformer 112a represents a power transmitting cable 130 connected between a power distribution grid network 110 and a power distribution sub area 120 such as, for example, an industrial customer power distribution area 120 configured to supply power to server 102 and battery chargers 106a,b,c. A network electricity sub-station 114 in the power distribution network 110 will typically supply power to this type of electrical power distribution sub-area 120 to cover power demands of up to around 2000 kW/h, or 2 Megawatts/h per sub-area of the grid. In some embodiments, each electricity sub- station may be configured to supply only one distribution sub-area, but in others, it is possible for other sub-areas to be supplied with power. It is also possible for one sub-area to be provided, for example, with single-phase electricity whereas one or more other sub-areas may be provided, for example, with three-phase electricity. [000168] The electrical power used to charge a battery 101a,b,c, of an electric heavy vehicle 100a,b,c, such as the trucks shown schematically in Figure 8 may be of the order of 50kW/hour to 500kW/hour. Based on a fleet comprising, for example, twenty or so such electric heavy vehicles, each electric heavy vehicle requiring 20 kW/hour of power to charge its battery system 101, results in a potential power demand of typically ̴ 1000 kW/hour for however many hours it takes to charge the battery systems of all of the electric heavy vehicles in the fleet of vehicles. As this would be over half of the total “normal” power output by the grid power distribution network 110 to the power distribution sub-network or sub-area 120, it could negatively impact other users of electrical power supplied by the same substation 112. This means that to ensure there is sufficient energy available for all of the devices which may require power from that sub-station, some sort of prioritization is likely to be needed so that not all heavy vehicles 100a,b,c, attempt to be charged at the same time. [000169] Those skilled in the art will appreciate that whilst Figure 8 shows three electric vehicles 100a,b,c, in practice, any number of electric vehicles and/or vehicle accessories having batteries which may need to be recharged from time to time may operate and need to use battery chargers 106a,b,c, in a sub-area 120 at any given point in time. Accordingly, the disclosed embodiments should not be limited to just three vehicles 100a,b, c as shown in the example embodiments of Figure 8. As the number of vehicles in a fleet rises, so too will the need to manage how much power is drawn at any given time from the power distribution network 110. [000170] As the number of electric vehicles rises in any power distribution sub-area, especially if that area includes a large fleet of electric heavy vehicles. The conclusion is that often, especially for larger fleets, some sort of prioritizing of which vehicles are charged and when is advantageous not just to manage electrical pricing but also to manage power demands. [000171] The self-learning system disclosed herein above with reference to Figures 1 to 7 and the accompanying description hereinabove sought to use a reinforcement learning based charging model to implement a charging policy to manage the timing of energy consumption for recharging a single vehicle so as to manage grid electricity expenses and ideally to avoid recharging during periods of peak demand, which are more costly accordingly, for a single vehicle being charged. However, such a model requires certain adaptation when extending to how to manage charging multiple vehicles in a way that manages power demands and/or electricity costs. [000172] The disclosed technology uses the techniques 200 disclosed hereinabove for managing recharging a battery of a single electric vehicle using a charging model which may be trained for example, using a method such as method 300 disclosed herein to determine if any of the plurality of vehicles 100a,b,c should be first connected to the power distribution network 120, and then if an electric vehicle is determined by the charging model implemented using method 200 to be allowed to be connected to receive charging power from the power distribution sub-area network 120, and then it identifies which vehicles should be connected to which individual power stations 106a,b,c, so as to receive charging power during one or more time-periods. [000173] In this way, a sub-set of the electric vehicles which form a fleet of electric vehicles can be identified for connection to individual battery chargers 106a,b,c by at least determining or using a known maximum power limit for the amount of power that should be provided to the fleet of electric vehicles by the set of battery chargers 106a, 106b, 106c and then maintaining the amount of power that is transmitted to recharge the batteries of the fleet of vehicles below the maximum power limit. In addition, in some embodiments, the disclosed technology seeks to minimize a standard deviation of the battery state of energy levels so these all remain within acceptable levels. In other words, ideally no vehicles should run out of battery energy whilst another vehicle has its battery recharged to full capacity based on the charging model. [000174] In some embodiments, in addition, the charging model seeks to minimize the total deviation from a target SoE of vehicle batteries across the fleet of vehicles. In other words, ideally no vehicle should have their battery capacity fall below a certain percentage of their target SoE in some embodiments. In some embodiments, the certain percentage target SoE may be replaced or accompanied by a lower threshold for battery SoE. [000175] Such a charging model may be implemented by finding solutions to the following optimization problem which seeks to minimise a recharging model cost, min cost(u) with respect to ^∑ _^^^..^ P_{^^ ^} (u)< P_{^^ ^^^ ^^^^^} where the cost = tad⁽u, ^{^} S^{^}o^{^^}E^{^}) _{+ W ∙ std}(_u, ^{^} _S ^{^} _o ^{^^} _E ^{^}) , where tad(u,^{^} S^{^}o^{^^}E^{^}) = ∑_^^^..^ nb(SoE_{^^^^^ ^}(t + ∆T) ) and std( mean(SoE^⁽t + ∆T⁾^)^{^} [000176] Here n reflects the number of vehicles in the fleet, Pch i refers to the power consumed charging the ith vehicle of the fleet to the target SoE for that vehicle, Pch max fleet refers to the maximum amount of power that the fleet can draw from the connected grid distribution network 110 in the power distribution sub-area 120 via which the battery chargers 106a,b,c are connected to the grid 110. the SoE is a battery state of energy, a normalized number.100% for a fully charged battery, SoE_error is the target SoE minus the actual SoE, nb(x) is a function zero for a negative argument, else the argument itself. Nb(x) acts accordingly as a negative values blocker. Action refers to a Boolean decision taken by a charge policy, which is true if charging of any vehicle is recommended, and W is a weighting hyper parameter, which may be initially set to one. The term u is the control variable, expressing the connection policy for whether a vehicle I of the plurality of n vehicles be connected to the grid power supply or not. It is a binary string. Every position in the string corresponds to a vehicle. A binary value of one may mean charge in some embodiments. The values of u may be based on the actions or control logic output by a charging model such as a charging model described herein above which is self-learning and which, once trained, may be used to implement a charging policy. As mentioned above, in some embodiments where a Q-learning reinforcement algorithm is used to determine actions for charging or not charging individual vehicles in the fleet, the decisions may be stored in a look-up table or in neural networks in some embodiments which allows the charging model to be implemented off-line and just the decisions retrieved later from memory when the variables input to the charging model match input conditions associated with a stored charging logic value. [000177] If there are three vehicles in a fleet, then the number of string variant settings are 2³=8. The term t+∆t indicates the cost is to be minimised taking into account the consequences at some time ahead at the end of the charging period ∆t, of now (as in the current time-step) taking a specific control action, for example, if a specific u setting is applied in the current time-step of the charging model. [000178] In Figures 9A and 9B, illustrate schematically consequences of letting two vehicles 100a, 100b be charged for ∆t minutes in the form of a graph of % battery SoE (y-axis) vs charging time period Δt (x-axis). In Figures 9A, 9B, a SoE of each of three electric vehicles 100a, 100b, 100c, for example, the electric vehicles 100a, 100b, 100c shown in Figure 8 and described above for example is shown as a % of the full battery energy capacity. [000179] When electric vehicles 100a, 100b have a % SoE below a target % SoE, the charging policy implemented at the start of any charging time period may affect the fleet performance in future at the end of the charging time period. This is illustrated schematically in Figures 9A and 9B which where each differently filled column shows a % SoE for each vehicle 100a,b,c. For example, the % SoE of the battery system 101a of vehicle 100a may be represented by the left-hand side column of the chart in Figures 9A and 9B with a horizontal line fill, the % SoE of the battery system of vehicle 100b may be represented by the middle column which has a dotted fill, and the % SoE of vehicle 100c may be represented by the right hand side column with a plain/no fill. [000180] Figures 9A and 9B show two different examples of how the % SoE of vehicles 100a and 100b may change from the start of a charging time period ∆t to the end of the charging time period based on the charging policy implemented for the fleet of vehicles. In both scenarios represented by Figures 9A and 9B, the vehicle 100c is not charged during the period shown as it has a SoE above its target SoE. The darker shaded areas in Figures 9A an 9B illustrate SoE target deviations. [000181] As shown in Figure 9A, the charging model appears to be providing optimal control over when each vehicle 100a,b is charged and to what SoE, because on the left hand side of the charge, at the end of the charging period, both the tad, the sum of SoE target deviations has decreased and the standard deviation, in other words, the spread, of the future actual SoE values, have decreased. As the deviations have reduced for vehicle 100a, and vehicle 100b has reached its target SoE, the charging model appears to be making good decisions for the fleet of vehicles. [000182] However, if the charging model determines power is to be restricted to only charge one of the three vehicles at a given time, different consequences result. For example, consider an example scenario where only vehicle 100a corresponding the left hand side (horizontal line filled) column is charged based on the charging policy determined by a charging model according to some embodiments of the invention, charging this vehicle reduces its SoEerror by the end of the charging period Δt as the right-hand side set of figures indicates, however, vehicle 100b will not have been charged. At best it may maintain its SoE at the start of the charging period as shown on the left-hand side of Figure 1. However, if instead, the charging policy had selected to only charge vehicle 100b, the middle column, then at the end of the charging period, the SoE of vehicle 100a would not have changed, and as a result this would have resulted in a relatively worse spread, i.e. a standard deviation of future SoE values of vehicle A would be quite large (as the SoE % shown at the start would then be maintained at the end, this is illustrated schematically in Figure 9B. [000183] Figure 10 A shows a flow chart for a method 600 of managing the charging of a plurality of vehicles, for example, n vehicles. In Figure 10A, based on parameters including the current average SoE levels of the n vehicles, an electricity unit price, a charging time and SoE levels changes for each vehicle, a method 600 of power management for charging a plurality of batteries of a fleet of electric vehicles is implemented. [000184] In some embodiments, the method 600 of power management for charging a plurality of batteries of a fleet of vehicles comprises determining a set of variables for each vehicle in the fleet, the set of variables including a current battery state of energy variable and a target battery state of energy at the end of a charging period in S602, and determining in S604 if power should be provided to charge one or more vehicles in the fleet using at least one external power source using a self-learning charging model. An example of a self-learning charging model which may be used to implement the disclosed technology is one which uses reinforcement learning such as an embodiment of the Q-learning charging model described herein above,. Such a model may be configured to map the set of variables to an action to charge the vehicle battery or not to charge the vehicle, based on one or more charging constraints for the fleet of vehicles. Examples of variables include a current time of day, a charging tariff for the current time of day, the target charged battery energy state and the current energy state of the battery. [000185] The charging constraints may comprise one or more charging constraints of the method 200 described herein above. For example, a charging constraint for the fleet of vehicles may comprise a cost constraint for charging the fleet of vehicles. [000186] In some embodiments, a charging constraint for the fleet of vehicles comprises a power constraint representing a power limit for the amount of power that can be transmitted to the fleet of vehicles at any given point in time. [000187] In some embodiments, the charging model is configured to minimize a standard deviation of battery state of energy levels across the fleet of vehicles. [000188] In some embodiments, the charging policy is configured to minimize a total deviation from a target battery state of energy level across the fleet of vehicles. [000189] In some embodiments, for each vehicle in the fleet, the current battery state of energy is determined when that vehicle is connected to an external power supply and the method further comprises, if that vehicle is determined to receive power using the charging policy, configuring the external power supply to provide power to charge the vehicle. [000190] The external power supply may be configured to provide power to charge a battery of an electric vehicle and/or an electrically connected vehicle accessory by actuating a soft switch or relay. The method 600 may accordingly include configuring an external power supply such as a battery charger 106a,b, c to provide power to charge a vehicle battery system by actuating the soft switch or relay 104a, b,c in some embodiments. [000191] In some embodiments of the method 400, for each vehicle 100a, 100b, 100c in the fleet of vehicles, the charging model policy may be configured to determine, for each of a plurality of charging periods, an electricity cost and a probable risk of a battery SoE not meeting a target charged battery SoE at the end of each charging period. [000192] The charging model used in the above method 400 may be used to implement a charging policy such as the example the charging policy 500 shown schematically in the flow- chart of Figure 10B. In Figure 10B, a method 700 of implementing a charging policy for power management when charging a plurality of batteries of a fleet of vehicles comprises in S702 determining if any vehicle is allowed to be connected to the grid, for example, based on inputting the average of present SoE levels of the vehicles of the fleet into a charging model. If the charging model output indicates an action should be taken to not charge any vehicles, for example, if the charging model outputs an action = 0 then the soft-switches 104a,b,c, for all three vehicles 100a,b,c shown in Figure 8 may be activated to disconnect those vehicles from the energy supplied by battery chargers 106a,b,c in S704. However, if the variables input to the charging model such as those indicated above as variables of method 400, result in an output with an action value of 1, then instead the method must determine which vehicles of vehicles 100a,b,c shall be individually able to receive charging power from their respective battery chargers 106a,b,c by actuating soft-switches 104a,b,c, in S706. S506 may be implemented by determining a binary control string which controls which individual vehicles, say vehicle 100a, 100b should receive power by actuating the soft switches 104a, 104b of respective battery chargers 106a,106b in S708. [000193] The action values 0, and 1 indicated in Figure 10B represents the charge logic determined from the output of the charging model, in other words, the output determined using a suitable reinforcement learning algorithm in some embodiments which may be trained using data such as that shown in Figures 1A and 1B obtained for the plurality of different electric vehicles forming the fleet which indicates if charging should happen at a given point of time to optimize the model and ideally achieve a target SoE for each vehicle in the fleet. [000194] If instead of implementing the above methods, a decision was always taken to only charge electric vehicles such as heavy vehicles with the lowest SoE at any given point of time, this would ignore that the charging power is SoE dependant. A low SoE level can use a higher charging power than is advisable when the SoE is at a high level. Accordingly, only charging heavy vehicles with the lowest SoE may require the use of more electricity from the grid than can be supplied at any given point, and accordingly, in such situations, it may be better to charge, for example, the lowest level SoE heavy vehicle and just some of the higher SoE level electric heavy vehicles to reduce power consumption whilst ensuring a maximum number of vehicles are likely to be charged to a desired SoE (in other words, more likely to be operational at the end of a charging period for their assigned tasks). [000195] In some embodiments, the charge or not logic presented by the action value may set charging power restrictions for all of the plurality of vehicles, in other words, for the full fleet. This may allow, for example, at least one or a few vehicles to be allowed to be charged even if electricity prices and/or power demands are very high. It may also be possible in some embodiments to take into account a role or priority variable for an electric vehicle to determine if it should be allowed to be charged. For example, at a hospital site, recharging an electric ambulance may be prioritized over a laundry van. At a construction site, recharging an unloading vehicle may be prioritised over a hospitality truck. A vehicle with a refrigerated container attached, where the refrigerated container uses the vehicle battery system for power or which has a battery system which is also charged when the vehicle’s battery system is charged may be priorities over a vehicle without any attached vehicle accessories for example. [000196] Figure 11A shows an example of a server 102 which comprise suitable processors and memory as described above in the context of Figure 6, but which implements an embodiment of method 600 shown in Figure 10A. In Figure 11A, the computer code 510 comprise one or more modules or circuitry M602 or M604 which when executed cause an embodiment of method 600 to be implemented by server 102. For example, module M602 may be configured to implement step S602 and module M604 may be configured to implement S604 shown in Figure 10A and described herein above. [000197] Figure 11B shows an example of a server 102 which comprise suitable processors and memory as described above in the context of Figure 6, but which implements an embodiment of the charging policy using method 700 as shown in Figure 10B. In Figure 11B, the computer code 510 comprise one or more modules or circuitry M702, M704, M706, and M708 which when executed cause an embodiment of method 700 to be implemented by server 102. For example, module M702 may be configured to implement step S702, module M704 may be configured to implement S704, module M706 may be configured to implement S704, and module M708 may be configured to implement S708 shown in Figure 10B and described herein above. [000198] Where the disclosed technology is described with reference to drawings in the form of block diagrams and/or flowcharts, it is understood that several entities in the drawings, e.g., blocks of the block diagrams, and also combinations of entities in the drawings, can be implemented by computer program instructions, which instructions can be stored in a computer-readable memory, and also loaded onto a computer or other programmable data processing apparatus. Such computer program instructions can be provided to a processor of a general purpose computer, a special purpose computer and/or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer and/or other programmable data processing apparatus, create means for implementing the functions/acts specified in the block diagrams and/or flowchart block or blocks. [000199] In some implementations and according to some aspects of the disclosure, the functions or steps noted in the blocks can occur out of the order noted in the operational illustrations. For example, two blocks shown in succession can in fact be executed substantially concurrently or the blocks can sometimes be executed in the reverse order, depending upon the functionality/acts involved. Also, the functions or steps noted in the blocks can according to some aspects of the disclosure be executed continuously in a loop. [000200] The description of the example embodiments provided herein have been presented for the purposes of illustration. The description is not intended to be exhaustive or to limit example embodiments to the precise form disclosed, and modifications and variations are possible in light of the above teachings or may be acquired from practice of various alternatives to the provided embodiments. The examples discussed herein were chosen and described in order to explain the principles and the nature of various example embodiments and its practical application to enable one skilled in the art to utilize the example embodiments in various manners and with various modifications as are suited to the particular use contemplated. The features of the embodiments described herein may be combined in all possible combinations of methods, apparatus, modules, systems, and computer program products. It should be appreciated that the example embodiments presented herein may be practiced in any combination with each other. [000201] It should be noted that the word “comprising” does not necessarily exclude the presence of other elements, features, functions, or steps than those listed and the words “a” or “an” preceding an element do not exclude the presence of a plurality of such elements, features, functions, or steps. It should further be noted that any reference signs do not limit the scope of the claims, that the example embodiments may be implemented at least in part by means of both hardware and software, and that several “means”, “units” or “devices” may be represented by the same item of hardware. [000202] The various example embodiments described herein are described in the general context of methods, and may refer to elements, functions, steps or processes, one or more or all of which may be implemented in one aspect by a computer program product, embodied in a computer- readable medium, including computer-executable instructions, such as program code, executed by computers in networked environments. [000203] A computer-readable medium may include removable and non-removable storage devices including, but not limited to, Read Only Memory (ROM), Random Access Memory, RAM), which may be static RAM, SRAM, or dynamic RAM, DRAM. ROM may be programmable ROM, PROM, or EPROM, erasable programmable ROM, or electrically erasable programmable ROM, EEPROM. Suitable storage components for memory may be integrated as chips into a printed circuit board or other substrate connected with one or more processors or processing modules, or provided as removable components, for example, by flash memory (also known as USB sticks), compact discs (CDs), digital versatile discs (DVD), and any other suitable forms of memory. Unless not suitable for the application at hand, memory may also be distributed over a various forms of memory and storage components, and may be provided remotely on a server or servers, such as may be provided by a cloud-based storage solution. Generally, program modules may include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. Computer-executable instructions, associated data structures, and program modules represent examples of program code for executing steps of the methods disclosed herein. The particular sequence of such executable instructions or associated data structures represents examples of corresponding acts for implementing the functions described in such steps or processes. [000204] The memory used by any apparatus whatever its form of electronic apparatus described herein accordingly comprise any suitable device readable and/or writeable medium, examples of which include, but are not limited to: any form of volatile or non-volatile computer readable memory including, without limitation, persistent storage, solid-state memory, remotely mounted memory, magnetic media, optical media, random access memory (RAM), read-only memory (ROM), mass storage media (for example, a hard disk), removable storage media (for example, a flash drive, a Compact Disk (CD) or a Digital Video Disk (DVD)), and/or any other volatile or non-volatile, non-transitory device readable and/or computer-executable memory devices that store information, data, and/or instructions that may be used by processing circuitry. Memory may store any suitable instructions, data or information, including a computer program, software, an application including one or more of logic, rules, code, tables, etc. and/or other instructions capable of being executed by processing circuitry and, utilized by the apparatus in whatever form of electronic apparatus. Memory may be used to store any calculations made by processing circuitry and/or any data received via a user or communications or other type of data interface. In some embodiments, processing circuitry and memory are integrated. Memory may be also dispersed amongst one or more system or apparatus components. For example, memory may comprises a plurality of different memory modules, including modules located on other network nodes in some embodiments. [000205] In the drawings and specification, there have been disclosed exemplary aspects of the disclosure. However, many variations and modifications can be made to these aspects which fall within the scope of the accompanying claims. Thus, the disclosure should be regarded as illustrative rather than restrictive in terms of supporting the claim scope which is not to be limited to the particular examples of the aspects and embodiments described above. The invention which is exemplified herein by the various aspects and embodiments described above has a scope which is defined by the following claims.

Claims

CLAIMS 1. A computer-implemented method of power management for charging a plurality of batteries of a fleet of vehicles, each vehicle comprising at least one battery, the method comprising: determining a set of variables for each vehicle in the fleet, the set of variables including a current battery state of energy variable and a target battery state of energy at the end of a charging period (S602); and determining if power should be provided to charge one or more vehicles in the fleet using at least one external power source based on output of a self-learning charging model configured to map input comprising the set of variables to output comprising an action to charge the vehicle battery or not to charge the vehicle, based on one or more charging constraints for the fleet of vehicles (S604).

2. The method of claim 1, wherein a charging constraint for the fleet of vehicles comprises a cost constraint for charging the fleet of vehicles.

3. The method of claim 1 or 2, wherein a charging constraint for the fleet of vehicles comprises a power constraint representing a power limit for the amount of power that can be transmitted to the fleet of vehicles at any given point in time.

4. The method of any one of claims 1 to 3, wherein the charging model is configured to minimize a standard deviation of battery state of energy levels across the fleet of vehicles.

5. The method of any one of claims 1 to 4, wherein the charging policy is configured to minimize a total deviation from a target battery state of energy level across the fleet of vehicles.

6. The method of any one of claims 1 to 5, wherein for each vehicle in the fleet, the current battery state of energy is determined when that vehicle is connected to an external power supply and the method further comprises, if that vehicle is determined to receive power using the charging policy, configuring the external power supply to provide power to charge the vehicle.

7. The method of any one of claims 1 to 6, configuring the external power supply to provide power to charge that vehicle comprises actuating a soft switch or relay.

8. The method of any one of claims 1 to 7, wherein for each vehicle in the fleet, the charging model policy is configured to determine, for each of a plurality of charging periods, electricity cost and probable risk of a battery state of energy not meeting a target charged battery energy state at the end of each charging period.

9. The method of any one of the previous claims, wherein the set of variables include a current time of day, a charging tariff for the current time of day, the target charged battery energy state and the current energy state of the battery.

10. The method of any one of the previous claims, wherein using the self-learning model includes performing, for each vehicle of the fleet of vehicles, a method (200) for charging an electric vehicle (100) at a charging power source (106), wherein the method (200) comprises: detecting a current state of energy of a battery of a vehicle (S202); determining a target charged state of energy of the battery at a future point in time (S204); and determining a point in time when power should be provided to charge the vehicle from the charging power source based on the detected current state of energy of the battery and the determined target charged state of energy of the battery (S206) so that the future point in time is a predicted end of a charging time period, wherein the future point in time is determined using a vehicle battery charging model configured to determine the target charged battery energy state based on a predicted user demand for power from the charged vehicle at the end of the charging period and at least one charging constraint for the charging power source.

11. The method of claim 10, wherein the method further comprises training the vehicle battery charging model to: map input to the model comprising a set of power load variables of the charging power source to an output representing a charging action to charge the battery or a non-charging action to not charge the battery by rewarding for long-term and short-term consequences of the charging or non- charging actions.

12. The method of either claim 10 or 11, wherein the method further comprises: when the battery is determined to start charging at the future point in time, based on the determined current state of energy of the battery and a determined charging action of the dynamic vehicle battery charging model, configuring the external charging power supply to automatically provide power to charge the vehicle by actuating a soft switch (S208).

13. The method of any one of claims 10 to claim 12, wherein based on the predicted future point in time for achieving the determined target charged battery state, the method further comprises, responsive to determining when power should start to be provided to charge the vehicle to achieve the predicted target charged battery state by the determined future time, causing an alert to be provided to a user to connect the vehicle to a power supply if the vehicle is not already connected (S210) at or in advance of the determined start time.

14. The method of any one of claims 10 to 13, wherein at least one charging constraint is a charge or not condition based on an objective to minimize long term energy costs.

15. The method of any one of claims 10 to 14, wherein the set of power load variables of the external power source includes a power load variable of an external power supply to the charging power source, wherein the external power supply is connected to one or more other power- consuming devices consuming power in a charging period.

16. The method of claim 15, wherein the charging constraint comprises a maximum available power constraint for the external power supply to provide power to the charging power supply.

17. The method of claim 15, wherein the power-consuming devices include one or more devices which are not battery operated.

18. The method of any one of claims 10 to 17, wherein the charging model is trained to determine, for each of a plurality of charging periods, electricity cost and a probable risk of a battery state of energy not meeting a target charged battery energy state at the end of that charging period.

19. The method of any one of claims 10 to 18, wherein the method further comprises: varying the amount of charging power used by the charging power supply to charge the vehicle battery based on the current vehicle battery state of energy.

20. The method of any one of claims 10 to 19, wherein the method further comprises: obtaining data generated by implementing the dynamic vehicle battery charging model at the charging power supply; using the gathered data as a training data set for training the dynamic battery vehicle charging model, wherein the gathered data comprises, for each charging period, data representing the start time, the end time, the initial battery charge state, the end battery charge set, the power consumed charging the battery and the cost of the power consumed charging the battery to the charging model (S212), and re-training the trained dynamic battery vehicle charging model by inputting the gathered data into the trained model.

21. The method of any one of claims 1 to 9, wherein the self-learning charging model is trained using reinforcement learning for use in a method of any one of claims 1 to 20, the trained model being configured to determine when to charge the vehicle based on predicted charging costs for an end state of battery energy to meet a predicted target charged battery energy state at the end of the one or more charging periods, the method comprising: inputting training data to the charging policy model (S302) ; and iteratively processing the input training data to provide iterative output representing a charging cost (S304), wherein each iteration comprises: comparing a charging cost with a target charging cost or with a charging cost from a previous iteration (S306); and maximising cumulative rewards for reducing the charging cost (S308) to achieve the target battery charge state.

22. The method of claim 21, wherein each reward, r, of the maximised cumulative rewards, can be represented for each charging period as either: a charge power consumption per unit time multiplied by a duration of time over which charge power is consumed multiplied by the energy consumption cost per unit of power in the case where the end of the charging period is reached and the target battery energy state is reached; or, if the target battery energy state is not reached at the end of the charging period, a total energy consumption cost for the duration of time the battery was charged plus a penalty term comprising the energy deficiency at the end of the charging period multiplies by a penalty constant.

23. The method of claim 22, wherein each reward r of the maximised cumulative rewards is determined using a reward function based on a charge power consumption per unit time, a duration of time over which charge power is consumed, a battery energy deficiency comprising a difference between a target state of battery energy and a current state of battery energy, an energy consumption cost, and wherein the reward function indicates if an end of a charging episode is reached or not, and includes a penalty term defining how a violation from a target state of energy is to be penalised.

24. An apparatus comprising a computer-program product comprising a set of instructions stored in a memory and comprising one or more modules or circuitry which, when loaded from the memory for execution by one or more processors or processing circuitry of the apparatus cause the apparatus to implement a method according to any one of claims 1 to 9.

25. An apparatus comprising a computer-program product comprising a set of instructions stored in a memory and comprising one or more modules or circuitry which, when loaded from the memory for execution by one or more processors or processing circuitry of the apparatus cause the apparatus to implement a method according to any one of claims 10 to 20.

26. An apparatus comprising a computer-program product comprising a set of instructions stored in a memory and comprising one or more modules or circuitry which, when loaded from the memory for execution by one or more processors or processing circuitry of the apparatus cause the apparatus to implement a method according to any one of claims 21 to 23.

27. An apparatus 102 comprising a computer-program product comprising a set of instructions stored in a memory and comprising one or more modules or circuitry which, when loaded from the memory for execution by one or more processors or processing circuitry of the apparatus cause the apparatus to implement a method according to any one of claims 1 to 9, a method according to any one of claims 10 to 20, and a method according to any one of 21 to 23.

28. A fleet vehicle charging management system, the fleet comprising a plurality of electric vehicles 100a,b,c, wherein the charging management system comprises: an apparatus 102 according to claim 27; a plurality of soft-switches (104a,b,c); a plurality of battery chargers (106a,b,c) configured to be connected to a grid power supply (110, 120), wherein each respective one of the battery chargers is configured to provide a charging power supply to a connected electric vehicle 100a,b,c of the plurality of vehicles 100a,b,c via a respective one of the soft-switches 104 according to a decision based on output from a self-learning battery charging model, wherein the battery charging model is configured to minimise a financial cost and/or a power demand of implementing a connection policy control variable for charging the vehicle fleet.

29. The fleet vehicle charging management system of claim 28, wherein, for each electric vehicle (100a,b,c) connected to a respective one of the battery chargers (106a,b,c) via a soft-switch (104a,b,c) the system is configured, responsive to the apparatus (102) implementing a battery charging model policy which selectively determines which of the plurality of vehicles is to be charged based on a SoE deviation from the average SoE of the vehicle fleet, and if a vehicle is determined to be charged, a charging period for charging that vehicle’s battery system (101), wherein the charging period is started by the apparatus (102) causing a respective one of the soft-switches (104a,b,c) to be actuated so as to control a supply of electrical power to start charging the battery system (101) of the connected electric vehicle (100a,b,c).

30. The fleet vehicle charging management system of claim 28 or 29, wherein minimising the connection policy control variable min cost(u) aims to result in ∑_^^^..^ P_{^^ ^} (u)< P_{^^ ^^^ ^^^^^}, where n is the number of vehicles in the fleet, Pch i is the Power consumed to charge the i^th vehicle in the fleet, and Pch max fleet is the maximum power allowed to charge the fleet of vehicles.

31. The fleet vehicle charging management system of any one of claims 28 to 30, wherein at least one electric vehicle is a heavy duty electric vehicle.

32. The fleet vehicle charging management system of any one of claims 28 to 30, wherein at least one or more or all of the electric vehicles comprise an autonomous or semi-autonomous or remote controlled electric vehicle.