WO2025093650A1

WO2025093650A1 - Handling ai/ml for a communication link between a user device and one or more network entities of a wireless communication network

Info

Publication number: WO2025093650A1
Application number: PCT/EP2024/080777
Authority: WO
Inventors: Tatiana Rykova; Thomas Fehrenbach; Baris GÖKTEPE; Thomas Wirth; Thomas Schierl; Cornelius Hellge; Thomas Wiegand
Original assignee: Fraunhofer Gesellschaft zur Foerderung der Angewandten Forschung eV
Current assignee: Fraunhofer Gesellschaft zur Foerderung der Angewandten Forschung eV
Priority date: 2023-11-03
Filing date: 2024-10-30
Publication date: 2025-05-08
Anticipated expiration: 2026-05-03

Abstract

A user device, UE, for a wireless communication network, is configured or preconfigured with at least one Artificial Intelligence/Machine Learning model, AI/ML model, or at least one AI/ML functionality for performing one or more tasks associated with data transmissions on a communication link between the UE and one or more network entities of the wireless communication network. The UE is to monitor the communication link for one or more certain events, and responsive to detecting one or more of the certain events on the communication link or responsive to a certain signaling from a network entity of the wireless communication network, the UE is to trigger one or more actions concerning the use of one or more of the AI/ML models or AI/ML functionalities.

Description

HANDLING AI/ML FOR A COMMUNICATION LINK BETWEEN A USER DEVICE AND ONE OR MORE NETWORK ENTITIES OF A WIRELESS COMMUNICATION NETWORK

Description

The present invention relates to the field of wireless communication systems or networks, more specifically a use of at least one Artificial Intelligence/Machine Learning model, AI/ML model, or at least one AI/ML functionality in a wireless communication system for performing one or more tasks. Embodiments of the present invention concern improvements and enhancements in the handling of AI/ML models or AI/ML functionalities used for performing one or more tasks associated with data transmissions on a communication link between the UE and one or more network entities of the wireless communication network.

Fig. 1 is a schematic representation of an example of a terrestrial wireless network 100 including, as is shown in Fig. 1 (A), the core network, CN, 102 and one or more radio access networks RANi, RAN2, ... RANN. Fig. 1 (B) is a schematic representation of an example of a radio access network RAN_n that may include one or more base stations gNBi to gNBs, each serving a specific area surrounding the base station schematically represented by respective cells IO61 to IO65. The base stations are provided to serve users within a cell. The one or more base stations may serve users in licensed and/or unlicensed bands. The term base station, BS, refers to a gNB in 5G networks, an eNB in UMTS/LTE/LTE-A/ LTE- A Pro, or just a BS in other mobile communication standards. The BS may also comprise of integrated access and backhaul, IAB, nodes, e.g., an IAB Donor and/or IAB Node, consisting of a central unit, CU, as well as of a distributed unit, DU, and/or containing IAB- MTs including IAB mobile termination, MT. The term base station may refer to an access point, AP, in any of the WiFi standards, e.g., belonging to the IEEE 802.11-familiy. A user may be a stationary device or a mobile device. The wireless communication system may also be accessed by mobile or stationary loT devices which connect to a base station or to a user. The mobile or stationary devices may include physical devices, ground based vehicles, such as robots or cars, aerial vehicles, such as manned or unmanned aerial vehicles, UAVs, the latter also referred to as drones, buildings and other items or devices having embedded therein electronics, software, sensors, actuators, or the like as well as network connectivity that enables these devices to collect and exchange data across an existing network infrastructure. Fig. 1 (B) shows an exemplary view of five cells, however, the RAN_n may include more or less such cells, and RAN_n may also include only one base station. Fig. 1 (B) shows two users UEi and UE2, also referred to as user device or user equipment, that are in cell IO62 and that are served by base station gNB2. Another user UE3 is shown in cell IO64 which is served by base station gNB4. The arrows IO81, IO82 and IO83 schematically represent uplink/downlink connections for transmitting data from a user UE1, UE2 and UE3 to the base stations gNB2, gNB4 or for transmitting data from the base stations gNB2, gNB4 to the users UE1, UE2, UE3. This may be realized on licensed bands or on unlicensed bands. Further, Fig. 1 (B) shows two further devices 110i and HO2 in cell IO64, like loT devices, which may be stationary or mobile devices. The device 110i accesses the wireless communication system via the base station gNB4 to receive and transmit data as schematically represented by arrow 112i. The device HO2 accesses the wireless communication system via the user UE3 as is schematically represented by arrow 1122. The respective base station gNBi to gNBs may be connected to the core network 102, e.g., via the S1 interface, via respective backhaul links 114i to 114s, which are schematically represented in Fig. 1 (B) by the arrows pointing to “core”. The core network 102 may be connected to one or more external networks. The external network may be the Internet, or a private network, such as an Intranet or any other type of campus networks, e.g., a private WiFi communication system or a 4G or 5G mobile communication system. Further, some or all of the respective base station gNBi to gNBs may be connected, e.g., via the S1 or X2 interface or the XN interface in NR, with each other via respective backhaul links 116i to 1165, which are schematically represented in Fig. 1 (B) by the arrows pointing to “gNBs”. A sidelink channel allows direct communication between UEs, also referred to as device-to- device, D2D, communication. The sidelink interface in 3GPP is named PC5. Note, that the term user equipment, UE, or user device may also refer to a station, STA, as used in any of the WiFi standards, e.g., belonging to the IEEE 802.11-familiy.

For data transmission a physical resource grid may be used. The physical resource grid may comprise a set of resource elements to which various physical channels and physical signals are mapped. For example, the physical channels may include the physical downlink, uplink and sidelink shared channels, PDSCH, PLISCH, PSSCH, carrying user specific data, also referred to as downlink, uplink and sidelink payload data, the physical broadcast channel, PBCH, and the physical sidelink broadcast channel, PSBCH, carrying for example a master information block, MIB, and one or more system information blocks, SIBs, one or more sidelink information blocks, SLIBs, if supported, the physical downlink, uplink and sidelink control channels, PDCCH, GC-PDCCH, PLICCH, PSSCH, carrying for example the downlink control information, DCI, the uplink control information, UCI, and the sidelink control information, SCI, and physical sidelink feedback channels, PSFCH, carrying PC5 feedback responses. The sidelink interface may support a 2-stage SCI which refers to a first control region containing some parts of the SCI, also referred to as the 1^st-stage SCI, and optionally, a second control region which contains a second part of control information, also referred to as the 2^nd-stage SCI.

For the uplink, the physical channels may further include the physical random-access channel, PRACH or RACH, used by UEs for accessing the network once a UE synchronized and obtained the MIB and SIB. The physical signals may comprise reference signals or symbols, RS, synchronization signals and the like. The resource grid may comprise a frame or radio frame having a certain duration in the time domain and having a given bandwidth in the frequency domain. The frame may have a certain number of subframes of a predefined length, e.g., 1ms. Each subframe may include one or more slots of 12 or 14 OFDM symbols depending on the cyclic prefix, CP, length. A frame may also have a smaller number of OFDM symbols, e.g., when utilizing shortened transmission time intervals, sTTI, or a mini-slot/non-slot-based frame structure comprising just a few OFDM symbols.

The wireless communication system may be any single-tone or multicarrier system using frequency-division multiplexing, like the orthogonal frequency-division multiplexing, OFDM, system, the orthogonal frequency-division multiple access, OFDMA, system, or any other Inverse Fast Fourier Transform, IFFT, based signal with or without Cyclic Prefix, CP, e.g., Discrete Fourier Transform-spread-OFDM, DFT-s-OFDM. Other waveforms, like non- orthogonal waveforms for multiple access, e.g., filter-bank multicarrier, FBMC, generalized frequency division multiplexing, GFDM, or universal filtered multi carrier, LIFMC, may be used. The wireless communication system may operate, e.g., in accordance with 3GPPs LTE, LTE-Advanced, LTE-Advanced Pro, or the 5G or 5G-Advanced or 6G or 3GPPs NR, New Radio, or within LTE-ll, LTE Unlicensed or NR-U, New Radio Unlicensed, which is specified within the LTE and within NR specifications.

The wireless network or communication system depicted in Fig. 1 may be a heterogeneous network having distinct overlaid networks, e.g., a network of macro cells with each macro cell including a macro base station, like base station gNBi to gNBs, and a network of small cell base stations, not shown in Fig. 1 , like femto or pico base stations. In addition to the above-described terrestrial wireless network also non-terrestrial wireless communication networks, NTN, exist including spaceborne transceivers, like satellites, and/or airborne transceivers, like unmanned aircraft systems. The non-terrestrial wireless communication network or system may operate in a similar way as the terrestrial system described above with reference to Fig. 1 , for example in accordance with the LTE-Advanced Pro or 5G or 5G-Advanced or NR, New Radio, or a possible future 6G radio system.

In mobile communication networks, for example in a network like that described above with reference to Fig. 1 , like an LTE or 5G/NR network, there may be UEs that communicate directly with each other over one or more sidelink, SL, channels, e.g., using the PC5/PC3 interface or WiFi direct. UEs that communicate directly with each other over the sidelink may include vehicles communicating directly with other vehicles, V2V communication, vehicles communicating with other entities of the wireless communication network, V2X communication, for example roadside units, RSUs, roadside entities, like traffic lights, traffic signs, or pedestrians. An RSU may have a functionality of a BS or of a UE, depending on the specific network configuration. Other UEs may not be vehicular related UEs and may comprise any of the above-mentioned devices. Such devices may also communicate directly with each other, D2D communication, using the SL channels.

When considering two UEs directly communicating with each other over the sidelink, both UEs may be served by the same base station so that the base station may provide sidelink resource allocation configuration or assistance for the UEs. For example, both UEs may be within the coverage area of a base station, like one of the base stations depicted in Fig. 1. This is referred to as an “in-coverage” scenario. Another scenario is referred to as an “out- of-coverage” scenario. It is noted that “out-of-coverage” does not mean that the two UEs are necessarily outside one of the cells depicted in Fig. 1 , rather, it means that these UEs may not be connected to a base station, for example, they are not in an RRC connected state, so that the UEs do not receive from the base station any sidelink resource allocation configuration or assistance, and/or may be connected to the base station, but, for one or more reasons, the base station may not provide sidelink resource allocation configuration or assistance for the UEs, and/or may be connected to the base station that may not support NR V2X services, e.g., GSM, UMTS, LTE base stations or a WiFi AP.

Fig. 2(A) is a schematic representation of an in-coverage scenario in which two UEs directly communicating with each other are both connected to a base station. The base station gNB has a coverage area that is schematically represented by the circle 200 which, basically, corresponds to the cell schematically represented in Fig. 1. The UEs directly communicating with each other include a first vehicle 202 and a second vehicle 204 both in the coverage area 200 of the base station gNB. Both vehicles 202, 204 are connected to the base station gNB and, in addition, they are connected directly with each other over the PC5 interface. The scheduling and/or interference management of the V2V traffic is assisted by the gNB via control signaling over the llu interface, which is the radio interface between the base station and the UEs. In other words, the gNB provides SL resource allocation configuration or assistance for the UEs, and the gNB assigns the resources to be used for the V2V communication over the sidelink. This configuration is also referred to as a Mode 1 configuration in NR V2X or as a mode 3 configuration in LTE V2X. Thus, in Mode 1 , a UE, e.g., UE 202 is connected via Uu interface to the gNB, and the gNB coordinates the resources for UE 202 be used to transmit control and/or data to another UE, e.g., UE 204, via a SL interface, which is referred to in NR as PC5.

Fig. 2(B) is a schematic representation of an out-of-coverage scenario in which the UEs directly communicating with each other are either not connected to a base station, although they may be physically within a cell of a wireless communication network, or some or all of the UEs directly communicating with each other are connected to a base station but the base station does not provide for the SL resource allocation configuration or assistance. Three vehicles 206, 208 and 210 are shown directly communicating with each other over a sidelink, e.g., using the PC5 interface. The scheduling and/or interference management of the V2V traffic is based on algorithms implemented between the vehicles. This configuration is also referred to as a Mode 2 configuration in NR V2X or as a Mode 4 configuration in LTE V2X. As mentioned above, the scenario in Fig. 2(B) which is the out-of-coverage scenario does not necessarily mean that the respective Mode 2 UEs in NR or mode 4 UEs in LTE are outside of the coverage 200 of a base station, rather, it means that the respective Mode 2 UEs in NR or mode 4 UEs in LTE are not served by a base station, are not connected to the base station of the coverage area, or are connected to the base station but receive no SL resource allocation configuration or assistance from the base station. Thus, there may be situations in which, within the coverage area 200 shown in Fig. 2(A), in addition to the NR Mode 1 or LTE Mode 3 UEs 202, 204 also NR Mode 2 or LTE mode 4 UEs 206, 208, 210 are present. In addition, Fig. 2(B), schematically illustrates an out of coverage UE using a relay to communicate with the network. For example, the UE 210 may communicate over the sidelink with UE 212 which, in turn, may be connected to the gNB via the Uu interface. Thus, UE 212 may relay information between the gNB and the UE 210. Thus, the SL-UEs, e.g., UEs 206-210, need not to have a connectivity to the gNB, and perform a sensing & access resource allocation or a random access-based resource allocation, e.g., when transmitting from UE 206 to UE 208. Nevertheless, basic configurations need to be available for the UEs 206-210, in order to successfully exchange data. This information may be pre-configured or may be configured while a UE is within coverage of the gNB. For this the gNB may provide a basic configuration, e.g., basic information, which may be transported via a broadcast channel, e.g., using system information blocks (SIBs). The BS may also assist Mode 2 UEs to provide basic information on which resource pool (RP) is to be used or may act as a synchronization source.

Although Fig. 2(A) and Fig. 2(B) illustrate vehicular UEs, it is noted that the described incoverage and out-of-coverage scenarios also apply for non-vehicular UEs. In other words, any UE, like a hand-held device, communicating directly with another UE using SL channels may be in-coverage and out-of-coverage.

In general, Mode 1 refers to a RAN-supported operation including base stations, whereas Mode 2 refers to an autonomous mode, where UEs communicate directly without support of a base station. In the context of WiFi, the coordination done by a WiFi access point, AP, may be referred to a similar operation as Mode 1 , whereas Mode 2 translates to the WiFi autonomous mode. In the latter, two WiFi devices may directly communicate with each other without assistance by the WiFi AP.

In mobile communication networks, for example in a network like that described above with reference to Fig. 1 , like an LTE or 5G/NR network or a WiFi network, data transmissions on a communication link between the UE and one or more network entities of the wireless communication network may be impaired by certain events. For example, a beam link failures, BLF, or a radio link failure, RLF, may occur. Furthermore, if unlicensed bands are used for the communication, the data transmissions may be impaired if the UE fails to access a channel due to a listen before talk, LBT.

A BLF indicates that a currently used beam is not able to maintain a reliable communication. For example, a 5G beam link failure, BLF, is a situation where the communication link between a 5G base station (gNB) and a user equipment (UE) or between two UEs is disrupted due to the loss of beam alignment. This may happen due to various factors, such as mobility, interference, blockage, or misconfiguration. A BLF between two UEs may happen in case two UEs communicate over the sidelink , e.g., via the PC5 interface, using a direct communication. In this case, UEs may utilize beam management in case they are equipped with more than one antenna, or if equipped with antenna arrays or antenna panels, which may be the case if they are transmitting in a higher frequency band, e.g., in FR2. The beam management techniques may be applied to ensure beam alignment between transmitting and receiving UEs.

When a beam link failure occurs, the UE tries to recover the connection by scanning for alternative beams from the same gNB or from neighboring gNBs. The gNB also assists the UE by providing beam failure detection reference signals and configuration parameters. If the UE is not able to find a suitable beam within a certain time, it declares a radio link failure, RLF, and performs a re-establishment procedure. In case of a BLF on the sidelink, the exact RLF procedure may depend on if a UE is operating in-coverage of a gNB, Mode 1 , or in case a UE is out-of-coverage of a gNB, Mode 2. In Mode 1 , a similar RLF procedure with gNB assistance may be utilized. In case of Mode 2, no assistance from the network is to be expected and the UE may either try to change modes, or has to perform a reestablishment procedure by itself, e.g., by transmitting a broader beam to find a beam-pair-link, BPL, between the two UEs.

When an RLF is triggered, this means that the communication link between the UE and the destination is broken due to various reasons, such as poor signal quality, interference, mobility, or handover failure. Depending on the network configuration and the type of cell group that fails, different actions are taken to recover from the RLF. For example:

If the UE is in NR or LTE standalone operation and the RLF occurs in a master cell group, MCG, which is the only cell group that the UE is connected to, then the UE declares the RLF and triggers the RRC re-establishment procedure. This procedure involves sending a RRCReestablishmentRequest message to the network, which contains the cause of the RLF and the identity of the UE. The network then tries to re-establish the connection with the UE by sending a RRCReestablishment message, which contains the new configuration for the UE. If the re-establishment is successful, the UE resumes normal operation. If not, the UE enters an RRCJDLE state and perform cell selection.

If the UE is in multi-radio dual connectivity, MR-DC, operation, which means that it is connected to two cell groups: a master cell group, MCG, through a 4G base station, MN, and a secondary cell group, SCG, through a 5G base station, SN, then different scenarios may happen depending on which cell group fails. For instance: o If the RLF occurs in the MCG, then the UE uses the SCG to report the failure to the network and to request a handover to another MCG. This way, the UE may quickly recover from the MCG failure without losing the connection or data. This feature is called fast MCG link recovery. o If the RLF occurs in the SCG, then the UE marks the radio link failure on the SCG cell and sends a SCGFailurelnformation message to the network through the MCG. This message contains the cause of the RLF and some measurements of nearby cells. The network then decides whether to reconfigure or release the SCG for the UE. This feature is called SCG connectivity.

An LBT failure is a situation where a device that wants to transmit data on an unlicensed spectrum fails to detect a clear channel before sending its signal. LBT stands for listen- before-talk, which is a protocol that requires devices to sense the channel state and avoid interfering with other transmissions. LBT is mandatory for unlicensed spectrum operation in some regions, such as Europe and Japan, and optional in others, such as the US and China. 5G Unlicensed is a feature that allows 5G New Radio, NR, to operate on unlicensed spectrum bands, such as 5 GHz and 6 GHz. 5G Unlicensed may be used in different modes, such as carrier aggregation with a licensed band, dual connectivity with a licensed band, or standalone operation on unlicensed band only. 5G Unlicensed may provide higher bandwidth and capacity for 5G services, but it also faces challenges such as coexistence with other technologies, e.g., Wi-Fi, and meeting regulatory requirements.

An LBT failure in the context of 5G Unlicensed means that a 5G NR device is not able to access the unlicensed channel due to the presence of other signals or noise. This may degrade the performance and reliability of 5G Unlicensed transmissions. When a UE faces LBT failures, it may take different actions depending on the scenario and the configuration. Some possible actions may be:

If the UE is performing an initial access to the unlicensed spectrum, it retries the LBT procedure until it succeeds or reaches a maximum number of attempts. If it fails to access the channel after the maximum number of attempts, it reports a failure to the network and wait for further instructions.

If the UE is transmitting data on the unlicensed spectrum using carrier aggregation or dual connectivity with a licensed band, it suspends the transmission on the unlicensed carrier and continues to use the licensed carrier. It also informs the network about the LBT failure and requests a new grant for the unlicensed carrier.

If the UE is transmitting data on the unlicensed spectrum in standalone mode, it suspends the transmission and waits for a new transmission opportunity. It also informs the network about the LBT failure and requests a new grant for the unlicensed carrier.

If the UE is transmitting HARQ feedback on the unlicensed spectrum, it drops the feedback and waits for a retransmission of the data from the network. The network assumes that the feedback was not received and retransmits the data accordingly.

In a wireless network or communication system Artificial Intelligence (Al) and Machine Learning (ML) may be employed for certain tasks. For example, according to 3GPP, AI/ML techniques and data analytics may be incorporated into the 5G system design for supporting certain tasks, e.g., for supporting network automation, data collection for various network functions, network energy savings, resource allocation and scheduling optimizations, network slicing management, load balancing, mobility optimizations, AI/ML-based services, AI/ML for the new radio (NR) air interface. For example, when considering the NR air interface, AI/ML models may be employed for one or more of the following use cases:

Channel State Information (CSI):

For example, AI/ML may be used for a time-domain prediction.

Beam Management (BM):

For example, Al for beam management in 5G involves the use of Al and ML techniques to improve the efficiency and reliability of a wireless communication using directional beams. Beam management is the process of steering, tracking, and selecting the best beams for each user and link in a 5G network. This is challenging due to factors such as user mobility, blockage and reflections, multi-user interference, a higher number of antennas, and the adoption of elevated frequencies. Al and ML may offer valuable solutions to mitigate this complexity and minimize the overhead associated with beam management and selection, while maintaining system performance.

Unlicensed band operation:

For example Al for channel access in unlicensed bands for 5G involves the use of Al and ML techniques to improve the efficiency and reliability of wireless communication using the unlicensed spectrum. The unlicensed spectrum is the part of the radio frequency spectrum that is not allocated to any specific service or operator, and may be used by anyone who follows certain rules and regulations. The unlicensed spectrum may offer more bandwidth, lower cost, and greater flexibility for 5G applications, especially in scenarios where the licensed spectrum is scarce or expensive. There are some challenges and opportunities of Al for channel access in unlicensed bands for 5G, like: o Channel access methods: There are different methods for accessing unlicensed channels, such as listen before talk, LBT, gap-based channel access, contention-based random access, etc. Each method has its own advantages and disadvantages in terms of latency, throughput, fairness, and overhead. Al and ML may help to design, optimize, and adapt these methods according to the network conditions and user requirements. o Spectrum sharing and coexistence: The unlicensed spectrum is shared by multiple users and technologies, such as Wi-Fi, Bluetooth, LTE-ll, LAA, MulteFire, CBRS, NR, etc. This may cause interference, congestion, and collisions among different transmissions. Al and ML may help to enhance the spectrum sharing and coexistence mechanisms, such as sensing, coordination, scheduling, power control, beamforming, etc., to improve the spectral efficiency and quality of service. o Private networks and industrial loT: The unlicensed spectrum may enable the deployment of 5G private networks and industrial loT applications, such as smart factories, warehouses, mines, etc. These applications have high demands for reliability, security, and low latency. Al and ML may help to customize and optimize the network performance for these applications, such as intelligent load balancing, proactive network slicing, anomaly detection, etc.

Positioning:

For example, a direct AI/ML positioning approach (e.g., fingerprinting) and an AI/ML assisted positioning approach (e.g., the output of the AI/ML model inference is an additional measurement and/or an enhancement of an existing measurement) may be implemented.

The AI/ML model may be running at one of the two sides or at both sides of the communication link, e.g., at the gNB or the network-side, e.g., CN, and/or at the UE. Some AI/ML models may not be specified and left up to implementation, while others, e.g., enabling AI/ML for the air interface, need to be specified.

It is noted that the information in the above section is only for enhancing the understanding of the background of the invention and, therefore, it may contain information that does not form prior art that is already known to a person of ordinary skill in the art. Starting from the above, there may be a need for improvements or enhancements to the use of AI/ML models in a wireless communication system or network.

Embodiments of the present invention are now described in further detail with reference to the accompanying drawings:

Fig. 1 (A)-(B) illustrate a wireless communication network, wherein Fig. 1 (A) is a schematic representation of an example of a terrestrial wireless network, and Fig. 1 (B) is a schematic representation of an example of a radio access network, RAN;

Fig. 2(A) is a schematic representation of an in-coverage scenario;

Fig. 2(B) is a schematic representation of an out-of-coverage scenario;

Fig. 3 is a schematic representation of a wireless communication system including a transmitter, like a base station, and one or more receivers, like user devices, UEs, implementing embodiments of the present invention;

Fig. 4 illustrates a user device, UE, according to an embodiment of the present invention;

Fig. 5 illustrates an embodiment implementing the inventive approach when employing AI/ML for the beam management; and

Fig. 6 illustrates a further embodiment implementing the inventive approach when employing AI/ML for the beam management; and

Fig. 7 illustrates an example of a computer system on which units or modules as well as the steps of the methods described in accordance with the inventive approach may execute.

Embodiments of the present invention are now described in more detail with reference to the accompanying drawings, in which the same or similar elements have the same reference signs assigned. In a wireless communication system network, like the one described above with reference to Fig. 1 , one or more Artificial Intelligence/Machine Learning models, AI/ML models, or one or more AI/ML functionalities may be implemented in a user device or user equipment, UE, for performing one or more tasks, e.g., one or more of the following:

- AI/ML model based access to a RAN,

- AI/ML model based network energy saving,

- AI/ML model based load balancing,

- AI/ML model based mobility optimization,

- AI/ML model based use cases, like o channel state information, CSI, feedback, like a CSI compression and/or a CSI prediction, or o beam management, or o positioning, like a direct AI/ML positioning (e.g., fingerprinting) and/or an AI/ML assisted positioning,

- AI/ML model based mobility management, e.g., a handover, HO, prediction and/or conditional handover, CHO, prediction,

- AI/ML model based modulation and coding scheme, MCS, selection,

- AI/ML model based synchronization,

- AI/ML model based encoding and/or decoding and/or precoding,

- AI/ML model based modulation and/or demodulation,

- AI/ML model based positioning or ranging,

- AI/ML model based joint communication and sensing, JSAC,

- AI/ML model based feedback calculation, e.g., channel state information, CSI, channel quality indicator, CQI, preferred matrix index, PMI, rank indicator feedback,

- AI/ML model based interference management,

- AI/ML model based quality of experience, QoE, and/or quality of service, QoS, predictions,

- AI/ML model based network traffic forecasting.

When implementing one or more AI/ML models or one or more AI/ML functionalities in a wireless communication network, like a 3GPP network or a WiFi network, the overall operation of the network or an efficiency of certain functions within the network may be improved. For example, the air interface in a 5G network may be enhanced using AI/ML. The respective AI/ML models when being implemented, for example within a user device, are trained on a basis of a training dataset, and the trained AI/ML model is used for performing a certain task. Further, the respective AI/ML models may be generalized. The generalization of an AI/ML model describes how it may adapt to new data, which is one of the key capabilities for evaluating the model’s performance. For example, when considering a 3GPP wireless communication network, the following cases may be considered for verifying a generalization performance of an AI/ML model considering various scenarios/configurations:

Case 1 :

The AI/ML model is trained based on a dataset from Scenario #A/Configuration#A, and then the AI/ML model performs an inference or test on a dataset for the same scenario/configuration, i.e., on a dataset for Scenario#A/Configuration#A.

Case 2:

The AI/ML model is trained based on dataset from a Scenario#A/Configuration#A, and then the AI/ML model performs an inference or test on a dataset different from Scenario#A/Configuration#A, for example on a dataset from Scenario#B/Configuration#B or from Scenario#A/Configuration#B.

Case 3:

The AI/ML model is trained based on a dataset constructed by mixing datasets from multiple scenarios/configurations including a first Scenario#A/Configuration#A and a second dataset different from the first scenario/configuration, for example, a dataset from Scenario#B/Configuration#B or Scenario#A/Configuration#B, and then the AI/ML model performs an inference or test on a dataset from a single scenario/configuration from the multiple scenarios/configurations, e.g., Scenario#A/Configuration#A, or Scenario#B/Configuration#B, or Scenario#A/Configuration#B.

It is noted that the number of multiple scenarios/configurations may be larger than 2. Also, ratio of dataset mixing may be reported.

While AI/ML may provide for the above-mentioned benefits, like potential performance gains over non-AI approaches, AI/ML also has some weaknesses. For example, when considering a 3GPP network, AI/ML may be used for PHY layer use cases, such as beam prediction, CSI prediction, CSI compression, and positioning. Despite the potential performance gains over conventional approaches, there are some weaknesses. For example, when considering the above-mentioned generalization, under certain circumstances the performance of AI/ML may degrade. Its performance may even be catastrophic causing severe connection issues between the UE and its communication partner, e.g., gNB or access point, AP. For example, such issues may manifest in the form of a BLF or even an RLF. As mentioned above, a BLF indicates that the currently used beam is not able to maintain a reliable communication. An RLF is even more severe, as an RLF indicates a complete communication failure, e.g., due to continuously failing transmissions or receptions, or failing beam recovery procedures. Also, if unlicensed bands are used for the communication, the UE may fail to access the channel due to a LBT failure, which causes communication issues between the gNB and the UE. While there may be some monitoring mechanisms to evaluate the Al performance such mechanisms may be too slow or may miss some aspects, so that the link fails although monitoring does to detect an issue.

In other words, there may be situations that AI/ML procedures, which usually improve the performance of the communication link, under certain circumstances, may fail to deliver a good performance. This may cause, for example an RLF, a BLF, a LBT failure or collisions on the communication link. For example, if AI/ML for beam management is employed, the AI/ML may predict a wrong beam, hence, causing a BLF as a consequence. If this prediction fails at certain locations, even after having recovered from a BLF with a beam link recovery, the AI/ML may cause persistent failures in the beam procedure. This may even lead to an RLF in some cases. When using AI/ML to intelligently choose channels for LBT, such that the UEs coordinate, it may happen that the AI/ML chooses wrong channels, i.e., causing an LBT failure or “winning” the LBT but then colliding with another UE which performed its LBT at the same time and same channel. Hence, AI/ML may actually degrade the performance significantly.

Therefore, there may be a need for improvements or enhancements in the handling of AI/ML models or AI/ML functionalities used for performing one or more tasks associated with data transmissions on a communication link between the UE and one or more network entities of the wireless communication network.

Embodiments of the present invention address the above problem by allowing the user device to change to or stick to conventional procedures, i.e., non-AI procedures. The present invention provides a user device, UE, for a wireless communication network, which is configured or preconfigured with at least one Artificial Intelligence/Machine Learning model, AI/ML model, or at least one AI/ML functionality for performing one or more tasks associated with data transmissions on a communication link between the UE and one or more network entities of the wireless communication network The UE monitors the communication link for one or more certain events, and, responsive to detecting one or more of the certain events on the communication link or responsive to a certain signaling from a network entity of the wireless communication network, the UE triggers one or more actions concerning the use of one or more of the AI/ML models or AI/ML functionalities.

The present invention is advantageous as it avoids undesired impairments on the communication link or of a data transmission on the communication link due to one or more AI/ML models or functionality not providing an acceptable performance. In case it is determined that the use of the AI/ML may actually degrade the performance over the communication link the UE may stop using a currently used AI/ML and further operate on the basis of conventional, non-AI procedures or it may consider a modification of the currently used AI/ML.

Embodiments of the present invention may be implemented in a wireless communication system as depicted in Fig. 1 including base stations and users, like mobile terminals or loT devices. Fig. 3 is a schematic representation of a wireless communication system 310 including a transmitter 300, like a base station, and one or more receivers 302, 304, like user devices, UEs. The transmitter 300 and the receivers 302, 304 may communicate via one or more wireless communication links or channels 306a, 306b, 308, like a radio link. The transmitter 300 may include one or more antennas ANTT or an antenna array having a plurality of antenna elements, a signal processor 300a and a transceiver 300b, coupled with each other. The receivers 302, 304 include one or more antennas ANTUE or an antenna array having a plurality of antennas, a signal processor 302a, 304a, and a transceiver 302b, 304b coupled with each other. The base station 300 and the UEs 302, 304 may communicate via respective first wireless communication links 306a and 306b, like a radio link using the Uu interface, while the UEs 302, 304 may communicate with each other via a second wireless communication link 308, like a radio link using the PC5 or sidelink, SL, interface. When the UEs are not served by the base station or are not connected to the base station, for example, they are not in an RRC connected state, or, more generally, when no SL resource allocation configuration or assistance is provided by a base station, the UEs may communicate with each other over the sidelink. The system or network of Fig. 3, the one or more UEs 302, 304 of Fig. 3, and the base station 300 of Fig. 3 may operate in accordance with the inventive teachings described herein.

According to aspect 1 there is provided a user device, UE, for a wireless communication network, wherein the UE is configured or preconfigured with at least one Artificial Intelligence/Machine Learning model, AI/ML model, or at least one AI/ML functionality for performing one or more tasks associated with data transmissions on a communication link between the UE and one or more network entities of the wireless communication network, wherein the UE is to monitor the communication link for one or more certain events, and wherein, responsive to detecting one or more of the certain events on the communication link or responsive to a certain signaling from a network entity of the wireless communication network, the UE is to trigger one or more actions concerning the use of one or more of the AI/ML models or AI/ML functionalities.

According to aspect 2 relating to aspect 1 , the UE is to trigger the one or more actions following the n^th occurrence of the certain event or the n^th occurrence of the certain signaling, with n being an integer greater than 0.

According to aspect 3 relating to aspect 2, the UE is to trigger the one or more actions only if the n certain events or certain signalings occurred within a predefined time window.

According to aspect 4 relating to one of aspects 1 to 3, the one or more certain events comprise one or more of the following: an impairment of the communication link between the UE and the one or more entities of the wireless communication network, an impairment of a data transmission on the communication link between the UE and the one or more entities of the wireless communication network.

According to aspect 5 relating to aspect 4, the UE is to determine the impairment of the communication link if one or more of the following applies: one or more failures of the communication link are experienced, a quality of the communication link drops below a configured or preconfigured threshold or drops during a predefined time period by more than a configured or preconfigured amount, e.g., a reference signal received power, RSRP, or a reference signal received quality, RSRQ, or a radio signal strength indicator, RSSI, or a signal to interference plus noise ratio, SINR, or a signal to noise ratio SNR. According to aspect 6 relating to aspect 5, one or more failures comprises one or more of the following: a number of consecutive failures, a number of failures during a predefined time period, e.g., a number of failures within a configured or pre-configured time interval, a percentage of failures during a predefined time period, e.g., a percentage of failures within a configured or pre-configured time interval.

According to aspect 7 relating to one of aspects 4 to 6, the UE is to determine the impairment of the data transmission on the communication link if one or more of the following applies: one or more data transmissions are not successful, a ratio of successful and unsuccessful data transmissions from the UE to the one or more entities exceeds a configured or preconfigured threshold, e.g., ratio of HARQ- ACKs to HARQ-NACKs, a signal strength of a radio signal including the data transmission drops below a configured or preconfigured threshold or drops during a predefined time period by more than a configured or preconfigured amount, e.g., a reference signal received power, RSRP, or a reference signal received quality, RSRQ, or a radio signal strength indicator, RSSI, ora signal to interference plus noise ratio, SINR, or a signal to noise ratio SNR, a number or percentage of collisions with transmission of other UEs experienced by the data transmission during a predefined time period exceeds a configured or preconfigured threshold, an interference level detected on the communication link exceeds a configured or preconfigured threshold, a network congestion exceeds a configured or preconfigured threshold, a number of failed RACH attempts exceeds a configured or preconfigured threshold, a number of failed SIB decoding attempts exceeds a configured or preconfigured threshold, a number of failed cell reselection attempts exceeds a configured or preconfigured threshold, a geographical region/location, a scenario type such as urban, suburban or rural.

According to aspect 8 relating to any one of the preceding aspects, the certain signaling from the network entity, e.g., from a neighboring UE or from a base station, is provided by the network entity when the network entity detected one or more of the certain events on a further communication link between the network entity and the UE or between the network entity and one or more further entities of the wireless communication network, e.g., an impairment of the further communication link or an impairment of a data transmission on the further communication link.

According to aspect 9 relating to aspect 8, the UE is to receive the certain signaling via a unicast transmission, a groupcast or multicast transmission, or a broadcast transmission.

According to aspect 10 relating to aspect 9, the certain signaling from the network entity, e.g., from a neighboring UE or from a base station, is a groupcast, e.g. in Group Common- PDCCH (GC-PDCCH), or a broadcast, e.g. a SIB, indicating to all or a group of UEs to performing one or more actions concerning the use of one or more of the AI/ML models or AI/ML functionalities.

According to aspect 11 relating to aspect 10, the one or more actions concerning the use of one or more of the AI/ML models or AI/ML functionalities comprise to deactivate all and/or some AI/ML models or functionalities in all or certain UEs, e.g., based on an emergency trigger signaling.

According to aspect 12 relating to any one of the preceding aspects, the UE is to trigger one or more actions concerning the use of one or more of the AI/ML models or AI/ML functionalities only if one or more further configured or preconfigured conditions are met.

According to aspect 13 relating to aspect 12, the one or more configured or preconfigured conditions comprise one or more of the following: a certain location or area at/in which the UE is located, a signal strength of a radio signal including the data transmission drops below a configured or preconfigured threshold or drops during a predefined time period by more than a configured or preconfigured amount, e.g., a reference signal received power, RSRP, or a reference signal received quality, RSRQ, or a radio signal strength indicator, RSSI, ora signal to interference plus noise ratio, SINR, or a signal to noise ratio SNR, a percentage or a number of LBT failures due to communications from the base station serving the UE exceeds a configured or preconfigured threshold, an absence of an evacuation signal on one or more frequency bands in which the data transmission is performed.

According to aspect 14 relating to aspect 13, the threshold varies dynamically, depending on the timing condition.

According to aspect 15 relating to any one of the preceding aspects, the one or more actions comprise one or more of the following: a modification of one or more of the AI/ML models or AI/ML functionalities currently used, a modification of the communication link and continuing using the one or more currently used AI/ML models or AI/ML functionalities for the modified communication link, a modification of one or more of the AI/ML models or AI/ML functionalities currently used and of the communication link, and using the one or more modified AI/ML models or AI/ML functionalities for the modified communication link

According to aspect 16 relating to aspect 15, the modification of one or more of the AI/ML models or AI/ML functionalities comprises one or more of the following: deactivating some or all of the currently used AI/ML models or AI/ML functionalities, switching to a different AI/ML model or AI/ML functionality for performing the one or more tasks, e.g., a configured or preconfigured fallback AI/ML model or a fallback AI/ML functionality, adapting some or all of the currently used AI/ML models or AI/ML functionalities, e.g., increasing a quantization granularity, resetting parameters to initial or default values, performing a retraining, or performing a fine-tuning, transitioning into a non-connected state, like the RRCJDLE state or the RRCJNACTIVE state, in which the use of non-connected AI/ML models and functionalities is enabled, switching to a fallback non-AI procedure.

According to aspect 17 relating to aspect 16, for the non-connected state the UE is to use a non-connected mode AI/ML model or AI/ML functionality being more robust compared to connected mode AI/ML model or AI/ML functionality. According to aspect 18 relating to aspect 16 or 17, deactivating some or all of the currently used AI/ML models or AI/ML functionalities comprises one or more of the following further actions: switch off the AI/ML model or the AI/ML functionality, stop performing the one or more tasks, switch to a different task, use a conventional calculation technique for performing the one or more tasks.

According to aspect 19 relating to one of aspects 15 to 18, the modification of the communication link comprises one or more of the following: performing a carrier aggregation, e.g., aggregate a carrier in a lower frequency band in case the UE is already aggregating carriers, switching to a carrier which is in another frequency band, e.g., in FR1 and deactivating a carrier in the higher frequency band, switching to a broader beam, e.g., by temporarily deactivating Al beamforming,

Switching to a different beam pattern/codebook that better suits current network scenario, performing handover to a new cell with a better communication link, redirecting the UE to less congested cells or sectors to balance the network load and reduce the likelihood of RLF.

According to aspect 20 relating to any one of the preceding aspects, the UE is report to the wireless communication network, e.g., to a base station thereof, the one or more actions, e.g., via RRC, MAC-CE, or PHY layer signaling.

According to aspect 21 relating to any one of the preceding aspects, wherein the one or more of tasks comprise one or more of the following:

- AI/ML model based access to a RAN,

- AI/ML model based network energy saving,

- AI/ML model based load balancing,

- AI/ML model based mobility optimization,

- AI/ML model based modulation and coding scheme, MCS, selection,

- AI/ML model based synchronization,

- AI/ML model based encoding and/or decoding and/or precoding,

- AI/ML model based modulation and/or demodulation,

- AI/ML model based positioning or ranging,

- AI/ML model based joint communication and sensing, JSAC,

- AI/ML model based feedback calculation, e.g., CSI/CQI/PMI/RI feedback,

- AI/ML model based interference management,

- AI/ML model based network traffic forecasting.

According to aspect 22 relating to any one of the preceding aspects, the UE comprise one or more of a power-limited UE, or a hand-held UE, like a UE used by a pedestrian, and referred to as a Vulnerable Road User, VRU, or a Pedestrian UE, P-UE, or an on-body or hand-held UE used by public safety personnel and first responders, and referred to as Public safety UE, PS-UE, or an loT UE or Ambient loT UE, e.g., a sensor, an actuator or a UE provided in a campus network to carry out repetitive tasks and requiring input from a gateway node at periodic intervals, or a mobile terminal, or a stationary terminal, or a cellular loT-UE, an industrial loT-UE, 11 oT, or a SL UE, or a vehicular UE, or a vehicular group leader UE, GL-UE, or a scheduling UE, S-UE, or an loT or narrowband loT, NB-loT, device, a NTN UE, or a WiFi device or WiFi station, STA, or a ground based vehicle, or an aerial vehicle, or a drone, or a moving base station, or road side unit, RSU, or a building, or any other item or device provided with network connectivity enabling the item/device to communicate using the wireless communication network, e.g., a sensor or actuator, or any other item or device provided with network connectivity enabling the item/device to communicate using a sidelink the wireless communication network, e.g., a sensor or actuator, or any sidelink capable network entity.

According to aspect 23, a wireless communication network, like a 3^rd Generation Partnership Project, 3GPP, system, comprising a one or more user devices, UEs, of any one of the preceding aspects and one or more base stations, BSs. According to aspect 24 relating to aspect 23, the BS comprises one or more of a macro cell base station, or a small cell base station, or a central unit of a base station, or a distributed unit of a base station, or an Integrated Access and Backhaul, IAB, node, or a road side unit, RSU, or a WiFi access point, AP, or a UE, or a SL UE, or a group leader UE, GL-LIE, or a relay or a remote radio head, or an AMF, or an SMF, or a core network entity, or mobile edge computing, MEC, entity, or a network slice as in the NR or 5G core context, or any transmission/reception point, TRP, enabling an item or a device to communicate using the wireless communication network, the item or device being provided with network connectivity to communicate using the wireless communication network.

According to aspect 25 there is provided a method for operating a user device, UE, for a wireless communication network, wherein the UE is configured or preconfigured with at least one Artificial Intelligence/Machine Learning model, AI/ML model, or at least one AI/ML functionality for performing one or more tasks associated with data transmissions on a communication link between the UE and one or more network entities of the wireless communication network, the method comprising: monitoring the communication link for one or more certain events, and responsive to detecting one or more of the certain events on the communication link or responsive to a certain signaling from a network entity of the wireless communication network, triggering one or more actions concerning the use of one or more of the AI/ML models or AI/ML functionalities.

According to aspect 26 there is provided a non-transitory computer program product comprising a computer readable medium storing instructions which, when executed on a computer, perform the method of aspect 25.

The present invention provides a computer program product comprising instructions which, when the program is executed by a computer, causes the computer to carry out one or more methods in accordance with the present invention.

Embodiments of the present invention are now described in more detail with reference to the accompanying drawing. It is noted that the subsequently outlined and described aspects or embodiments may be combined such that some or all of the aspects/embodiments are implemented within one embodiment. Reference is made herein one or more AI/ML models and/or to one or more AI/ML functionalities. It is noted that when referring only to an AI/ML model, this is to be understood to refer also to an AI/ML functionality, and that when referring only to an AI/ML functionality, this it to be understood to refer also to an AI/ML model. AI/ML functionality may refer to an AI/ML-enabled Feature/Feature Group, FG, enabled by one or more configurations, where the one or more configurations may be supported based on one or more conditions indicated by a UE capability. An AI/ML-enabled Feature refers to a Feature where AI/ML may be used. It is noted that a UE may have one AI/ML model for the functionality, or the UE may have multiple AI/ML models for the functionality. Examples of use cases for AI/ML-enabled Features or Feature Groups are:

CSI feedback enhancement, e.g., overhead reduction, improved accuracy, prediction.

Beam management, e.g., beam prediction in time, and/or spatial domain for overhead and latency reduction, beam selection accuracy improvement.

Positioning accuracy enhancements for different scenarios including, e.g., those with heavy NLOS conditions.

Other examples may comprise of access to the RAN, network energy saving, NES, resource management and load balancing, mobility enhancements and optimization including handover, HO, management and/or prediction, conditional handover, CHO, management and/or prediction, modulation and coding scheme, MOS, selection, MIMO precoder calculation, general PHY-layer signal processing, e.g., synchronization, channel coding or decoding, modulation or demodulation, positioning or ranging, joint communication and sensing, JSAC, feedback calculation of CSI/CQI or PMI/RI, general MIMO processing, equalization, network offloading, interference management, quality of experience, QoE, and/or quality of service, QoS, predictions, and/or network traffic forecasting. It is noted that the AI/ML approaches for the selected sub use cases need to be diverse enough to support various requirements on the gNB-UE collaboration levels.

An AI/ML model operates based on identified models, where a model may be associated with one or more specific configurations/conditions associated with a UE capability of an AI/ML-enabled Feature/FG and additional conditions (e.g., scenarios, sites, and datasets) as determined/identified between the UE-side and the NW-side.

Fig. 4 illustrates a user device, UE, in accordance with embodiments of the present invention. The UE 400 includes a signal processing unit or signal processor 402 and one or more antennas or an antenna array 404 for communicating with other network entities over the air interface. As is depicted in Fig. 4, the UE 400 may communicate with a base station or gNB 406 using the llu interface 408 and/or with a further UE 410 using the PC5 interface 412 for a sidelink, SL, communication. As is schematically illustrated, the UE 400 is configured or preconfigured with at least one Artificial Intelligence/Machine Learning model, AI/ML model, or at least one AI/ML functionality 414 for performing one or more tasks associated with data transmissions on a communication link 408 or 412 between the UE 400 and the gNB 406 of the further UE 410.

In a connected state, like the RRC_CONNECTED state, the UE 400 may use the configured/preconfigured AI/ML models or functionalities 414, which are also referred to as “connected AI/ML models or functionalities”. The UE receives an activation signal, e.g., from the gNB 406, for activating one or more or all of the connected AI/ML models or functionalities. Thus, the one or more connected AI/ML models or functionalities include one or more or all of the configured or preconfigured AI/ML models or AI/ML functionalities 414. In accordance with embodiments, in a non-connected state, like the RRCJNACTIVE state or the RRCJDLE state, the UE 400 may also make use of one or more or all of the configured/preconfigured AI/ML models or functionalities 414, which are also referred to as “non-connected AI/ML models or functionalities”. The non-connected AI/ML models or functionalities include one or more or all of the configured or preconfigured AI/ML models or AI/ML functionalities 414. In other words, the UE 400 when being in a non-connected state may activate one or more or all of the configured or preconfigured AI/ML models or functionalities 414 without any explicit or implicit signaling from the network side causing such an activation, and the UE 400 may also benefit from the advantages of implementing AI/ML approaches in the UE, for example for improving the potential transmissions the UE is to transmit or receive even when being in the non-connected state.

The UE 400 monitors the communication link, for example the communication link 408 or the communication link 412 when communicating with the gNB 406 and/or the UE 410, for certain events, as is schematically indicated at 416. When detecting one or more of the certain events on the communication link 408, 412, or when receiving a certain signaling from a network entity, like the communication partner, for example the gNB 406 or the UE 410, the UE triggers one or more actions concerning the use of one or more of the AI/ML models and AI/ML functionalities, as is schematically indicated at 418. Fig. 5 illustrates an embodiment implementing the inventive approach when employing AI/ML for the beam management. The UE 400 comprises a plurality of antennas or an antenna array with a plurality of elements allowing the UE to direct a transmit or receive beam into a desired direction. As is depicted in Fig. 5(A), the UE 400 may form the beams B1 , B2 and B3 pointing into different directions with their main lobes. For selecting the beam to be used for a communication with the base station 406, the UE 400 employs a AI/ML model or functionality 414a, referred to as beam Al. The beam Al 414a is assumed to select beam B1 for a communication with the base station 406. However, as is depicted, beam B1 does not point towards the base station 406, so that the UE 400 experiences an impairment on the communication link between the UE 400 and the base station 406, for example the beam B1 selected by the AI/ML 414a may cause a BLF or even an RLF, as is indicated at 420. Responsive to detecting the event 420 once or responsive to detecting the event 420 multiple times, for example within a predefined time period, the UE 400 decides to take an action with regard to the use of the AI/ML model. In the depicted embodiment the UE 400 decides to deactivate the beam Al 414b, as is illustrated in Fig. 5(B) at 422. Deactivating the beam Al 414b causes the 400 to either switch to a non-AI procedure, i.e. to a conventional procedure not making use of AI/ML models or functionalities. The UE 400 using the conventional non-AI approach selects beam B3 for the communication pointing towards the gNB 406 for initiating a beam recovery procedure or an RRC reestablishment procedure.

Fig. 6 illustrates a further embodiment implementing the inventive approach when employing AI/ML for the beam management. Like in Fig. 5 the UE 400 comprises a plurality of antennas or an antenna array with a plurality of elements allowing the UE to direct a transmit or receive beam into a desired direction. As is depicted in Fig. 6(A), the UE 400 may form the beams B1 , B2 and B3 pointing into different directions with their main lobes. For selecting the beam to be used for a communication with the base station 406, the UE 400 employs a AI/ML model or functionality 414a, referred to as beam Al. The beam Al 414a is assumed to select beam B1 for a communication with the base station 406. However, as is depicted, beam B1 does not point towards the base station 406, so that the UE 400 experiences an impairment on the communication link between the UE 400 and the base station 406, for example the beam B1 selected by the AI/ML 414a may cause a BLF or even an RLF, as is indicated at 420. Responsive to detecting the event 420 once or responsive to detecting the event 420 multiple times, for example within a predefined time period, the UE 400 decides to take an action with regard to the use of the AI/ML model. In the depicted embodiment the UE 400 decides to adapt the beam Al 414b, as is illustrated in Fig. 6(B) a 424. Adapting the beam Al 414b causes the 400 to either switch to an alternative AI/ML model or to modify the beam Al 414b. The UE 400, using the adapted beam Al 414b, selects beam B3 for the communication pointing towards the gNB 406 for initiating a beam recovery procedure or an RRC reestablishment procedure.

Thus, in accordance with embodiments of the present invention, the degradation or impairment of the communication between the UE 400 and the gNB 406 caused by a degrade in the performance of the beam Al 414a is overcome by deactivating or adapting the beam Al 414a and selecting the appropriate beam B3 using, for example, non-AI procedures or other Al procedures which are more suited for the situation. This allows the UE to reestablish the link using the appropriate beam B3. This resolves the degrade in the performance of an AI/ML model or functionality used for supporting the UE 400 with its transmissions transmitted over or received over the communication link by taking appropriate action, like deactivating the concerned AI/ML model or switching back to a non- AI/ML procedure so that impairments on the link may be avoided or quickly resolved.

In accordance with further embodiments, the UE 400, after adapting its operation, may report the adaption of the beam Al to the gNB 406, e.g., after the link has been reestablished, as is schematically illustrated in Fig. 6(B) at 426. It is noted that also in the embodiment of Fig. 5 the UE 400 may report the deactivation of the beam Al 414a to the gNB 406. In other words, the UE 400 may report to the gNB 406 that it took some action. For example, the UE 400 may report that certain or all AI/ML models/functionalities have been deactivated, or that it switched to another AI/ML model or functionality, or that one or more or all of the AI/ML models/functionalities were adapted by, for example, resetting the AI/ML. The signaling or the report 422 may be provided using RRC signaling, or one or more MAC-CEs, or a PHY layer signaling, like a UCI.

In accordance with embodiments, the UE 400 may trigger the one or more actions, like the above described deactivation of the beam Al 414a, immediately after detecting a certain event, like the BLF or the RLF, for the first time. In accordance with other embodiments, for avoiding frequent reconfigurations of the UE 400 with regard to the use of the implemented AI/ML, the respective action concerning the use of the AI/ML may only be taken once the certain event or the certain signaling occurred multiple times, e.g., during a predefined time period. For example, the UE 400 triggers the one or more actions following the n^th occurrence of the certain event or the n^th occurrence of the certain signaling, with n being an integer greater than 0. In accordance with embodiments, the UE 400 may trigger the one or more actions when a number of events/signalings during the predefined time period exceeds the threshold. In accordance with embodiments, the predefined time period or time mentioned herein may be a time or time window during which a certain AI/ML model/functionality is active.

Stated differently, the trigger may not be activated after a first occurrence of the trigger potentials or event but after a certain number. For example, a first BLF may not cause the trigger to be activated but the trigger may be activated dependent on the failure behavior within a certain time window. For example, the trigger may only be activated after n BLFs (being an integer greater than 0) or a certain frequency or periodicity of the BLFs. As mentioned earlier, the time window may also be the time in which a certain Al model/functionality is active.

In accordance with embodiments, the certain events on the communication link 408, 412 concern an impairment or degradation of the actual communication link 408, 412 between the UE 400 and its communication partner, link the gNB 406 or the UE 410. The certain event, besides being a degradation of the actual communication link, may also be an impairment or degradation of the actual data transmission on or over the communication link 408, 412 between the UE and the gNB 406 and/or the UE 410.

In accordance with embodiments, the UE 400 determines an impairment of the communication link if one or more failures of the communication link are experienced. For example, an impairment of the communication link may be determined if a number of consistent failures of the communication link during a certain time period exceeds a configured or preconfigured threshold. It is noted that the threshold may be set to one or more failures. The threshold may be configured differently, depending on various factors, such as geographical region/location, scenario type (urban/suburban/rural), site configuration and/or may vary dynamically, depending e.g., on the time of the day, etc. The failures may one or more of the following: beam link failures, BLFs, or radio link failures, RLFs, or listen before talk, LBT, failures, or handover failures from a source base station, which currently serves the UE, to a target base station. The number of consistent failures may include one or more of the following: a number of consecutive failures, like n consecutive failures with n being an integer greater than 0, a number of failures during a predefined time period, e.g., a n failures within a configured or pre-configured time interval with n being an integer greater than 0, a percentage of failures during a predefined time period, e.g., a percentage of failures within a configured or pre-configured time interval

In accordance with other embodiments, the UE 400 determines an impairment of the communication link if a quality of the communication link drops, for example during a predefined time period, below a configured or preconfigured threshold, or drops during a predefined time period by more than a configured or preconfigured amount. The quality of the communication link may be determined using one or more of the following: a reference signal received power, RSRP, or a reference signal received quality, RSRQ, or a radio signal strength indicator, RSSI, or a signal to interference plus noise ratio, SI NR, or a signal to noise ratio SNR.

In accordance with yet other embodiments, the UE 400 determines the impairment of the data transmission on the communication link if one or more of the following applies:

One or more data transmissions are not successful, e.g. during a predefined time period.

For example, if a number of unsuccessful data transmissions from the UE to the one or more entities exceeds a configured or preconfigured threshold an impairment of the data transmission is determined. It is noted that the threshold may be set to one or more unsuccessful data transmissions. For example, if a number of a number of Hybrid automatic repeat request non-acknowledgements, HARQ-NACKs exceeds the threshold, the impairment of the data transmission on the communication link is determined.

For example, if a number of successful data transmissions from the UE to the one or more entities drops below a configured or preconfigured threshold an impairment of the data transmission is determined. It is noted that the threshold may be set to one or more successful data transmissions. For example, if a number of Hybrid automatic repeat request acknowledgements, HARQ-ACKs, drops below the threshold, the impairment of the data transmission on the communication link is determined.

- A ratio of successful and unsuccessful data transmissions from the UE to the one or more entities exceeds, e.g. during a predefined time period, a configured or preconfigured threshold, like a ratio of HARQ-ACKs to HARQ-NACKs.

- A signal strength of a radio signal including the data transmission drops, e.g. during a predefined time period, below a configured or preconfigured threshold or drops during a predefined time period by more than a configured or preconfigured amount, e.g., a signal strength of a reference signal received power, RSRP, or a reference signal received quality, RSRQ, or a radio signal strength indicator, RSSI, or a signal to interference plus noise ratio, SI NR, or a signal to noise ratio SNR.

- A number or percentage of collisions with transmission of other UEs experienced by the data transmission, e.g., during a predefined time period, exceeds a configured or preconfigured threshold. It is noted that the threshold may be set to one or more collisions.

- An interference level detected on the communication link exceeds a configured or preconfigured threshold.

- A network congestion exceeds a configured or preconfigured threshold.

- A number of failed RACH attempts, e.g. during a predefined time period, exceeds a configured or preconfigured threshold. It is noted that the threshold may be set to one or more failed RACH attempts.

- A number of failed SIB decoding attempts, e.g. during a predefined time period, exceeds a configured or preconfigured threshold. It is noted that the threshold may be set to one or more failed SIB decoding attempts.

- A number of failed cell reselection attempts, e.g. during a predefined time period, exceeds a configured or preconfigured threshold. It is noted that the threshold may be set to one or more failed cell reselection attempts.

So far the inventive approach has been described with reference to embodiments in which the UE 400 triggers one or more actions concerning the use of one or more of the AI/ML models or AI/ML functionalities responsive to detecting the one or more certain events on the communication link. The present invention is not limited to such embodiments. In accordance with further embodiment the UE 400 triggers one or more actions concerning the use of one or more of the AI/ML models or AI/ML functionalities responsive to a certain signaling from a network entity of the wireless communication network, the UE is to. For example, the certain signaling may be from the network entity with which the UE 400 communication over the communication link, e.g., from the neighboring UE 410 or from the base station 406, The signaling may be provided by the network entity when it detected one or more of the certain events on a further communication link between the network entity and the UE or between the network entity and one or more further entities of the wireless communication network, e.g., an impairment of the further communication link or an impairment of a data transmission on the further communication link. In accordance with embodiments, wherein the UE 400 receives the certain signaling via a unicast transmission, a groupcast or multicast transmission, or a broadcast transmission. For example, the certain signaling from the network entity, e.g., from a neighboring UE or from a base station, may be a groupcast, e.g. in Group Common-PDCCH (GC-PDCCH), or broadcast, e.g. a SIB, indicating to all or a group of UEs to perform one or more actions concerning the use of one or more of the AI/ML models or AI/ML functionalities. In other words, the UE 400 may receive a broadcast or groupcast emergency deactivation signal that may be used to deactivate Al for all or certain UEs due to issues on the communication link. In accordance with embodiments, the UE may also transition to RRCJDLE after the emergency has been triggered. For example, in some cases AI/ML in UEs in a certain region may perform catastrophically due to changes in the environment, which cannot be properly accommodated to by the currently used AI/ML schemes. That would result in a performance drop in almost all UEs in that region. Hence, in such a scenario, the network entity may use an emergency trigger signaling to deactivate all and/or some AI/ML models or functionalities in all or certain UEs. Compared to state-of-the-art deactivation of certain AI/ML models or functionalities, which requires individual deactivation for each UE, the proposed method allows the network entity to react fast to changed circumstances. Hence, the proposed method prevents further degradation due to problems with AI/ML and avoids more severe issues, such as simultaneous communication link failures in many UEs.

In certain scenarios, the trigger may be activated, e.g., due to an RLF, BLF, etc., however, the probability that this failure is caused by an AI/ML malfunction may be low. For example, if the UE passes a tunnel and loses its connection, or the LBT failure is due to a lot of communication from the gNB any degradation of the performance on/over the communication link is most likely not due to a degradation of the AI/ML performance. Furthermore, certain unlicensed bands may be evacuated due to evacuation signals causing LBT failures and/or HARQ-NACKs. In these cases, it may not be beneficial to take action although the trigger is activated. Hence, in accordance with embodiments, the UE 400 triggers the one or more actions concerning the use of one or more of the AI/ML models or AI/ML functionalities only if one or more further configured or preconfigured conditions are met. The one or more configured or preconfigured conditions may include one or more of the following:

- A certain location or area at/in which the UE is located, i.e. , the UE 400 needs to be at a predefined position at which the inventive approach is enabled.

- A signal strength of a radio signal including the data transmission drops below a configured or preconfigured threshold, e.g., during a predefined time period, or drops during a predefined time period by more than a configured or preconfigured amount, e.g., a reference signal received power, RSRP, or a reference signal received quality, RSRQ, or a radio signal strength indicator, RSSI, or a signal to interference plus noise ratio, SINR, or a signal to noise ratio SNR. Thus, the additional condition serves as a filter so that when considering, for example, an RLF to be the trigger that causes the actions, they are only performed if, e.g., the SNR is under a certain threshold.

- A percentage or a number of LBT failures due to communications from the base station serving the UE exceeds a configured or preconfigured threshold. The threshold may vary dynamically, depending on the timing condition, e.g., time of the day. Thus, LBT failures that happened because of the gNB are not considered. For example, the gNB uses the channel which causes an LBT failure at the UE. Since the gNB has mechanisms to fairly share the medium, this may have been done intentionally by the gNB, so this is not a trigger to perform the one or more actions.

- An absence of an evacuation signal on one or more frequency bands in which the data transmission is performed. Some bands may have shared access. For example, they are also used by the military. Then there usually are certain signals, which are reserved to the military that cause all non-military devices to not use the band for a certain duration. Obviously, this is not a failure of the Al and hence, Al should not be altered although such an event would surely trigger an RLF.

An exemplary RRC Configuration for a dynamic Al deactivation may be as follows:

Dynamic-AI-Deactivation-Config := SEQUENCE {

Triggersignal ENUMERATED {RLF, BLF, LBT, HARQ},

TriggerRSRPThreshold RSRP-Range OPTIONAL,

TriggerOnlyOnEvacSignalAbsence ENUMERATED {enabled} OPTIONAL,

MinimumTimeToLastReport ENUMERATED {ms0.1 , ms1 , ms2, ms5}

OPTIONAL, }

The parameter Triggersignal may be used to configure which trigger event is monitored for the emergency actions. TriggerRSRPThreshold describes an RSRP range, in which the one or more actions are taken. For example, this may be beneficial, if the RSRP is very low. In this case, the trigger events may be activated by the bad channel conditions with very high probability and taking actions on the AI/ML procedures may not improve the situation. TriggerOnlyOnEvacSignalAbsence may configure whether the trigger shall be omitted in the presence of an evacuation signal. For example, some bands may be shared with military usage. In cases where a military user uses the band, an evacuation signal may be transmitted causing all non-military users to not use the band for a certain time. For example, in this case the presence of such a signal may cause consistent LBT failures or an RLF. However, it may not be beneficial to take action on the AI/ML procedures since the communication link issues are due to the evacuation. The parameter MinimumTimeToLastReport may define a time to the last measurement or performance report on the AI/ML performance or to the last trigger. In case the time to the last report or trigger is less than the MinimumTimeToLastReport when the trigger is activated, the UE may not take action as it expects that the network entity is aware of potential issues and may take action accordingly.

In the embodiment described above with reference to Fig. 5 the action taken by UE 400 was a deactivation of the beam Al 414a and the use of a non-AI procedure for the beam selection. The present invention is not limited to such embodiments, rather, the UE 400 may also perform other actions. In accordance with embodiments, the one or more actions may include a modification of one or more of the AI/ML models or AI/ML functionalities currently used, as described with reference to Fig. 6. For example, the modification may include one or more of the following:

Deactivating some or all of the currently used AI/ML models or AI/ML functionalities. For example, deactivating some or all of the currently used AI/ML models or AI/ML functionalities may include one or more of the following further actions: switch off the AI/ML model or the AI/ML functionality, stop performing the one or more tasks, switch to a different task, use a conventional calculation technique for performing the one or more tasks.

Switching to a different AI/ML model or AI/ML functionality for performing the one or more tasks, e.g., a configured or preconfigured fallback AI/ML model or a fallback AI/ML functionality,

- Adapting some or all of the currently used AI/ML models or AI/ML functionalities, e.g., increasing a quantization granularity, resetting parameters to initial or default values, performing a retraining, or performing a fine-tuning.

Transitioning into a non-connected state, like the RRCJDLE state or the RRCJNACTIVE state. The non-connected state may or may not enable the use of non-connected AI/ML models and functionalities. In the non-connected mode, the UE may switch to non-connected mode AI/ML, which may be more robust compared to connected mode AI/ML. The UE may or may not perform a RACH using the nonconnected mode Al to transition to the RRC_CONNECTED state again.

Switching to a fallback non-AI procedure. Since Al is an additional on-the-top feature, all the functionalities may also be performed without Al (or at least without Al 3GPP is aware of, e.g. internally in the chip). This is referred to as fallback procedure.

In accordance with other embodiments, the one or more actions may include a modification of the communication link and continuing using the one or more currently used AI/ML models or AI/ML functionalities for the modified communication link. For example, the modification of the communication link may include one or more of the following:

Performing a carrier aggregation, e.g., aggregate a carrier in a lower frequency band in case the UE is already aggregating carriers.

Switching to a carrier which is in another frequency band, e.g., in FR1 and deactivating a carrier in the higher frequency band.

Switching to a broader beam, e.g., by temporarily deactivating Al beamforming.

Switching to a different beam pattern/codebook that better suits current network scenario,#

Performing handover to a new cell with a better communication link.

Redirecting the UE to less congested cells or sectors to balance the network load and reduce the likelihood of RLF.

In accordance with yet other embodiments, the one or more actions may include a modification of one or more of the AI/ML models or AI/ML functionalities currently used and of the communication link, and using the one or more modified AI/ML models or AI/ML functionalities for the modified communication link.

General

Embodiments of the present invention have been described in detail above, and the respective embodiments and aspects may be implemented individually or two or more of the embodiments or aspects may be implemented in combination.

In accordance with embodiments, the wireless communication system may include a terrestrial network, or a non-terrestrial network, or networks or segments of networks using as a receiver an airborne vehicle or a space-borne vehicle, or a combination thereof. Further, the wireless communication system may by a system or network different from the above described 4G or 5G mobile communication systems, rather, embodiments of the inventive approach may also be implemented in any other wireless communication network, e.g., in a private network, such as an Intranet or any other type of campus networks, or in a WiFi communication system. In accordance with embodiments of the present invention, a user device comprises one or more of the following: a power-limited UE, or a hand-held UE, like a UE used by a pedestrian, and referred to as a Vulnerable Road User, VRU, or a Pedestrian UE, P-UE, or an on-body or hand-held UE used by public safety personnel and first responders, and referred to as Public safety UE, PS-UE, or an loT UE, e.g., a sensor, an actuator or a UE provided in a campus network to carry out repetitive tasks and requiring input from a gateway node at periodic intervals, a mobile terminal, or a stationary terminal, or a cellular loT-UE, or a vehicular UE, or a vehicular group leader (GL) UE, or a sidelink relay, or an loT or narrowband loT, NB-loT, device, or wearable device, like a smartwatch, or a fitness tracker, or smart glasses, or a ground based vehicle, or an aerial vehicle, or a drone, or a moving base station, or road side unit (RSU), or a building, or any other item or device provided with network connectivity enabling the item/device to communicate using the wireless communication network, e.g., a sensor or actuator, or any other item or device provided with network connectivity enabling the item/device to communicate using a sidelink the wireless communication network, e.g., a sensor or actuator, or a Wi-Fi device, like a station (STA), access point (AP), node or mesh node, or mesh point, or Mesh AP, or any sidelink capable network entity.

In accordance with embodiments of the present invention, a network entity comprises one or more of the following: a macro cell base station, or a small cell base station, or a central unit of a base station, an integrated access and backhaul, IAB, node, or a distributed unit of a base station, or a road side unit (RSU), or a Wi-Fi device such as an access point (AP) or mesh node (Mesh AP), or a remote radio head, or an AMF, or a MME, or a SMF, or a core network entity, or mobile edge computing (MEC) entity, or a network slice as in the NR or 5G core context, or any transmission/reception point, TRP, enabling an item or a device to communicate using the wireless communication network, the item or device being provided with network connectivity to communicate using the wireless communication network.

Although some aspects of the described concept have been described in the context of an apparatus, it is clear, that these aspects also represent a description of the corresponding method, where a block or a device corresponds to a method step or a feature of a method step. Analogously, aspects described in the context of a method step also represent a description of a corresponding block or item or feature of a corresponding apparatus. Various elements and features of the present invention may be implemented in hardware using analog and/or digital circuits, in software, through the execution of instructions by one or more general purpose or special-purpose processors, or as a combination of hardware and software. For example, embodiments of the present invention may be implemented in the environment of a computer system or another processing system. Fig. 7 illustrates an example of a computer system 600. The units or modules as well as the steps of the methods performed by these units may execute on one or more computer systems 600. The computer system 600 includes one or more processors 602, like a special purpose or a general-purpose digital signal processor. The processor 602 is connected to a communication infrastructure 604, like a bus or a network. The computer system 600 includes a main memory 606, e.g., a random-access memory, RAM, and a secondary memory 608, e.g., a hard disk drive and/or a removable storage drive. The secondary memory 608 may allow computer programs or other instructions to be loaded into the computer system 600. The computer system 600 may further include a communications interface 610 to allow software and data to be transferred between computer system 600 and external devices. The communication may be in the from electronic, electromagnetic, optical, or other signals capable of being handled by a communications interface. The communication may use a wire or a cable, fiber optics, a phone line, a cellular phone link, an RF link and other communications channels 612.

The terms “computer program medium” and “computer readable medium” are used to generally refer to tangible storage media such as removable storage units or a hard disk installed in a hard disk drive. These computer program products are means for providing software to the computer system 600. The computer programs, also referred to as computer control logic, are stored in main memory 606 and/or secondary memory 608. Computer programs may also be received via the communications interface 610. The computer program, when executed, enables the computer system 600 to implement the present invention. In particular, the computer program, when executed, enables processor 602 to implement the processes of the present invention, such as any of the methods described herein. Accordingly, such a computer program may represent a controller of the computer system 600. Where the disclosure is implemented using software, the software may be stored in a computer program product and loaded into computer system 600 using a removable storage drive, an interface, like communications interface 610.

The implementation in hardware or in software may be performed using a digital storage medium, for example cloud storage, a floppy disk, a DVD, a Blue-Ray, a CD, a ROM, a PROM, an EPROM, an EEPROM or a FLASH memory, having electronically readable control signals stored thereon, which cooperate or are capable of cooperating with a programmable computer system such that the respective method is performed. Therefore, the digital storage medium may be computer readable.

Some embodiments according to the invention comprise a data carrier having electronically readable control signals, which are capable of cooperating with a programmable computer system, such that one of the methods described herein is performed.

Generally, embodiments of the present invention may be implemented as a computer program product with a program code, the program code being operative for performing one of the methods when the computer program product runs on a computer. The program code may for example be stored on a machine readable carrier.

Other embodiments comprise the computer program for performing one of the methods described herein, stored on a machine readable carrier. In other words, an embodiment of the inventive method is, therefore, a computer program having a program code for performing one of the methods described herein, when the computer program runs on a computer.

A further embodiment of the inventive methods is, therefore, a data carrier or a digital storage medium, or a computer-readable medium comprising, recorded thereon, the computer program for performing one of the methods described herein. A further embodiment of the inventive method is, therefore, a data stream or a sequence of signals representing the computer program for performing one of the methods described herein. The data stream or the sequence of signals may for example be configured to be transferred via a data communication connection, for example via the Internet. A further embodiment comprises a processing means, for example a computer, or a programmable logic device, configured to or adapted to perform one of the methods described herein. A further embodiment comprises a computer having installed thereon the computer program for performing one of the methods described herein.

In some embodiments, a programmable logic device, for example a field programmable gate array, may be used to perform some or all of the functionalities of the methods described herein. In some embodiments, a field programmable gate array may cooperate with a microprocessor in order to perform one of the methods described herein. Generally, the methods are preferably performed by any hardware apparatus.

The above-described embodiments are merely illustrative for the principles of the present invention. It is understood that modifications and variations of the arrangements and the details described herein are apparent to others skilled in the art. It is the intent, therefore, to be limited only by the scope of the impending patent claims and not by the specific details presented by way of description and explanation of the embodiments herein.

Claims

1 . A user device, UE, for a wireless communication network, wherein the UE is configured or preconfigured with at least one Artificial Intelligence/Machine Learning model, AI/ML model, or at least one AI/ML functionality for performing one or more tasks associated with data transmissions on a communication link between the UE and one or more network entities of the wireless communication network, wherein the UE is to monitor the communication link for one or more certain events, and wherein, responsive to detecting one or more of the certain events on the communication link or responsive to a certain signaling from a network entity of the wireless communication network, the UE is to trigger one or more actions concerning the use of one or more of the AI/ML models or AI/ML functionalities.

2. The user device, UE, of claim 1 , wherein the UE is to trigger the one or more actions following the n^th occurrence of the certain event or the n^th occurrence of the certain signaling, with n being an integer greater than 0.

3. The user device, UE, of claim 2, wherein the UE is to trigger the one or more actions only if the n certain events or certain signalings occurred within a predefined time window.

4. The user device, UE, of one of claims 1 to 3, wherein the one or more certain events comprise one or more of the following: an impairment of the communication link between the UE and the one or more entities of the wireless communication network, an impairment of a data transmission on the communication link between the UE and the one or more entities of the wireless communication network.

5. The user device, UE, of claim 4, wherein the UE is to determine the impairment of the communication link if one or more of the following applies: one or more failures of the communication link are experienced, a quality of the communication link drops below a configured or preconfigured threshold or drops during a predefined time period by more than a configured or preconfigured amount, e.g., a reference signal received power, RSRP, or a reference signal received quality, RSRQ, or a radio signal strength indicator, RSSI, or a signal to interference plus noise ratio, SINR, or a signal to noise ratio SNR.

6. The user device, UE, of claim 5, wherein one or more failures comprises one or more of the following: a number of consecutive failures, a number of failures during a predefined time period, e.g., a number of failures within a configured or pre-configured time interval, a percentage of failures during a predefined time period, e.g., a percentage of failures within a configured or pre-configured time interval.

7. The user device, UE, of any one of claims 4 to 6, wherein the UE is to determine the impairment of the data transmission on the communication link if one or more of the following applies: one or more data transmissions are not successful, a ratio of successful and unsuccessful data transmissions from the UE to the one or more entities exceeds a configured or preconfigured threshold, e.g., ratio of HARQ- ACKs to HARQ-NACKs, a signal strength of a radio signal including the data transmission drops below a configured or preconfigured threshold or drops during a predefined time period by more than a configured or preconfigured amount, e.g., a reference signal received power, RSRP, or a reference signal received quality, RSRQ, or a radio signal strength indicator, RSSI, ora signal to interference plus noise ratio, SINR, or a signal to noise ratio SNR, a number or percentage of collisions with transmission of other UEs experienced by the data transmission during a predefined time period exceeds a configured or preconfigured threshold, an interference level detected on the communication link exceeds a configured or preconfigured threshold, a network congestion exceeds a configured or preconfigured threshold, a number of failed RACH attempts exceeds a configured or preconfigured threshold, a number of failed SIB decoding attempts exceeds a configured or preconfigured threshold, a number of failed cell reselection attempts exceeds a configured or preconfigured threshold, a geographical region/location, a scenario type such as urban, suburban or rural.

8. The user device, UE, of any one of the preceding claims, wherein the certain signaling from the network entity, e.g., from a neighboring UE or from a base station, is provided by the network entity when the network entity detected one or more of the certain events on a further communication link between the network entity and the UE or between the network entity and one or more further entities of the wireless communication network, e.g., an impairment of the further communication link or an impairment of a data transmission on the further communication link.

9. The user device, UE, of claim 8, wherein the UE is to receive the certain signaling via a unicast transmission, a groupcast or multicast transmission, or a broadcast transmission.

10. The user device, UE, of claim 9, wherein the certain signaling from the network entity, e.g., from a neighboring UE or from a base station, is a groupcast, e.g. in Group Common-PDCCH (GC-PDCCH), or a broadcast, e.g. a SIB, indicating to all or a group of UEs to performing one or more actions concerning the use of one or more of the AI/ML models or AI/ML functionalities.

11. The user device, UE, of claim 10, wherein the one or more actions concerning the use of one or more of the AI/ML models or AI/ML functionalities comprise to deactivate all and/or some AI/ML models or functionalities in all or certain UEs, e.g., based on an emergency trigger signaling.

12. The user device, UE, of any one of the preceding claims, wherein the UE is to trigger one or more actions concerning the use of one or more of the AI/ML models or AI/ML functionalities only if one or more further configured or preconfigured conditions are met.

13. The user device, UE, of claim 12, wherein the one or more configured or preconfigured conditions comprise one or more of the following: a certain location or area at/in which the UE is located, a signal strength of a radio signal including the data transmission drops below a configured or preconfigured threshold or drops during a predefined time period by more than a configured or preconfigured amount, e.g., a reference signal received power, RSRP, or a reference signal received quality, RSRQ, or a radio signal strength indicator, RSSI, ora signal to interference plus noise ratio, SINR, or a signal to noise ratio SNR, a percentage or a number of LBT failures due to communications from the base station serving the UE exceeds a configured or preconfigured threshold, an absence of an evacuation signal on one or more frequency bands in which the data transmission is performed.

14. The user device, UE, of claim 13, wherein the threshold varies dynamically, depending on the timing condition.

15. The user device, UE, of any one of the preceding claims, wherein the one or more actions comprise one or more of the following: a modification of one or more of the AI/ML models or AI/ML functionalities currently used, a modification of the communication link and continuing using the one or more currently used AI/ML models or AI/ML functionalities for the modified communication link, a modification of one or more of the AI/ML models or AI/ML functionalities currently used and of the communication link, and using the one or more modified AI/ML models or AI/ML functionalities for the modified communication link.

16. The user device, UE, of claim 15, wherein the modification of one or more of the AI/ML models or AI/ML functionalities comprises one or more of the following: deactivating some or all of the currently used AI/ML models or AI/ML functionalities, switching to a different AI/ML model or AI/ML functionality for performing the one or more tasks, e.g., a configured or preconfigured fallback AI/ML model or a fallback AI/ML functionality, adapting some or all of the currently used AI/ML models or AI/ML functionalities, e.g., increasing a quantization granularity, resetting parameters to initial or default values, performing a retraining, or performing a fine-tuning, transitioning into a non-connected state, like the RRCJDLE state or the RRCJNACTIVE state, in which the use of non-connected AI/ML models and functionalities is enabled, switching to a fallback non-AI procedure.

17. The user device, UE, of claim 16, wherein for the non-connected state the UE is to use a non-connected mode AI/ML model or AI/ML functionality being more robust compared to connected mode AI/ML model or AI/ML functionality.

18. The user device, UE, of claim 16 or 17, wherein deactivating some or all of the currently used AI/ML models or AI/ML functionalities comprises one or more of the following further actions: switch off the AI/ML model or the AI/ML functionality, stop performing the one or more tasks, switch to a different task, use a conventional calculation technique for performing the one or more tasks.

19. The user device, UE, of any one of claims 15 to 18, wherein the modification of the communication link comprises one or more of the following: performing a carrier aggregation, e.g., aggregate a carrier in a lower frequency band in case the UE is already aggregating carriers, switching to a carrier which is in another frequency band, e.g., in FR1 and deactivating a carrier in the higher frequency band, switching to a broader beam, e.g., by temporarily deactivating Al beamforming, Switching to a different beam pattern/codebook that better suits current network scenario, performing handover to a new cell with a better communication link, redirecting the UE to less congested cells or sectors to balance the network load and reduce the likelihood of RLF.

20. The user device, UE, of any one of the preceding claims, wherein the UE is report to the wireless communication network, e.g., to a base station thereof, the one or more actions, e.g., via RRC, MAC-CE, or PHY layer signaling.

21 . The user device, UE, of any one of the preceding claims, wherein the one or more of tasks comprise one or more of the following:

- AI/ML model based access to a RAN,

- AI/ML model based network energy saving,

- AI/ML model based load balancing,

- AI/ML model based mobility optimization,

- AI/ML model based modulation and coding scheme, MCS, selection,

- AI/ML model based synchronization,

- AI/ML model based encoding and/or decoding and/or precoding,

- AI/ML model based modulation and/or demodulation,

- AI/ML model based positioning or ranging,

- AI/ML model based joint communication and sensing, JSAC,

- AI/ML model based feedback calculation, e.g., CSI/CQI/PMI/RI feedback,

- AI/ML model based interference management,

- AI/ML model based network traffic forecasting.

22. The user device, UE, of any of the preceding claims, wherein the UE comprise one or more of a power-limited UE, or a hand-held UE, like a UE used by a pedestrian, and referred to as a Vulnerable Road User, VRU, or a Pedestrian UE, P-UE, or an on-body or hand-held UE used by public safety personnel and first responders, and referred to as Public safety UE, PS-UE, or an loT UE or Ambient loT UE, e.g., a sensor, an actuator or a UE provided in a campus network to carry out repetitive tasks and requiring input from a gateway node at periodic intervals, or a mobile terminal, or a stationary terminal, or a cellular loT-UE, an industrial loT-UE, 11 oT, or a SL UE, or a vehicular UE, or a vehicular group leader UE, GL-UE, or a scheduling UE, S-UE, or an loT or narrowband loT, NB-loT, device, a NTN UE, or a WiFi device or WiFi station, STA, or a ground based vehicle, or an aerial vehicle, or a drone, or a moving base station, or road side unit, RSU, or a building, or any other item or device provided with network connectivity enabling the item/device to communicate using the wireless communication network, e.g., a sensor or actuator, or any other item or device provided with network connectivity enabling the item/device to communicate using a sidelink the wireless communication network, e.g., a sensor or actuator, or any sidelink capable network entity.

23. A wireless communication network, like a 3^rd Generation Partnership Project, 3GPP, system, comprising a one or more user devices, UEs, of any one of the preceding claims and one or more base stations, BSs.

24. The wireless communication network of claim 23, wherein the BS comprises one or more of a macro cell base station, or a small cell base station, or a central unit of a base station, or a distributed unit of a base station, or an Integrated Access and Backhaul, IAB, node, or a road side unit, RSU, or a WiFi access point, AP, or a UE, or a SL UE, or a group leader UE, GL-UE, or a relay or a remote radio head, or an AMF, or an SMF, or a core network entity, or mobile edge computing, MEC, entity, or a network slice as in the NR or 5G core context, or any transmission/reception point, TRP, enabling an item or a device to communicate using the wireless communication network, the item or device being provided with network connectivity to communicate using the wireless communication network.

25. A method for operating a user device, UE, for a wireless communication network, wherein the UE is configured or preconfigured with at least one Artificial Intelligence/Machine Learning model, AI/ML model, or at least one AI/ML functionality for performing one or more tasks associated with data transmissions on a communication link between the UE and one or more network entities of the wireless communication network, the method comprising: monitoring the communication link for one or more certain events, and responsive to detecting one or more of the certain events on the communication link or responsive to a certain signaling from a network entity of the wireless communication network, triggering one or more actions concerning the use of one or more of the AI/ML models or AI/ML functionalities.

26. A non-transitory computer program product comprising a computer readable medium storing instructions which, when executed on a computer, perform the method of claim 25.