Selecting measurement resources for training a UE sided model ML for ai / ML radio measurement predictions

Abstract

Systems and methods are disclosed for selecting measurement resources for training a User Equipment (UE)-sided model for Artificial Intelligence (AI) / Machine Learning (ML) radio measurement predictions are disclosed. In one embodiment, a method performed by a UE for data collection for training of one or more AI / ML models or functionalities comprises receiving, from a network node, first information that indicates a first set of measurement resources. The method further comprises, based on the first set of measurement resources, selecting one or more second sets of recommended measurement resources in which the UE is to perform radio measurements and / or one or more third sets of measurement resources for prediction in which, once trained, one or more AI / ML models or functions available at the UE are to provide radio measurement predictions, upon performing radio measurements in one or more second sets of measurement resources.

Description

[0001] METHOD FOR SELECTING MEASUREMENT RESOURCES FOR TRAINING A UE SIDED MODEL ML FOR AIML RADIO MEASUREMENT PREDICTIONS RELATED APPLICATIONS This application claims the benefit of provisional patent application serial number 63 / 557,817, filed February 26, 2024, the disclosure of which is hereby incorporated herein by reference in its entirety. TECHNICAL FIELD The present disclosure relates to a cellular communications system and, morespecifically, training of a User Equipment (UE)-side Artificial Intelligence (AI) / Machine Learning (ML) model for AI / ML radio measurement predictions. BACKGROUND One of the key features of 3rdGeneration Partnership Project (3GPP) New Radio (NR), compared to previous generation of wireless networks, is the ability to operate in higher frequencies (e.g., above 10 Gigahertz (GHz)). The available large transmission bandwidths in these frequency ranges can potentially provide large data rates. However, as carrier frequency increases, both pathloss and penetration loss increase. To maintain the coverage at the same level, highly directional beams are required to focus the radio transmitter energy in a particulardirection on the receiver. However, large radio antenna arrays – at both receiver and transmittersides – are needed to create such highly direction beams.To reduce hardware costs, large antenna arrays for high frequencies use time-domain analog beamforming. The core idea of analog beamforming is to share a single radio frequencychain between many (or, potentially, all) of the antenna elements. A limitation of analogbeamforming is that it is only possible to transmit radio energy in using one beam (in one direction) at a given time. The above limitation requires the network (NW) and User Equipment (UE) to perform beam management procedures to establish and maintain suitable transmitter (Tx) / receiver (Rx) beam-pairs. For example, beam management procedures can be used by a transmitter to sweep a geographic area by transmitting reference signals on different candidate beams, during non- overlapping time intervals, using a predetermined pattern. And by measuring the quality of these reference signals at the receiver side, the best transmit and receive beams can be identified.1 NR Beam Management ProceduresBeam management procedures in NR are defined by a set of Layer 1 (L1) / Layer 2 (L2) procedures that establish and maintain a suitable beam pairs for both transmitting and receiving data. A beam management procedure can include the following sub procedures: beam determination, beam measurements, beam reporting, and beam sweeping. In case of downlink transmission from the NW to the UE, P1 / P2 / P3 beam managementprocedures can be performed according to the NR Study Item (SI) technical report to overcomethe challenges of establishing and maintaining the beam pairs when, for example, a UE moves or some blockage in the environment requires changing the beams. Although these scenarios arenot directly mentioned in specifications, there are relevant procedures defined which enable therealization of these scenarios, examples of such realization are depicted in the corresponding figure of each scenario: ^P1: The P1 procedure is used to enable UE measurement on differenttransmission / reception point (TRP) Tx beams to support selection of TRP Tx beams / UE Rx beam(s). During initial access, for example, the NR base station (i.e., the gNodeB, gNB) transmits Synchronization Signal (SS) / Physical Broadcast Channel (PBCH) block(SSB) beams in different directions to cover the whole cell. The UE measures signal quality on corresponding SSB signals to detect and select an appropriate SSB beam, this is shown in Figure 1 (SSB beam selection as part of Initial access procedure according toP1 scenario). Random access is then transmitted on the Random Access Channel (RACH) resources indicated by the selected SSB. The corresponding beam will be usedby both the UE and the network to communicate until connected mode beam management is active. The network infers which SSB beam was chosen by the UE without any explicit signaling. oFor beamforming at TRP, it typically includes an intra / inter-TRP Tx beam sweepfrom a set of different beams. For beamforming at UE, it typically includes a UE Rx beam sweep from a set of different beams. ^P2: The P2 procedure is used to enable UE measurement on different TRP Tx beams topossibly change inter / intra-TRP Tx beam(s). The network can use the SSB beam as an indication of which (narrow) Channel State Information (CSI) Reference Signal (CSI- RS) beams to try; that is, the selected SSB beam can be used to define a candidate set ofnarrow CSI-RS beams for beam management. Once CSI-RS is transmitted, the UE measures the Reference Signal Received Power (RSRP) and reports the result to thenetwork. If the network receives a CSI-RSRP report from the UE where a new CSI-RS beam is better than the old used to transmit Physical Downlink Control Channel (PDCCH) / Physical Downlink Shared Channel (PDSCH), the network updates the serving beam for the UE accordingly, and possibly also modifies the candidate set of CSI-RS beams. The network can also instruct the UE to perform measurements on SSBs. If the network receives a report from the UE where a new SSB beam is better than the previous best SSB beam, a corresponding update of the candidate set of CSI-RS beams for the UE may be motivated. oP2 procedure is performed on a possibly smaller set of beams for beamrefinement than in P1. Note that P2 can be a special case of P1. For example, in connected mode gNB configures the UE with different CSI-RSs and transmits each CSI-RS on corresponding beam. UE then measures the quality of each CSI- RS beam on its current RX beam and sends feedback about the quality of themeasured beams. Thereafter, based on this feedback, gNB will decide and possibly indicates to the UE which beam will be used in future transmissions. This is shown in Figure 2 (CSI-RS Tx beam selection in Downlink according toP2 scenario).^ P3: is used to enable UE measurement on the same TRP Tx beam to change UE Rx beamin the case UE uses beamforming. Once in connected mode, the UE is configured with a set of reference signals. Based on measurements, the UE determines which Rx beam is suitable to receive each reference signal in the set. The network then indicates which reference signals are associated with the beam that will be used to transmit PDCCH / PDSCH, and the UE uses this information to adjust its Rx beam when receiving PDCCH / PDSCH. oIn connected mode, P3 can be used by the UE to find the best Rx beam forcorresponding Tx beam. In this case gNB keeps one CSI-RS Tx beam at a time, and UE performs the sweeping and measurements on its own Rx beams for that specific Tx beam. UE then finds the best corresponding Rx beam based on the measurements and will use it in future for reception when gNB indicates the use of that Tx beam. oIn this regard, Figure 3 illustrates UE Rx beam selection for corresponding CSI-RS Tx beam in DL according to P3 scenario.2 Beam Measurement and Reporting in NRFor beam management, a UE can be configured to report RSRP or / and Signal toInterference plus Noise Ratio (SINR) for each one of up to four beams, either on CSI-RS or SSB.UE measurement reports can be sent either over PUCCH or PUSCH to the network node, e.g., gNB. 2.1 Reference Signal Configurations in NRCSI-RS: A CSI-RS is transmitted over each transmit (Tx) antenna port at the network node and for different antenna ports. The CSI-RS are multiplexed in time, frequency, and code domain such that the channel between each Tx antenna port at the network node and each receive antenna port at a UE can be measured by the UE. The time-frequency resource used for transmitting CSI-RS is referred to as a CSI-RS resource. In NR, the CSI-RS for beam management is defined as a 1- or 2-port CSI-RS resource ina CSI-RS resource set where the filed repetition is present. The following three types of CSI-RS transmissions are supported: ^Periodic CSI-RS: CSI-RS is transmitted periodically in certain slots. This CSI-RStransmission is semi-statically configured using Radio Resource Control (RRC) signalingwith parameters such as CSI-RS resource, periodicity, and slot offset. ^Semi-Persistent CSI-RS: Similar to periodic CSI-RS, resources for semi-persistent CSI-RS transmissions are semi-statically configured using RRC signaling with parameters such as periodicity and slot offset. However, unlike periodic CSI-RS, dynamic signaling is needed to activate and deactivate the CSI-RS transmission. ^Aperiodic CSI-RS: This is a one-shot CSI-RS transmission that can happen in any slot.Here, one-shot means that CSI-RS transmission only happens once per trigger. The CSI- RS resources (i.e., the RE locations which consist of subcarrier locations and Orthogonal Frequency Division Multiplexing (OFDM) symbol locations) for aperiodic CSI-RS aresemi-statically configured. The transmission of aperiodic CSI-RS is triggered by dynamic signaling through PDCCH using the CSI request field in uplink (UL) Downlink Control Information (DCI), in the same DCI where the UL resources for themeasurement report are scheduled. Multiple aperiodic CSI-RS resources can be included in a CSI-RS resource set and the triggering of aperiodic CSI-RS is on a resource set basis. SSB: In NR, an SSB consists of a pair of synchronization signals (SSs), physical broadcastchannel (PBCH), and Demodulation Reference Signal (DMRS) for PBCH. An SSB is mapped to4 consecutive OFDM symbols in the time domain and 240 contiguous subcarriers (20 resource blocks (RBs)) in the frequency domain. NR supports beamforming and beam-sweeping for SSB transmission, by enabling a cell to transmit multiple SSBs in different narrow-beams multiplexed in time. The transmission of these SSBs is confined to a half frame time interval (5 milliseconds (ms)). It is also possible to configure a cell to transmit multiple SSBs in a single wide-beam with multiple repetitions. The design of beamforming parameters for each of the SSBs within a half frame is up to network implementation. The SSBs within a half frame are broadcasted periodically from each cell. The periodicity of the half frames with SS / PBCH blocks is referred to as SSB periodicity, which is indicated by System Information Block (SIB) 1 (SIB1). The maximum number of SSBs within a half frame, denoted by L, depends on the frequency band, and the time locations for these L candidate SSBs within a half frame depends on the SCS of the SSBs. The L candidate SSBs within a half frame are indexed in an ascending order in time from 0 to L-1. By successfully detecting PBCH and its associated DMRS, a UE knows the SSB index. A cell does not necessarily transmit SS / PBCH blocks in all L candidate locations in a half frame, and the resource of the un-used candidate positions can be used for the transmission of data or control signaling instead. It is up to network implementation to decide which candidate time locations to select for SSB transmission within a half frame, and which beam to use for each SSB transmission. 2.2 Measurement Resource Configurations in NRA UE can be configured with the following: ^N≥1 CSI reporting settings (CSI-ReportConfig) and^ M≥1 resource settings (CSI-ResourceConfig).Each CSI reporting setting is linked to one or more resource setting for channel and / orinterference measurement. The CSI framework is modular in the sense that several CSI reporting settings may be associated with the same Resource Setting. The measurement resource configurations for beam management are provided to the UEby RRC information element (IE) (CSI-ResourceConfigs). One CSI-ResourceConfig containsseveral NZP-CSI-RS-ResourceSets and / or CSI-SSB-ResourceSets. A UE can be configured to measure CSI-RSs using the RRC IE NZP-CSI-RS-ResourceSet. A Non-Zero Power (NZP) CSI-RS resource set contains the configurations of Ks ≥1 CSI-RS resources. Each CSI-RS resource configuration resource includes at least the following: ^mapping to resource elements (REs),^ the number of antenna ports, and^ time-domain behavior.Up to 64 CSI-RS resources can be grouped together in an NZP-CSI-RS-ResourceSet.A UE can be configured to measure SSBs using the RRC IE CSI-SSB-ResourceSet. Resource sets comprising SSB resources are defined in a similar manner to the CSI-RS resources defined above. In the case of aperiodic CSI-RS and / or aperiodic CSI reporting, the network node configures the UE with ^^CSI triggering states. Each triggering state contains the aperiodic CSI report setting to be triggered along with the associated aperiodic CSI-RS resource sets. Periodic and semi-persistent resource settings can only comprise a single resource set(i.e., S=1). Aperiodic resource settings can have many resources sets (S>=1), because one out ofthe S resource sets defined in the resource setting is indicated by the aperiodic triggering statethat triggers a CSI report. 2.3 Measurement ReportingThree types of CSI reporting are supported in NR as follows: ^Periodic CSI Reporting on PUCCH: CSI is reported periodically by a UE. Parameterssuch as periodicity and slot offset are configured semi-statically by higher layer RRC signaling from the network node to the UE. ^Semi-Persistent CSI Reporting on PUSCH or PUCCH: similar to periodic CSI reporting,semi-persistent CSI reporting has a periodicity and slot offset which may be semi- statically configured. However, a dynamic trigger from network node to UE may be needed to allow the UE to begin semi-persistent CSI reporting. A dynamic trigger from network node to UE is needed to request the UE to stop the semi-persistent CSI reporting. ^Aperiodic CSI Reporting on PUSCH: This type of CSI reporting involves a single-shot(i.e., one time) CSI report by a UE which is dynamically triggered by the network node using DCI. Some of the parameters related to the configuration of the aperiodic CSI report are semi-statically configured by RRC but the triggering is dynamicIn each CSI reporting setting, the content and time-domain behavior of the report is defined, along with the linkage to the associated Resource Settings.The CSI-ReportConfig IE comprises the following configurations:^ reportConfigTypeo Defines the time-domain behavior (periodic CSI reporting, semi-persistent CSIreporting, or aperiodic CSI reporting) along with the periodicity and slot offset of the report for periodic CSI reporting. ^reportQuantityo Defines the reported CSI parameters -- the CSI content; for example, thePrecoding Matrix Indicator (PMI), Channel Quality Indicator (CQI), Rank Indicator (RI), LI (layer indicator), CRI (CSI-RS resource index) and L1-RSRP. Only certain combinations are possible; for example, ‘cri-RI-PMI-CQI’ is onepossible value and ‘cri-RSRP’ is another) and each value of reportQuantity could be said to correspond to a certain CSI mode. ^codebookConfigo Defines the codebook used for PMI reporting, along with possible codebooksubset restriction (CBSR). NR supported the following two types of PMI codebooks: Type I CSI and Type II CSI. Additionally, the Type I and Type II codebooks each have two different variants: regular and port selection. ^reportFrequencyConfigurationo Define the frequency granularity of PMI and CQI (wideband or subband), ifreported, along with the CSI reporting band, which is a subset of subbands of the bandwidth part (BWP) which the CSI corresponds to ^Measurement restriction in time domain (ON / OFF) for channel and interferencerespectively For beam management, a UE can be configured to report L1-RSRP for up to four different CSI-RS / SSB resource indicators. The reported RSRP value corresponding to the first (best) CRI / SSBRI requires 7 bits, using absolute values, while the others require 4 bits using encoding relative to the first. In NR release 16, the report of L1-SINR for beam management has already been supported. 3Beam PredictionThe use case of beam prediction, which will be standardized as part of 3GPP Release 19work item, consists of spatial beam prediction and temporal beam prediction. The core idea ofthis use case is to predict the “best” beam (or beams) from a Set A of beams using measurementresults from another Set B of beams.According to 3GPP Technical Report (TR) 38.843 V18.1.0, the spatial-domain beamprediction for Set A of beams is based on measurement results of Set B of beams, whereas the temporal beam prediction for Set A of beams is based on the historic measurement results of Set B of beams. Set A and Set B of beams have not been defined yet (left for future study); however, the following two examples illustrate some scenarios that will likely be studied in Release 18: -Set B is a subset of a Set A. For example, Set A is a set of 8 SSB / CSI-RS beams shown inFigure 4 (both light and dark circles). The UE measures Set B (the 4 beams indicated by dark circles). The AI / ML model should predict the best beam (or beams) in Set A using only measurements from Set B. oIn other words, Figure 4 illustrates an example where Set B is a subset of Set A.The figure illustrates a grid-of-beam type radiation pattern: Each row (resp. column) depicts a certain zenith (resp. azimuth) angle from the antenna array. Set Ahas 8 beams and Set B has 4 beams (indicated by dark circles).- Set A and Set B correspond to two different sets of beams. For example, Set A is a set of30 narrow CSI-RS beams, and Set B is a set of 8 wide SSB beams. The UE measures beams in Set B and the AI / ML model should predict the best beam(s) from Set A. oIn other words, Figure 5 illustrates an example where Set A is a set of narrowbeams and Set B is a set of wide beams. The beam prediction can be performed in the gNB and in the UE, and the gain is twofold. From the UE point of view, the UE would be able to generate good radio measurement estimations without really measuring certain resources, thereby saving energy, whereas from the gNB point of view, the gNB can get good radio measurements estimation from the UE without providing the measuring resources, thereby limiting the overhead over the air-interface. Whether the UE can perform the beam prediction on a certain set of resources with a certain accuracy, depends on the applicability conditions of an Artificial Intelligence (AI) / Machine Learning (ML) (also sometimes referred to herein as “AIML”) model / function. Inparticular, an AIML model / function may be trained to perform the beam prediction under certainapplicability conditions. Such applicability conditions need to be fulfilled in order for the AIML model / function to generate the expected output, i.e. beam prediction for this use case, with enough accuracy. The applicability conditions may include a set of parameters / variables under which the AIML model / function was trained. Such set may include for example UE-specific conditions under which the model was trained, as the UE speed, the UE antenna shape, UE sensors information such as UE orientation, motion sensors etc.; whereas some other parameters / variables may depend on the specific network configuration under which the model was trained, e.g. the deployment scenario (e.g. indoor / outdoor), the carrier frequency, the gNB TX port number, the gNB TX power, etc. In order to determine whether an AIML model / function is applicable or not, the UE needs to assess the applicability conditions of such AIML model / function with respect to the output (beam prediction) that need to be generated and received input (e.g. radio measurement resources configured by the gNB). 43GPP Study Item Technical ReportThe following text is an excerpt from 3GPP TR 38.843 regarding performancemonitoring. ***** START EXCERPT FROM 3GPP TR 38.843 ***** Performance monitoring: For the performance monitoring of BM-Case1 and BM-Case2: -Performance metric(s) with the following alternatives:- Alt.1: Beam prediction accuracy related KPIs, e.g., Top-K / 1 beam prediction accuracy- Alt.2: Link quality related KPIs, e.g., throughput, L1-RSRP, L1-SINR, hypotheticalBLER -Alt.3: Performance metric based on input / output data distribution of AI / ML- Alt.4: The L1-RSRP difference evaluated by comparing measured RSRP and predictedRSRP -Benchmark / reference for the performance comparison, including:- Alt.1: The best beam(s) obtained by measuring beams of a set indicated by gNB (e.g.,Beams from Set A) -Alt.4: Measurements of the predicted best beam(s) corresponding to model output (e.g.,Comparison between actual L1-RSRP and predicted RSRP of predicted Top-1 / K Beams) -Signalling / configuration / measurement / report for model monitoring, e.g., signalling aspectsrelated to assistance information (if supported), Reference signals For BM-Case1 and BM-Case2 with a UE-side AI / ML model: -Type1 performance monitoring:- Configuration / Signalling from gNB to UE for measurement and / or reporting- UE may have different operations- Option1: UE sends reporting to NW (e.g., for the calculation of performance metricat NW) -Option2: UE calculates performance metric(s), either reports it to NW or reports anevent to NW based on the performance metric(s) -Indication from NW for UE to do LCM operations- Note: At least the performance and reporting overhead of model monitoring mechanismshould be considered -Type2 performance monitoring (UE-side performance monitoring):- Indication / request / report from UE to gNB for performance monitoring- Note: The indication / request / report may be not needed in some case(s)- Configuration / Signalling from gNB to UE for performance monitoring measurementand / or reporting -UE calculates performance metric(s), either reports it to NW or reports an event to NWbased on the performance metric(s) -If it is for UE-side model monitoring, UE makes decision(s) of modelselection / activation / deactivation / switching / fallback operation - -Indication from NW to UE to do LCM operation- UE reporting of beam measurement(s) based on a set of beams indicated by gNB- Signalling, e.g., RRC-based, L1-based- Note: Performance and UE complexity, power consumption should be considered- Mechanism that facilitates the UE to detect whether the functionality / model issuitable or no longer suitable Table 7.2.3-1 summarizes applicability of various alternatives for performance metric(s) of AI / ML model monitoring for BM-Case1 and BM-Case2. Table 7.2.3-1: Alternatives for Performance metric(s) of AI / ML model monitoring for BM-Case 1 and BM-Case 2 Alt.1: Beam Alt.2: Link quality Alt.3: Alt.4: The L1-RSRP prediction related KPIs, .e.g., Performance difference accuracy related throughput, L1- metric based on evaluated by KPIs, e.g., Top- RSRP, L1-SINR, input / output data comparing K / 1 beam hypothetical BLER distribution of measured RSRP prediction AI / ML and predicted accuracy RSRP Applicable to all Applicable to all Applicable to allMay not be applicablestudied AI models studied AI models studied AI models to some implementation of AI model (e.g., not output of predicted L1-RSRP) Reflect the Reflect the Reflect the change of Reflect accuracy of the prediction accuracy system / link the statics of the predicted 1-RSRP of AI model performance input / output data Not reflect the Not reflect the Not reflect the Not reflect the system / link prediction accuracy of prediction system / link performance AI model directly performance of AI performance directly directly model directly Not reflect the system / link performance directly Note1: The above analysis shall not give an indication about whether / which metric is supported or specified. Note2: Monitoring performance of the above alternatives are not addressed in the table. ***** END EXCERPT FROM 3GPP TR 38.843 ***** 5NW-Sided vs UE-Sided ModelAs mentioned above, the AI / ML model for beam prediction can be NW-sided or UE- sided (i.e. executed in the gNB or in the UE). 1. If the model is NW-sided, the UE makes RSRP (i.e., layer 1 RSRP or L1-RSRP) and / orSINR (i.e., layer 1 SINR or L1-SINR) measurements and reports the measurement results to the NW for input into the AI / ML model. 2. If the model is UE-sided, the UE both makes the measurements and the AI / ML-model-based prediction, and hence no reporting of the measurements is needed except for the final predicted beam(s). 6Data CollectionA key part of AI / ML-based prediction is data collection, which is essential to train a model, since the model is trained / retrained / finetuned based on collected data. Data collection is performed in several stages of the Life-Cycle Management (LCM). i. First, the model must be trained by collecting measurement data for a large set of UElocations / channel conditions representative for the UE locations / channel conditions that may be encountered during use of the model (i.e. inference). For each UE, preferably all possible narrow Tx beam directions should be swept, i.e. a fairly large set of beams.ii. Second, when using the model for prediction (i.e. inference), measurement data for anyUE to predict beams for must be collected and fed to the AI / ML model. The set of beams to sweep for a UE is here much smaller than during training, since not all narrow beams are swept, only a few wide (or possibly narrow) beams are swept.iii. Finally, measurements are needed to monitor that the model functions well, or otherwisedisable it or update it. According to 3GPP TR 38.843, for a NW-sided model, the data collection procedure would imply the gNB transmitting some signal (e.g. CSI-RS or SSB) using a set of several different Tx beams on the downlink (DL), and the UE collecting and logging associated measurement results, e.g. RSRP. The UE will then report, e.g. periodically, upon events, or on NW-demand, the logged measurements results so that the NW can use this information totrain / retrain / finetune the NW-side model. The training of the NW-side model can occur in thegNB itself or in a NW-node such as the Operations, Administration, and Maintenance (OAM) node. For the UE-side model, the UE may need to collect measurements from the gNB signals(e.g. CSI-RS or SSB) and, once the data collection is completed, such collected data shouldtransferred to a training entity which will be in charge of training / retraining / finetuning the UE- side model based on the collected measurements and possibly on network assistance information such that the collected data measurements can be categorized by the training entity. As an output of the training, the UE-side model will be able to perform beam predictions on certain sets of beams, i.e. set A. For the case of UE-side model, the training entity can be the UE itself (e.g. the application layer of the UE), or a network node, e.g. a radio access node like a gNB or a CoreNetwork (CN) node (e.g. like the Network Data Analytics Function (NWDAF)), or an Over-the-Top (OTT) server, outside 3GPP. This latter approach might be a reasonable solution, because in order to have optimal performances, the trained data set should fit the inference operations at the device which may depend on UE-vendor specific implementations (e.g. software / hardware properties / capabilities), that a NW node may not know entirely. SUMMARY Systems and methods are disclosed for selecting measurement resources for training a User Equipment (UE)-sided model for Artificial Intelligence (AI) / Machine Learning (ML) radiomeasurement predictions are disclosed. In one embodiment, a method performed by a UE fordata collection for training of one or more AI / ML models or functionalities comprises receiving,from a network node, first information that indicates a first set of measurement resources. The method further comprises, based on the first set of measurement resources, selecting one or more second sets of recommended measurement resources in which the UE is to perform radio measurements and / or one or more third sets of measurement resources for prediction in which, once trained, one or more AI / ML models or functions available at the UE are to provide radio measurement predictions, upon performing radio measurements in one or more second sets of measurement resources. In this manner, the UE saves on performing measurements by selecting recommended measurement resources. In one embodiment, the one or more AI / ML models or functions comprise one or more AI / ML models that are part of an AI / ML functionality available at the UE or at a node performing UE-side model training of the one or more AI / ML models for the UE, that corresponds to radio measurement predictions. In one embodiment, receiving the first information that indicates the one or more first sets of measurement resources comprises receiving the first information that indicates the one or more first sets of measurement resources as part of a configuration for data collection for UE- side model training. In one embodiment, receiving the first information that indicates the one or more first sets of measurement resources comprises receiving the first information that indicates the one or more first sets of measurement resources as part of a measurement configuration for performing and reporting of the radio measurements. In one embodiment, receiving the first information that indicates the one or more first sets of measurement resources comprises receiving the first information that indicates the one ormore first sets of measurement resources as part of a measurement configuration indicating a setof candidate measurement resources that can be configured by the network node to the UE to perform data collection for UE-side AI / ML model training. In one embodiment, selecting the one or more second recommended sets of measurement resources and / or the one or more third sets of measurement resources comprises selecting the one or more second recommended sets of measurement resources and the one or more third sets of measurement resources from resources included in the one or more first sets of measurement resources. In one embodiment, selecting the one or more second recommended sets of measurement resources and / or the one or more third sets of measurement resources is performed before training the one or more AI / ML models or functionalities. In one embodiment, selecting the one or more second recommended sets of measurement resources and / or the one or more third sets of measurement resources is performed upon fulfilling any one or more of the following conditions: receiving a request from the network node or from a training entity performing UE-side AI / ML model training, wherein the request is to start data collection for UE-side model training; receiving a request to indicate applicability of the one or more AI / ML models or functionalities available at the UE; receiving a request in response to the UE indicating capability to support the one or more AI / ML models or functionalities; receiving a request in response to UE indicating capability to collect data for AI / ML training. In another embodiment, selecting the one or more second recommended sets of measurement resources and / or the one or more third sets of measurement resources is performed upon fulfilling any one or more of the following conditions: upon determining that radio measurements for data collection for training of the one or more AI / ML models or functionalities has not been previously performed on at least part of the radio resources indicated in the one or more first sets of measurement resources; upon determining that radio measurements for data collection for training of the one or more AI / ML models or functionalities have not been previously performed for the network node transmitting the first information that indicates the one or more first sets of measurement resources; upon determining that radio measurements for data collection for training of the one or more AI / ML models or functionalities have not been previously performed in a geographic area in which the UE islocated at the moment of performing the selecting, upon determining that radio measurementsfor data collection for training of AIML model / functionality have not been performed since a certain amount of time in the area in which the UE is located or in the network node to which the UE is connected at the moment of doing the selection. In one embodiment, the method further comprises transmitting to the network node a firstindication comprising information that indicates the selected one or more second sets ofrecommended measurement resources and / or information that indicates the selected one or morethird sets of measurement resources for predictions. In one embodiment, the first indication istransmitted via Radio Resource Control (RRC) signaling, Medium Access Control (MAC)Control Element (CE), or Uplink Control Information, UCI. In one embodiment, for each of theselected one or more second sets of recommended measurement resources and each of the selected one or more third sets of measurement resources indicated by the information comprised in the first indication, the UE includes an associated set ID. In another embodiment, for each of the selected one or more second sets of recommended measurement resources and each of the selected one or more third sets of measurement resources indicated by the information comprised in the first indication, the UE includes one or more resource IDs associated to resources within that set of measurement resources. In one embodiment, the first indication is transmitted fromthe UE to the network node in response of any of: upon decision to retrain or finetune an existingmodel, wherein the decision is network-triggered; upon receiving a reconfiguration of the first set of measurement resources; being configured by the network node to perform AI / ML-based radio measurement prediction; upon receiving an activation request for the one or more AI / ML models or functionalities from the network node. In another embodiment, the first indication istransmitted from the UE to the network node in response of any of: upon decision to retrain orfinetune an existing model, wherein the decision is initiated by the UE or triggered by a training entity performing UE-side model training of the one or more AI / ML models or functions; uponchange in network or additional conditions; a new model is to be trained by the UE; one or moreof the existing AI / ML models or functions at the UE are not fulfilling associated performance requirements. In one embodiment, the method further comprises, in response to transmitting the firstindication, receiving, from the network node, a second indication comprising information thatindicates a second set of measurement resources on which the UE is to perform radio measurements for data collection for the AI / ML model(s) in order to determine radiomeasurement predictions in the third set(s) of measurement resources and information thatindicates a third set of measurement resources in which the trained AI / ML model(s) is to provideradio measurement predictions upon performing the radio measurements based on the second setof measurement resources. In this manner, the network is enabled to be involved in the selection of the measurement resources. In one embodiment, the second set of measurement resources is equal to or a subset of the one or more second sets of recommended measurement resources. In one embodiment, the third set of measurement resources indicated by the information comprised in the second indication received by the UE from the network node is equal to or a subset of the one or more third sets of measurement resources indicated by the information comprised in the first indication transmitted by the UE to the network node. In one embodiment, the method further comprises, upon selecting the one or more second sets of recommended measurement resources and the one more third sets of measurement resources for prediction, starting to perform the radio measurements on the resources included in the one or more second sets of recommended measurement resources and the one or more third sets of measurement resources for prediction. In one embodiment, the method further comprises sending the radio measurements and an associated set ID and / or resource ID of the radio resource for which data collection was performed to a training entity performing UE-side model training of the one or more AI / ML models / functionalities. In one embodiment, the collected measurements are used to train an AI / ML model at the training entity. In one embodiment, the UE or the training entity performing UE-side model training stores the associated set ID or resource ID for measurement resources used for performing the measurement. In one embodiment, the stored set ID or resource ID is used by the UE or by the training entity to determine the radio measurement resources for which the data collection for training has been performed for the network node that configured the UE with the one or more first sets of measurement resources. In one embodiment, the method further comprises, in response to transmitting the first indication, receiving a third indication indicating that the one or more second sets of recommended measurement resources and / or the one or more third sets of measurement resources are rejected. In one embodiment, one or more applicability conditions of the one or more AI / ML models or functionalities available at the UE are checked by the UE prior to transmitting the first indication. In one embodiment, receiving the first information that indicates the one or more first sets of measurement resources comprises receiving the first information via dedicated signaling or broadcast signaling. In one embodiment, a training entity for training the one or more AI / ML models orfunctionalities is a function located in the UE, and data collected is transmitted from one or more lower layers of the UE to the training entity within the UE. Corresponding embodiments of a UE are also disclosed. In one embodiment, a UE fordata collection for training of one or more AI / ML models or functionalities comprises acommunication interface comprising a transmitter and a receiver. The UE further comprises processing circuitry associated with the communication interface. The processing circuitry isconfigured to cause the UE to receive, from a network node, first information that indicates afirst set of measurement resources. The processing circuitry is further configured to cause the UE to, based on the first set of measurement resources, select one or more second sets of recommended measurement resources in which the UE is to perform radio measurements and / or one or more third sets of measurement resources for prediction in which, once trained, one or more AI / ML models or functions available at the UE are to provide radio measurement predictions, upon performing radio measurements in one or more second sets of measurement resources. Embodiments of a method performed by a network node are also disclosed. In oneembodiment, a method performed by a network node comprises transmitting, to a UE,information indicative of one or more first sets of measurement resources and receiving, from theUE, a first indication comprising any of: information that indicates one or more second sets ofrecommended measurement resources in which the UE is to perform radio measurements; and information that indicates one or more third sets of measurement resources for prediction in which one or more trained AI / ML models or functionalities available at the UE are to provide radio measurement predictions. In one embodiment, the method further comprises determining (a) a second set of measurement resources on which the UE is to perform radio measurements for data collection for the one or more AI / ML models or functionalities in order to determine radio measurement predictions in a third set of measurement resources and (b) the third set of measurement resources, based on the one or more second sets of recommended measurement resources and the one or more third sets of measurement resources for prediction indicated by the information comprised in the first indication. In one embodiment, the method further comprises transmitting a second indication to the UE, the second indication comprising information that indicates the determined second set of measurement resources and information that indicates the determined third set of measurement resources. In one embodiment, the method further comprises transmitting reference signals associated to resources included in the determined second and third sets of measurement resources. Corresponding embodiments of a network node are also disclosed. In one embodiment, a network node comprises processing circuitry configured to cause the network node to transmit,to a UE, information indicative of one or more first sets of measurement resources and receive,from the UE, a first indication comprising any of: information that indicates one or more secondsets of recommended measurement resources in which the UE is to perform radio measurements;and information that indicates one or more third sets of measurement resources for prediction inwhich one or more trained AI / ML models or functionalities available at the UE are to provide radio measurement predictions. BRIEF DESCRIPTION OF THE DRAWINGS The accompanying drawing figures incorporated in and forming a part of this specification illustrate several aspects of the disclosure, and together with the description serve to explain the principles of the disclosure. Figure 1 illustrates Synchronization Signal (SS) / Physical Broadcast Channel (PBCH)Block (SSB) selection as part of an initial access procedure.Figure 2 illustrates Channel State Information (CSI) Reference Signal (CSI-RS) transmit beam selection in downlink. Figure 3 illustrates User Equipment (UE) receives beam selection for a correspondingCSI-RS transmit beam in the downlink. Figure 4 illustrates an example in which Set B is a subset of Set A. Figure 5 illustrates an example in which Set A is a set of narrow beams and Set B is a set of wide beams. Figure 6 illustrates the operation of a network node (NW) and a UE in accordance with embodiments of the present disclosure. Figure 7 shows an example of a communication system in accordance with some embodiments. Figure 8 shows a UE in accordance with some embodiments. Figure 9 shows a network node in accordance with some embodiments. Figure 10 is a block diagram illustrating a virtualization environment in which functions implemented by some embodiments may be virtualized. DETAILED DESCRIPTION The embodiments set forth below represent information to enable those skilled in the art to practice the embodiments and illustrate the best mode of practicing the embodiments. Upon reading the following description in light of the accompanying drawing figures, those skilled in the art will understand the concepts of the disclosure and will recognize applications of these concepts not particularly addressed herein. It should be understood that these concepts and applications fall within the scope of the disclosure. Some of the embodiments contemplated herein will now be described more fully with reference to the accompanying drawings. Embodiments are provided by way of example to convey the scope of the subject matter to those skilled in the art. There currently exist certain challenge(s) related to the use of Artificial Intelligence (AI) / Machine Learning (ML) model for predictions (e.g., beam predictions) in a wirelesscommunication system such as, e.g., a 3rd Generation Partnership (3GPP) 5th Generation (5G) (orfuture generation) system. Related to beam prediction of User Equipment (UE)-side models, the training phase of an AI / ML model / functionality consists of the UE measuring the channel andcollecting data to be used by the training entity to train / retrain / finetune the AI / MLmodel / functionality. In particular, during this phase, the UE measures the channel in certainradio resources, e.g. Channel State Information (CSI) Reference Signal (CSI-RS) resourcesand / or Synchronization Signal (SS) / Physical Broadcast Channel (PBSCH) blocks (SSBs), andbased on these measurements, it will be possible to determine the radio resources, say set B, that need to be measured during the inference by the UE in order for the AI / ML model / functionalityto generate a radio measurement prediction(s) on certain radio resources, say set A. For UE sided model, if the resources (set B) in which the UE should train the AI / ML model / functionality are completely up to the UE, several challenges can be observed. First, set Brequires certain network configuration (i.e. reference signal (RS) transmissions) for the UE to beable to perform those measurements for inference purposes. The network may not be aware ofthe resources that the UE needs to measure in order to collect data for training purposes,especially if the UE-side model is trained in a node different than the New Radio (NR) base station (i.e., gNodeB, gNB). Additionally, each UE may request a different network configuration, which would require an excessive amount of additional referencesignal transmissions to accommodate for different UE needs, especially because these referencesignal transmissions are to be used by the UE to collect measurement for training purposes, rather than classical measurements to be reported to the gNB for data scheduling purposes. Fromthe network (NW) perspective, this diminishes the benefits of running an AI / ML model at theUE side, and it also creates lots of extra overhead over the air interface. Second, the NW has a better understanding of which beams are not likely to be picked within the deployment and predictions for those beams can be sufficient, while actual measurements are preferred and wanted for certain beams. If set A / B selection (see Section 3 of the Background section above for description of “set A” and “set B”) is completely up to the UE, there is a risk that the NW deactivates the AI / ML model / functionality, since it would generate radio measurement predictions on radioresources that are not of interest, and the UE would have just wasted power for the training.Certain aspects of the disclosure and their embodiments may provide solutions to these or other challenges. Embodiments of systems and methods are disclosed for enabling a UE to transmit a recommended set A / B for training an AI / ML beam prediction model and obtain an early feedback from the NW concerning the selected beams in set A and / or set B before initiating model training and / or training data collection. The early feedback enables the UE to obtain knowledge about the NW preferred set A / B prior to training and by that avoid wasting resources and energy to train a model that does not fit the NW needs. Some example embodiments of a method performed by a UE are as follows: ^A1. A method performed by a UE to perform data collection for training of one or moreAI / ML models / functionalities based on one or more first sets of measurement resourcesthat are configured by a network node (e.g., a gNB) to the UE, the method comprising:o based on a configuration of one or more first sets of measurement resourcesreceived from a network node, selecting the following sets of radio measurementresources:^ one or more second sets of recommended measurement resources in whichto perform radio measurements, say recommended set B, ^one or more third set of measurement resources for prediction in which thetrained one or more AI / ML models / functionalities provide radio measurement predictions, say set A, upon performing radio measurements in one or more second sets of measurement resources (set B).^ A2. The method according to A1, wherein the one or more AI / ML models / functionalitiescomprise one or more AI / ML models that are part of an AIML functionality available at the UE or at a node performing the UE-side model training for the UE, that corresponds to radio measurement predictions.^ A3. The method according to A1, further comprising receiving (e.g., from the networknode) information that indicates the one or more first sets of measurement resourcesconfigured by the network node to the UE.^ A3A. The method according to A3, wherein receiving the information that indicates theone or more first sets of measurement resources comprises receiving the information that indicates the one or more first sets of measurement resources as part of a configuration for data collection for UE-side model training.^ A4. The method according to A3, wherein receiving the information that indicates theone or more first sets of measurement resources comprises receiving the information that indicates the one or more first sets of measurement resources as part of a measurement configuration for performing and reporting of the radio measurements.^ A5. The method according to A3, wherein receiving the information that indicates theone or more first sets of measurement resources comprises receiving the information that indicates the one or more first sets of measurement resources as part of a measurement configuration indicating a set of candidate measurement resources that can be configured by the network node to the UE to perform data collection for UE side model training.^ A6. The method according to A1, wherein selecting the one or more secondrecommended sets of measurement resources and the one or more third sets ofmeasurement resources comprises selecting the one or more second recommended sets of measurement resources and the one or more third sets of measurement resources from resources included in the one or more first sets of measurement resources.^ A7. The method according to A1, wherein selecting the one or more secondrecommended sets of measurement resources and the one or more third sets of measurement resources is performed before training the one or more AI / ML models / functionalities.^ A8. The method according to A7, wherein selecting the one or more secondrecommended sets of measurement resources and the one or more third sets of measurement resources is performed upon fulfilling any one or more of the following conditions: oReceiving a request from the network node or from a training entity performingthe UE-side model training, wherein the request is to start data collection for UE- side model training, oReceiving a request to indicate applicability of the AIML models / functionalitiesavailable at the UE, oReceiving a request in response to UE indicating capability to support the AIMLmodels / functionalities, oReceiving a request in response to UE indicating capability to collect data fortraining, oUpon determining that radio measurements for data collection for training ofAIML model / functionality has not been previously performed on at least part of the radio resources indicated in the one or more first sets of measurementresources, oUpon determining that radio measurements for data collection for training ofAIML model / functionality has not been previously performed for the network node transmitting the one or more first sets of measurement resources,o Upon determining that radio measurements for data collection for training ofAIML model / functionality has not been previously performed in the area in which the UE is located at the moment of doing the selection, oUpon determining that radio measurements for data collection for training ofAIML model / functionality has not been performed since a certain amount of time in the area in which the UE is located or in the network node to which the UE is connected at the moment of doing the selection.^ A9. The method according to A1, wherein each of the one or more first sets ofmeasurement resources is associated to an identification ID.^ A10. The method according to A1, wherein each of the one or more first sets ofmeasurement resources is associated to a set ID^ A11. The method according to A1, wherein each of one or more resources comprised inthe one or more first sets of measurement resources is associated to a resource ID.^ A12. The method according to A10, wherein the set ID for one of the one or more firstsets of measurement resources is unique within the cell.^ A13. The method according to A11, wherein the resource ID for one resource within theone or more first sets of measurement resources is unique within the cell.^ A14. The method according to A1, further comprising transmitting to the network nodein a first indication any of: oinformation that indicates the selected one or more second sets of recommendedmeasurement resources (set B) oinformation that indicates the selected one or more third sets of measurementresources for predictions (set A)^ A15. The method according to A14, wherein for each of the selected one or more secondsets of recommended measurement resources and each of the selected one or more third sets of measurement resources indicated by the information comprised in the firstindication, the UE includes an associated set ID.^ A16. The method according to A14, wherein for each of the selected one or more secondsets of recommended measurement resources and each of the selected one or more third sets of measurement resources indicated by the information comprised in the firstindication, the UE includes one or more resource IDs associated to resources within that set of (recommended) measurement resources.^ A17. The method according to A14, further comprising, in response to transmitting thefirst indication, receiving (e.g., from the network node) a second indication comprising:o information that indicates a second set of measurement resources on which theUE is to perform radio measurements for data collection for the AI / ML model(s) in order to determine radio measurement predictions in the third set(s) ofmeasurement resources; and oinformation that indicates a third set of measurement resources in which thetrained AI / ML Model is to provide radio measurement predictions uponperforming the radio measurements based on the second set of measurement resources.^ A17A. The method according to A17, wherein the second set of measurement resourcesis equal to or a subset of the one or more second sets of recommended measurementresources.^ A18. The method according to A17, wherein the third set of measurement resourcesindicated by the information comprised in the second indication received by the UE fromthe network node is equal to or a subset of the one or more third sets of measurementresources indicated by the information comprised in the first indication transmitted by theUE to the network node.^ A19 The method according to A17, wherein the second indication is received by the UEas part of a configuration for performing radio measurements.^ A20. The method according to A17, wherein the second indication is received by the UEas part of a configuration for data collection for UE-side model training.^ A21. The method according to A17, further comprising, upon receiving the secondindication, transmitting (e.g., to the network node) a request for radio transmissionsrequired for performing the radio measurements on the resources included in the secondand third sets of measurement resources indicated by the information comprised in thesecond indication.^ A22. The method according to A21, wherein the request comprises an associated set IDfor the second set of measurement resources and an associated set ID for the third set of measurement resources.^ A23. The method according to A17, further comprising, upon receiving the secondindication, starting to perform the radio measurement on the resources included in thesecond and third sets of measurement resources.^ A24. The method according to A1 or A14, further comprising, upon selecting the one ormore second sets of recommended measurement resources and the one more third sets ofmeasurement resources for prediction (and optionally transmitting the first indication tothe network node), starting to perform the radio measurements on the resources includedin the one or more second sets of recommended measurement resources and the one or more third sets of measurement resources for prediction.^ A25. The method according to any of A23 or A24, further comprising sending the radiomeasurements and an associated set ID and / or resource ID of the radio resource for which data collection was performed to a training entity performing UE-side model training of the one or more AI / ML models / functionalities.^ A26. The method according to any of A23, A24, A25, wherein the UE or the trainingentity performing the UE-side model training logs / stores the associated set ID or resource ID for measurement resources used for performing the measurement.^ A27. The method according to A25, wherein the collected measurements are used to trainan AI / ML model at the training entity.^ A28. The method according to A26, wherein the logged set ID or resource ID is used bythe UE or by the training entity to determine the radio measurement resources for which the data collection for training has been performed for the network node that configured the UE with the one or more first sets of measurement resources.^ A29. The method according to any of A23 or A24, wherein the collected measurementsare not reported to the network node.^ A30. The method according to A14, wherein the first indication is transmitted from theUE to the network node in response of any of: oupon decision to retrain / finetune an existing model, wherein the decision istriggered by the NW or initiated by the UE, or triggered by the training entity performing the UE-side model training. oUpon receiving a reconfiguration of the first set of measurement resources.o Upon change in the NW configuration or additional conditions. As non-limitingexample, a change in the NW antenna configuration or antenna pattern, the existing model at the UE becomes no longer applicable, and a UE initiates training of a new model. oA new model is to be trained by the UE.o One or more of the existing models at the UE are not fulfilling the performancerequirements. oBeing configured by the gNB to perform AIML-based radio measurementprediction. oUpon AIML models / functionalities activation is request received from the gNB^ A31. The method according to A14, further comprising, in response to transmitting thefirst indication, receiving a third indication indicating that the one or more second sets ofrecommended measurement resources and / or the one or more third sets of measurementresources are rejected.^ A32. The method according to A31, wherein in response to receiving the third indication,the UE does not proceed with the AI / ML model training based on the selected second and third measurement resources.^ A33. The method according to A14, wherein one or more applicability conditions of theone or more AIML models / functionalities available at the UE are checked by the UE prior to transmitting the first indication.^ A34. The method according to A1, wherein each of the one or more first sets ofmeasurement resources comprise any of: oa set of SSB for a cello a set of CSI-RS resources for a cello a set of SS / PBCH block resource set for a cello a set of cellso a set of frequencieso a set of SSB for a list of cellso a set of CSI-RS resources for a list of cellso a set of SS / PBCH block resource set for a list of cells^ A35. A method according to any of A23 or A24, wherein an output of the trained one ormore AI / ML models / functionalities at the UE is radio measurement predictions on thethird set of measurement resources comprising prediction results for one or more measurement quantities, such as the RSRP, RSRQ, SINR, RSSI level, associated to the second set of measurement resources.^ A36. A method according to A35, wherein the radio measurement prediction resultscomprise any of: othe measured quantities for each of the one or more resources in the third set ofmeasurement resources othe measured quantities for the best resources in terms of measured quantitiesamong the resources in the second and / or third set of measurement resources, wherein the number of best resources can be a fixed or configured number othe measured quantities for the worst resources in terms of measured quantitiesamong the resources in the second and / or third set of measurement resources, wherein the number of worst resources can be a fixed or configured number othe average measured quantities for the resources in the second and / or third set ofmeasurement resources. othe variance of the measured quantities for the resources in the second and / orthird set of measurement resources. othe accuracy of the reported predictions results^ A37. A method according to A36, wherein the radio measurement prediction results canfurther include:o a time instance when the prediction results are valid, for example indicated in anabsolute UTC time, or in a NR time-unit in respect to when the second set of measurement resources are measured. ^For example, a time-index relative to when the first measurement of thesecond set of measurement resources are performed ^For example, a time-index relative to when the last measurement of thesecond set of measurement resources are performed oa time-window for how long the radio measurement prediction results are valid,for example a certain number of NR-time units from the NW receives the radio measurement prediction results. Or in respect to the time-instance in bullet above. oa time stamp indicating the point in time (indicated in an absolute UTC time, or ina NR time-unit) in which the data collection for the training purposes started or stopped. oa time stamp indicating the point in time (indicated in an absolute UTC time, or ina NR time-unit) in which a radio measurement prediction was performed othe location indicating the point in time (indicated in an absolute UTC time, or ina NR time-unit) in which the data collection for the training purposes started or stopped. othe location indicating the point in time (indicated in an absolute UTC time, or ina NR time-unit) in which a radio measurement prediction was performed^ A38. A method according to A1, further comprising receiving (e.g., from the networknode) information that indicates the one or more first sets of measurement resources viaRRC signaling dedicated to the UE, or broadcast signaling (e.g., SIB).^ A39. A method according to A14, wherein the first indication is transmitted via RRCsignaling (UEAssistanceInformation), or MAC (MAC CE), or UCI.^ A40. A method according to A17 or A33, wherein the second and / or third indication isreceived via RRC dedicated signaling or MAC (MAC CE), PDCCH.^ A41. A method according to A33, the UE indicates availability of AL / MLmodel / functionality that is applicable to conditions comprising training based on the second and third set for measurements resources.^ A42. A method according to any of the previous methods, wherein the training entity is afunction located in a RAN network node, gNB, or core network node, or OTT server, or UE.^ A43. A method according to A42, wherein if the training entity is a function located inthe UE, the data collected are transmitted from the UE lower layers to the said training entity within the UE. Some example embodiments of method performed by a network node are as follows: ^B1. A method performed by a network node (e.g., a RAN node such, e.g., a gNB), themethod comprises transmitting, to a UE (e.g., via dedicated or broadcast signaling) information indicative of one or more first sets of measurement resources.^ B2. A method according to B1, further comprising receiving, from the UE, a firstindication comprising any of:o information that indicates one or more second sets of recommended measurementresources (set B) in which the UE is to perform radio measurements; and oinformation that indicates the selected one or more third sets of measurementresources for prediction (set A) in which one or more trained AI / MLmodels / functionalities available at the UE are to provide radio measurement predictions. ^B3. A method according to B2, further comprising: determining:o a second set of measurement resources on which the UE is to perform radiomeasurements for data collection for the one or more AI / ML models / functionalities in order to determine radio measurement predictions in a third set of measurement resources, and othe third set of measurement resources,based on the one or more second sets of recommended measurement resources and theone or more third sets of measurement resources for prediction indicated by the informationcomprised in the first indication. ^B4. A method according to B3, further comprising transmitting a second indication to theUE, the second indication comprising: oinformation that indicates the determined second set of measurement resources;and oinformation that indicates the determined third set of measurement resources.^ B5. A method according to B4, further comprising transmitting reference signalsassociated to resources included in the determined second and third sets of measurementresources (e.g., for the UE to perform radio measurements).^ B6. A method according to B1, further comprising transmitting reference signalsassociated to resources included in the one or more first sets of measurement resources(e.g., for the UE to perform radio measurements).Certain embodiments may provide one or more of the following technical advantage(s).The benefits of the proposed solution are twofold. On one hand, the UE saves on performingmeasurements by offering different alternatives for set A,B to accommodate for the networks need. On the other hand, if configured correctly, the network (e.g., gNB) can save on reference signal transmissions. Another benefit is that the UE can provide information on certain alternatives that fits onto its own hardware, and alternatives that provide the UE with its own optimal trade-off between energy saving and prediction performance in finding the best beam. Moreover, the network is the consumer of the UE sided prediction; therefore, it is beneficial that the network has some level of involvement in the selection of set A / B for the UE sided model to ensure that the model developed by the UE is aligned with the network’s needs. This does not mean that the network has to dictate set A and B for the training of the UE sided model. The UE can train for different alternatives of set A, B. In this case, the UE can optimizebased on its own AI / ML capabilities, and the network has the final decision on which alterativeof set A / B should be used by the UE. In this way, the network can potentially reduce on reference signal transmissions by aligning the set B among different UEs. Now, a more detailed description of embodiments of the present disclosure will be provided. The following excerpt from 3GPP Technical Specification (TS) 38.331 shows thedefinition of a Non-Zero Power (NZP) Channel State Information (CSI) Reference Signal (CSI-RS) Resource Information Element (IE), the NZP CSI-RS Resource Set IE, the CSI ResourceConfig IE, and the CSI Report Config IE, which may be beneficial for understanding certainembodiments of the present disclosure.***** START EXCERPT FROM 3GPP TS 38.331 ***** NZP-CSI-RS-Resource The IE NZP-CSI-RS-Resource is used to configure Non-Zero-Power (NZP) CSI-RS transmitted in the cell where the IE is included, which the UE may be configured to measure on (see TS 38.214

[0019] , clause 5.2.2.3.1). A change of configuration between periodic, semi-persistent or aperiodic for an NZP-CSI-RS-Resource is not supported without a release and add. NZP-CSI-RS-Resource information element-- ASN1START-- TAG-NZP-CSI-RS-RESOURCE-STARTNZP-CSI-RS-Resource ::= SEQUENCE { nzp-CSI-RS-ResourceId NZP-CSI-RS-ResourceId, resourceMapping CSI-RS-ResourceMapping, …… NZP-CSI-RS-ResourceSet information element-- ASN1START-- TAG-NZP-CSI-RS-RESOURCESET-STARTNZP-CSI-RS-ResourceSet ::= SEQUENCE { nzp-CSI-ResourceSetId NZP-CSI-RS- ResourceSetId, nzp-CSI-RS-Resources SEQUENCE (SIZE (1..maxNrofNZP-CSI-RS-ResourcesPerSet)) OF NZP-CSI-RS- ResourceId, repetition ENUMERATED { on, off } …. OPTIONAL, -- Need S CSI-ResourceConfig information element-- ASN1START-- TAG-CSI-RESOURCECONFIG-STARTCSI-ResourceConfig ::= SEQUENCE { csi-ResourceConfigId CSI-ResourceConfigId, csi-RS-ResourceSetList CHOICE { nzp-CSI-RS-SSB SEQUENCE { …..The IE CSI-ReportConfig is used to configure a periodic or semi-persistent report sent onPUCCH on the cell in which the CSI-ReportConfig is included, or to configure a semi-persistent or aperiodic report sent on PUSCH triggered by DCI received on the cell in whichthe CSI-ReportConfig is included (in this case, the cell on which the report is sent isdetermined by the received DCI). See TS 38.214

[0019] , clause 5.2.1. CSI-ReportConfig information element-- ASN1START-- TAG-CSI-REPORTCONFIG-STARTCSI-ReportConfig ::= SEQUENCE { reportConfigId CSI-ReportConfigId, carrier ServCellIndexOPTIONAL, -- Need SresourcesForChannelMeasurement CSI- ResourceConfigId, csi-IM-ResourcesForInterference CSI-ResourceConfigId OPTIONAL, -- Need R….. ***** END EXCERPT FROM 3GPP TS 38.331 ***** A potential issue with a data-driven approach for training a beam prediction AI / ML model is that different sites / cells may have different antenna / beam configurations. Moreover, even within the same cell, there can be scenarios where antenna / beam configurations are semi- dynamically adjusted to better fit to the current traffic load situations. It is difficult to enable a trained AI / ML model at the UE-side to generalize to many different scenarios and / or antenna / beam configurations. In one embodiment, an identifier is provided to the UE indicating the beam configuration / pattern. For example, in case the UE receive the same beam configuration / pattern ID over two or more cells, it can assume that the CSI resources are usingthe same beams / precoders. This can be achieved via introduction in 3GPP specifications of a“consistency” identifier for its CSI resources, that is then valid over a longer duration than a normal ResourceID, and possibly over multiple cells. This can be introduced via extending any of the IEs according to the following: Existing IE (38.331) New element CommentNZP-CSI-RS- Consistency-nzp-CSI- An ID that indicates Resource RS-ResourceId (other could whether the UE can assume comprise: that the resource is using the -beamID same spatial TX-filter across -precoderID) time and cells NZP-CSI-RS- Consistency-nzp-CSI- An ID that indicates ResourceSet RS-ResourceSetId whether the UE can assume (other could comprise: that the set of resources is -beamSetID using the same spatial TX- -precoderSetID) filters across time and cells CSI-ReportConfig Consistency-csi- An ID that indicates ReportConfigId whether the UE can assume that reported resources are using the same spatial TX- filters across time and cellscsi-ResourceConfig Consistency-csi-An ID that indicates The consistency identifier, or set ID, or resource ID could be generated using any of thefollowing information: ^Consistency Cell ID^ Public Land Mobile Network (PLMN) ID (i.e., PLMN-ID)^ Network Vendor infoo E.g., Vendor ID^ Deployment info such as, e.g.:o Antenna physical tilto Antenna physical directiono Antenna Position^ Beam pattern informationo For example, time when beam pattern or specific beam that impacts a ResourceIDor was changed. Figure 6 illustrates the operation of a network node (NW) and a UE in accordance withembodiments of the present disclosure. The steps of the procedure of Figure 6 are as follows. Step 600: In Step 600, the network node (e.g., a RAN node such as, e.g., a gNB)configures the UE with measurements that can be used by the UE to train an AI / ML model, say a first set of radio measurement resources. In other words, the network node sends, to the UE,information that indicates the first set of radio measurement resources configured to the UE.Note that while a single first set of radio measurement resources is used for this discussion, it isto be understood that there may be one or more first sets of radio measurement resources. Theconfiguration, or information that indicates the first set of measurement resources, can beprovided to the UE in dedicated signaling (e.g., RRC signaling). In one embodiment, the UEmay indicate its capability to support AI / ML model / functionality or the UE may indicate the need to perform model training to the network node. Accordingly, the network node may thenprovide the configuration of the first set of measurement resources to the UE. Alternatively, theconfiguration of the first set of measurement resources may be provided via broadcastingsignaling (e.g., SIB) to the UEs in the cell. Step 602: In Step 602, the UE selects resources in which to perform radio measurement predictions (referred to herein as a third set of measurement resources for predictions, or set A) and resources in which to perform radio measurements necessary for the UE to perform the radio measurement predictions (referred to herein as a second set of recommended measurement resources, or recommended set B) from a set of resources configured by the network node (i.e.,the first set of measurement resources from Step 600). The first set of measurement resourcesmay be resources that the network node has configured to the UE to indicate CSI-RS (and / or other reference signals) belonging to the serving cell that the UE has to measure and for which measurement results should be reported, e.g. via PUCCH. In another embodiment, the first set of measurement resources may be resources indicated separately from the resources in which the UE has to perform radio measurements. In such case, this first set of measurement resources represents a candidate set of measurement resources in which the UE may perform the radio measurements to determine the radio measurement predictions according to one or more AI / ML models / functionalities (candidate second set of measurement resources), and a candidate set of measurement resources for which the UE can determine the radio measurement predictions (candidate third set of measurement resources). The first set of measurement resources can be associated by the network node to an identifier. In particular, an identifier may be associated to each resource set (set ID) included in the first set of measurement resources, or to each individual resource (resource ID) included bythe network node in a resource set (e.g., the first set of measurement resources). Such ID may beunique within the cell, and it may be associated to a specific network configuration. Based on received reference signal transmissions and / or information related to the first set of measurement resources, in Step 602, the UE selects one or more set B (second set of recommended measurement resources) to train the one or more AI models / functionalities available at the UE. The one or more selected set B may compromise one or more of the following beams: -one or more SSB beams- one or more narrow beams, e.g. the beams configured for CSI measurements, and / or- beams that the network node may activate to aid the UE prediction.For each set B, the UE may associate a set A (third set of measurement resources forprediction), wherein the set A may be a subset of the beams listed above. For temporal beam prediction, set B, or subset of set B can be included in set A. The selection of set A and B can be based on:- Performance of the combination of setB / setA, for example it should be above a certainaccuracy level -Cost of measurements, in case the UE is battery constrained, it can select to measure onless set B beams to save energy -Battery type / service type / QoS target / device type- Estimate of achievable power savings from different omission patterns- UE computational capabilities, for instance in terms of number of operations per seconds,type of processor (CPU, GPU), number of CPUs. This could be reported specifically for executing machine learning model or more generally associated to the UE oNote that reducing the number of beams in set B, leads to less model inputs andthereby typically simpler models. -Possible alternatives of Set A and B indicated by the network- Historical information at the UE, for example the UE have been configured with a certainconsistencyID and / or resource ID a threshold number of times, and would hence benefit in creating a model for predicting instead of measuring such resources. oThe UE would in this case, for example use the N most frequent beams in set B,and the other beams in set A. In this way, the UE would at least get measurement of the typically N strongest beams. oIn another embodiment, the UE estimates the correlation among beams and selectthe N beams that are most uncorrelated as part of set B. The selection of such resources by the UE in Step 602 may be triggered by any of thefollowing events: ^Receiving a request from the network node or from the training entity performing theUE-side model training, wherein the request is to start data collection for UE-side model training. oFor example, the training entity may determine that the UE needs to perform datacollection for training given that an AIML model / functionality is not applicable when the UE is connected to such network node , or no AIML model / functionality has been previously trained for this network node . ^Receiving a request to indicate the applicability of the AIML models / functionalitiesavailable at the UE. oThe UE may receive a request from the network node to determine theapplicability of an existing AIML model / functionality, and in response to that the UE may trigger data collection for training.^ Receiving a request in response to UE indicating to the network node the capability tosupport the AIML models / functionalities.^ Receiving a request in response to UE indicating the capability to collect data fortraining.^ Upon determining that radio measurements for data collection for training of AIMLmodel / functionality has not been previously performed on at least part of the radio resources indicated in the first set of measurement resources. oFor example, the training entity may determine that the UE needs to perform datacollection for training given that an AIML model / functionality is not applicable for the resources included in the first set of measurement resources, or no AIML model / functionality has been previously trained on such resources. oThis step may imply the UE indicating to the training entity the first set ofmeasurement resources, and the training entity evaluating whether data collection needs to be done for the said indicated resources.^ Upon determining that radio measurements for data collection for training of AIMLmodel / functionality has not been previously performed for the network node transmitting the first set of measurement resources. oThe training entity may for example determine that no data collection for trainingwas previously performed associated to this network node , and hence it may trigger the UE to perform data collection for training.^ Upon determining that radio measurements for data collection for training of AIMLmodel / functionality has not been previously performed in the area in which the UE is located at the moment of doing the selection. oThe training entity may for example determine that no data collection for trainingwas previously performed associated to the area in which this network node is located, and hence it may trigger the UE to perform data collection for training.^ Upon determining that radio measurements for data collection for training of AIMLmodel / functionality has not been performed since a certain amount of time in the area in which the UE is located or in the network node to which the UE is connected at the moment of doing the selection. oThe training entity may for example determine that the AIML model / functionalitythat may be applicable for this area may be outdated, i.e. certain amount of time has elapsed since last time a model was trained for this network node . The training entity involved in the above steps may be a logical function located in a RAN node, such as the network node, or in a core network node, e.g. the Network DataAnalytics Function (NWDAF), or in an over-the-top server, or in the application layer of the UE.Additionally, the UE may select one or more set B to train one or more AI / ML models,due to: -A new model is to be trained by the UE, e.g. there is no model available at the UE thatis applicable to the NW configuration. -Upon decision to retrain / finetune an existing model, wherein the decision is triggered bythe NW or initiated by the UE. -Upon receiving a reconfiguration of the first set of measurement resources.- Upon change in the NW configuration or additional conditions. As non-limiting example,a change in the NW antenna configuration or antenna pattern, the existing model at the UE becomes no longer applicable, and a UE initiate training of a new / updated model. -One or more of the existing models at the UE are not fulfilling the performancerequirements. -Being configured by the network node to perform AIML-based radio measurementprediction. -Upon AI / ML models / functionalities activation is request received from the network nodeIn one embodiment, upon performing the above selection, the UE may start performing radio measurements on the selected resources from the first set of measurement resources, i.e. on the second sets of recommended measurement resources to generated predictions on the third setof measurement resources for prediction (Step 608). Once the data collection is completed, theUE may log and store the collected data and transmit it to the training entity. The UE may alsolog and store the resources, e.g. the set and / or resource ID associated to which data collection fortraining was performed. For example, the UE may store the IDs associated to the resources of second sets of recommended measurement resources and of the third set of measurement resources for prediction. This information is important for the UE and / or for the training entity to determine whether training was previously performed when the UE was connected to the network node, and the resources associated to which data collection was performed. Hence, in this step, the UE along with the collected measurement results, the UE may collect additional information from the network node that is used for training purposes andtransmit that to the training entity. Such information may include:- The associated consistency ID and / or set ID and / or resource IDs for each ofmeasurement resource for which the measurements are collected- Time stamps at which the measurements are collected- Non-radio information to be used by the UE-sided model, for exampleo Geolocation informationo Sensor informationo UE orientation informationIn this embodiment, the network node transmits the reference signals associated to theresources included in the first set of measurement resources (Step 606). For example, thenetwork node may start transmitting the reference signals associated to the resources included in the first set of measurement resources upon transmitting the first set of measurement resources. Once data collection is completed, the training entity trains one or more AI modelscorresponding to each of the approved set (A,B) combination (Step 610).The UE may then report the availability of an AI / ML model that is applicable to the set A / B used for training to the network node. In another embodiment instead, upon doing the selection in Step 602, the UE indicates the second sets of recommended measurement resources and / or third set of measurement resources for prediction to the network node in a first indication, as described below in Step 602a. Step 602a: In this step, the UE signals a first indication that indicates a recommended setB and / or set A to the network node and asks for confirmation before training a correspondingAI / ML model(s). In the first indication, the UE can report the said set IDs or resource IDs associated to the selected set B and set A. For example, it can report:- Which nzp-CSI-RS-ResourceId that are part of setB / A, or in the “Consistency-nzp-CSI-RS-ResourceId”- Which nzp-CSI-RS-ResourceSetIds (or consistencynzp-CSI-RS-ResourceSetIds ) that arepart of setB / A. oAdditionally, the UEW can indicate which nzp-CSI-RS-ResourceId in case only asubset of the beams in each set are included- Which nzp-CSI-RS-ResourceId that are part of setB / A.o The UE can also include above information on specific -CSI-RS-ResourceId nzp-CSI-RS-ResourceSetIds that are part of setB / A- Which reportConfigId that are part of setB / A.o The UE can also include above information on specific -CSI-RS-ResourceId nzp-CSI-RS-ResourceSetIds that are part of setB / A- That it only need the SSB beams in set B, and the set A beams according to any of the abovemethods. In some embodiments, the UE may just report either only the second set of recommended measurement resources or the third set of recommended measurement resources. In the first case, it means that the UE would train a model that uses measurements on said second set, whereas it can perform the radio measurement predictions on the other resources included in the first set of measurement resources excluding the resources indicated in the said second set. In the second case, it means that the UE model would be trained to perform the radio measurement predictions on the resources indicated in the said third set using measure radio measurements according to the first set of measurement resources previously configured by the network node excluding the resources indicated in the said third set. In this step, the UE can report this information in the existing framework on capabilities in 3GPP. Alternatively, the UE can report this information via any one or more of RRC, uplink(UL) Medium Access Control (MAC) Control Elements (CE), or Uplink Control Information(UCI). For example, in a MAC CE, the UE can report the set IDs or resource IDs associated tothe selected set A and set B. Two different fields in the MAC CE can be used for the reporting of the set A and set B, or two different MAC CEs associated to different logical channels identities may be reported for the set A and set B. Each bit in the MAC CEs may be associated to a specific set ID or resource ID, or one octet can be used to represent the binary value of a specific set ID or resource ID. In case RRC is used, e.g. the UEAssistanceInformation message, the message may contain two separate lists indicating the resource IDs or set IDs associated to the selected set A and set B. Step 604: Upon receiving the first indication in Step 602a, the network node can, basedon the reported alternatives of the recommended set (A, B), decide on (i.e., determine) one ormore preferred sets (A,B), i.e. second set of measurement resources and third set of measurementresources, and send a second indication that indicates the one or more preferred sets (A,B) to theUE. The UE receives the second indication from the network that indicates the set B / set A. If thenetwork approves any of the recommended set A / set B that is suggested by the UE in the firstindication of Step 602a, the UE can proceed with Step 608 to start performing measurements.The indication of the approved set A and set B can be signaled to the UE in the second indication via any one or more of RRC messages (e.g. RRC reconfiguration procedure), DL MAC CE, orPDCCH. For example, in a MAC CE, the network node can indicate the set IDs or resource IDs associated to the set A and set B. Two different fields in the MAC CE can be used for the indication by the network node of the set A and set B, or two different MAC CEs associated to different logical channels identities may be indicated by the network node for the set A and set B. Each bit in the MAC CEs may be associated to a specific set ID or resource ID, or one octet can be used to represent the binary value of a specific set ID or resource ID. In case RRC is used, e.g. an RRC message containing a CSI measurement configuration, the message may contain two separate lists indicating the resource IDs or set IDs associated to the selected set A and set B. The second and third sets of measurements indicated by the information contained in thesecond indication may be signaled as part of different information element, e.g. an IE includinginformation that indicates the second set, and another IE including information that indicates thethird set. In another embodiment, the same IE can be used to transmit both. In such case, it is the UE implementation that the determines the second set and the third set from such IE. Forexample, in this case the second set corresponds to the second sets of recommendedmeasurement resources selected from the first set and included in this IE in the second indication, whereas the third set corresponds to the third set of measurement resources for prediction selected from the first set included in this IE in the second indication. The decision on whether the UE recommended set A / B are valid can be based on: -The time instance for such prediction is not useful for the NW, e.g. the NW anywaycannot schedule data in a certain time window (e.g. due to Time Division Duplex configuration) -The beams in set B or set A is seldom used, they may be occasional beam due to someevent (e.g. energy saving operation) -The beams are transmitted in direction that is unwanted by the NW, hence they cannot bepart of set B Step 606: In this step, the network node transmits reference signals on both set A and setB. Note that the network node may transmit, to the UE, information that configures the UE to perform measurements on both set A and set B. Further, in some embodiments, the UE may request the network to configure measurements corresponding to the reference signal transmissions on the approved set A and set B for the purpose of training data collection. Step 608: The UE performs measurements corresponding to the reference signaltransmissions on the approved set A and set B. The measurements are logged / stored by the UEfor the purpose of training the one or more AI / ML models. Hence, according to thisembodiment, the network node may start transmitting the reference signals associated to the resources included in the indicated second and third set of measurement resources for the UE to perform the corresponding data collection. As in the previous embodiment, the collected measurements may also be delivered the training entity along with additional information such as the associated consistency ID and / or set ID and / or resource IDs for each of measurement resource for which the measurements are collected, the time stamps at which the measurements are collected, non-radio information to be used by the UE-sided model, for example Geolocation information, Sensor information, UE orientation information Step 610: Once data collection is completed as per any of the above steps, the trainingentity trains one or more AI models corresponding to each of the approved set (A,B) combination. The UE may, in some embodiments, report the availability of an AI / ML model that isapplicable to the set A / B used for training. The UE can simply acknowledge that it has trained a model according to the network configuration in Step 606. It should be noted that this Step 602 and 4 can be performed by training entity thatdecides on the selection of set B based on the reported measurements from one or more UEs. In this case, the training entity trains one or more AL models and delivers the one or more models with the additional information about set A and B to the UE. An example implementation of an embodiment of the present disclosure may be providedvia the following changes to 3GPP specifications. The network node can for example, whenconfiguring CSI-RS and / or SSB-related measurements, indicate that the UE can use a certainconfiguration for data collection for training (e.g., indicate the first set of measurementresources). In this regard, the bold, italicized information in the CSI-MeasConfig IE shownbelow may be used for this purpose: nzp-ResourceSets)) OF NZP-CSI-RS-ResourceSetIdOPTIONAL, -- Need Ncsi-IM-ResourceToAddModList SEQUENCE (SIZE (1..maxNrofCSI-IM-Resources)) OF CSI-IM- Resource OPTIONAL, -- Need N csi-IM-ResourceToReleaseList SEQUENCE (SIZE (1..maxNrofCSI-IM-Resources)) OF CSI-IM-ResourceId OPTIONAL, -- Need Ncsi-IM-ResourceSetToAddModList SEQUENCE (SIZE (1..maxNrofCSI-IM-ResourceSets)) OF CSI-IM-ResourceSet OPTIONAL, -- Need Ncsi-IM-ResourceSetToReleaseList SEQUENCE (SIZE (1..maxNrofCSI-IM-ResourceSets)) OF CSI-IM-ResourceSetId OPTIONAL, -- Need N csi-SSB-ResourceSetToAddModListForTraining SEQUENCE (SIZE (1..maxNrofCSI-SSB-ResourceSets)) OF CSI-SSB-ResourceSet OPTIONAL, -- Need NOF csi-ResourceConfigToAddModList SEQUENCE (SIZE (1..maxNrofCSI-ResourceConfigurations)) OF CSI-ResourceConfigOPTIONAL, -- Need Ncsi-ResourceConfigToReleaseList SEQUENCE (SIZE (1..maxNrofCSI-ResourceConfigurations)) OFCSI-ResourceConfigIdOPTIONAL, -- Need Ncsi-ReportConfigToAddModList SEQUENCE (SIZE (1..maxNrofCSI-ReportConfigurations)) OFCSI-ReportConfig OPTIONAL, -- Need Ncsi-ReportConfigToReleaseList SEQUENCE (SIZE (1..maxNrofCSI-ReportConfigurations)) OFCSI-ReportConfigId <Text Omitted> }-- TAG-CSI-MEASCONFIG-STOP-- ASN1STOPIn one embodiment, the resources included in the first set of measurement resources as per the above are already measurable by the UE, i.e. the network node (e.g., gNB) already provides the reference signals / SSBs for the UE to perform the measurement. In anotherembodiment, instead, the UE indicates in the first indication the resources that it needs toperform the training. For example, the UE may indicate the second sets of recommended measurement resources and / or the third set of measurement resources for prediction. This first indication may be transmitted for example via RRC (UEAssistanceInformation), or via MAC CE. In response of receiving this first indication, the network node may transmit a secondindication including the second set of measurement resources (setA) and / or a third set ofmeasurement resources(setB) in which the UE should perform the radio measurements as shownby the bold, italicized text in CSI-MeasConfig below: CSI-MeasConfig ::= SEQUENCE { nzp-CSI-RS-ResourceToAddModList SEQUENCE (SIZE (1..maxNrofNZP-CSI-RS-Resources)) OF NZP-CSI-RS-Resource OPTIONAL, -- Need Nnzp-CSI-RS-ResourceToReleaseList SEQUENCE (SIZE (1..maxNrofNZP-CSI-RS-Resources)) OF NZP-CSI-RS-ResourceId OPTIONAL, -- Need Nnzp-CSI-RS-ResourceSetToAddModListForTraining SEQUENCE (SIZE (1..maxNrofNZP-CSI-RS- ResourceSets)) OF NZP-CSI-RS-ResourceSetId OPTIONAL, -- Need N csi-IM-ResourceToAddModList SEQUENCE (SIZE (1..maxNrofCSI-IM-Resources)) OF CSI-IM-Resource OPTIONAL, -- Need Ncsi-IM-ResourceToReleaseList SEQUENCE (SIZE (1..maxNrofCSI-IM-Resources)) OF CSI-IM-ResourceId OPTIONAL, -- Need Ncsi-IM-ResourceSetToAddModList SEQUENCE (SIZE (1..maxNrofCSI-IM-ResourceSets)) OF CSI-IM-ResourceSet OPTIONAL, -- Need N csi-IM-ResourceSetToReleaseList SEQUENCE (SIZE (1..maxNrofCSI-IM-ResourceSets)) OF CSI-IM-ResourceSetId OPTIONAL, -- Need Ncsi-SSB-ResourceSetToAddModListForTraining SEQUENCE (SIZE (1..maxNrofCSI-SSB-ResourceSets)) OF CSI-SSB-ResourceSet OPTIONAL, -- Need Ncsi-SSB-ResourceSetToReleaseListForTraining SEQUENCE (SIZE (1..maxNrofCSI-SSB-ResourceSets)) OF CSI-SSB-ResourceSetId OPTIONAL, -- Need Ncsi-ResourceConfigToAddModList SEQUENCE (SIZE (1..maxNrofCSI-ResourceConfigurations)) OF CSI-ResourceConfig setB-nzp-CSI-RS-ResourceSetToAddModListForTraining SEQUENCE (SIZE (1..maxNrofNZP-CSI-RS- ResourceSets)) OF NZP-CSI-RS-ResourceSetOPTIONAL, -- Need NsetB-nzp-CSI-RS-ResourceSetToReleaseListForTraining SEQUENCE (SIZE (1..maxNrofNZP-CSI-RS-ResourceSets)) OF NZP-CSI-RS-ResourceSetId setB-csi-SSB-ResourceSetToAddModListForTraining SEQUENCE (SIZE (1..maxNrofCSI-SSB-ResourceSets)) OF CSI-SSB-ResourceSetForTraining OPTIONAL, -- Need NsetB-csi-SSB-ResourceSetToReleaseListForTraining SEQUENCE (SIZE (1..maxNrofCSI-SSB-ResourceSets)) OF CSI-SSB-ResourceSetId OPTIONAL, -- Need Ncsi-ResourceConfigToAddModList SEQUENCE (SIZE (1..maxNrofCSI-ResourceConfigurations)) OF CSI-ResourceConfigOPTIONAL, -- Need Ncsi-ResourceConfigToReleaseList SEQUENCE (SIZE (1..maxNrofCSI-ResourceConfigurations)) OF CSI-ResourceConfigIdOPTIONAL, -- Need Ncsi-ReportConfigToAddModList SEQUENCE (SIZE (1..maxNrofCSI-ReportConfigurations)) OFCSI-ReportConfig OPTIONAL, -- Need Ncsi-ReportConfigToReleaseList SEQUENCE (SIZE (1..maxNrofCSI-ReportConfigurations)) OFCSI-ReportConfigId setA-nzp-CSI-RS-ResourceSetToAddModListForTraining SEQUENCE (SIZE (1..maxNrofNZP-CSI-RS- ResourceSets)) OF NZP-CSI-RS-ResourceSetOPTIONAL, -- Need NsetA-nzp-CSI-RS-ResourceSetToReleaseListForTraining SEQUENCE (SIZE (1..maxNrofNZP-CSI-RS- ResourceSets)) OF NZP-CSI-RS-ResourceSetId <Text Omitted> } -- TAG-CSI-MEASCONFIG-STOP-- ASN1STOPFurther Description Figure 7 shows an example of a communication system 700 in accordance with someembodiments. Note that the aspects and embodiments above related to the operation of thenetwork or network node or gNB may be performed by the network node 710 of Figure 7. Likewise, the aspects and embodiments above related to the operation of the UE may be performed by the UE 712 of Figure 7. In the example, the communication system 700 includes a telecommunication network 702 that includes an access network 704, such as a Radio Access Network (RAN), and a core network 706, which includes one or more core network nodes 708. The access network 704 includes one or more access network nodes, such as network nodes 710A and 710B (one or more of which may be generally referred to as network nodes 710), or any other similar Third Generation Partnership Project (3GPP) access nodes or non-3GPP Access Points (APs). Moreover, as will be appreciated by those of skill in the art, a network node is not necessarily limited to an implementation in which a radio portion and a baseband portion are supplied and integrated by a single vendor. Thus, it will be understood that network nodes include disaggregated implementations or portions thereof. For example, in some embodiments, the telecommunication network 702 includes one or more Open-RAN (ORAN) network nodes. An ORAN network node is a node in the telecommunication network 702 that supports an ORAN specification (e.g., a specification published by the O-RAN Alliance, or any similar organization) and may operate alone or together with other nodes to implement one or more functionalities of any node in the telecommunication network 702, including one or more network nodes 710 and / or core network nodes 708. Examples of an ORAN network node include an Open Radio Unit (O-RU), an Open Distributed Unit (O-DU), an Open Central Unit (O-CU), including an O-CU Control Plane (O- CU-CP) or an O-CU User Plane (O-CU-UP), a RAN intelligent controller (near-real time or non- real time) hosting software or software plug-ins, such as a near-real time control application (e.g., xApp) or a non-real time control application (e.g., rApp), or any combination thereof (the adjective “open” designating support of an ORAN specification). The network node may support a specification by, for example, supporting an interface defined by the ORAN specification, such as an A1, F1, W1, E1, E2, X2, Xn interface, an open fronthaul user plane interface, or an open fronthaul management plane interface. Moreover, an ORAN access nodemay be a logical node in a physical node. Furthermore, an ORAN network node may beimplemented in a virtualization environment (described further below) in which one or more network functions are virtualized. For example, the virtualization environment may include an O-Cloud computing platform orchestrated by a Service Management and OrchestrationFramework via an O-2 interface defined by the O-RAN Alliance or comparable technologies.The network nodes 710 facilitate direct or indirect connection of User Equipment (UE), such as by connecting UEs 712A, 712B, 712C, and 712D (one or more of which may be generally referred to as UEs 712) to the core network 706 over one or more wireless connections. Example wireless communications over a wireless connection include transmitting and / or receiving wireless signals using electromagnetic waves, radio waves, infrared waves, and / or other types of signals suitable for conveying information without the use of wires, cables, or other material conductors. Moreover, in different embodiments, the communication system 700 may include any number of wired or wireless networks, network nodes, UEs, and / or any other components or systems that may facilitate or participate in the communication of data and / or signals whether via wired or wireless connections. The communication system 700 may include and / or interface with any type of communication, telecommunication, data, cellular, radio network, and / or other similar type of system. The UEs 712 may be any of a wide variety of communication devices, including wireless devices arranged, configured, and / or operable to communicate wirelessly with the network nodes 710 and other communication devices. Similarly, the network nodes 710 are arranged, capable, configured, and / or operable to communicate directly or indirectly with the UEs 712 and / or with other network nodes or equipment in the telecommunication network 702 to enable and / or provide network access, such as wireless network access, and / or to perform other functions, such as administration in the telecommunication network 702. In the depicted example, the core network 706 connects the network nodes 710 to one or more hosts, such as host 716. These connections may be direct or indirect via one or more intermediary networks or devices. In other examples, network nodes may be directly coupled to hosts. The core network 706 includes one more core network nodes (e.g., core network node 708) that are structured with hardware and software components. Features of these components may be substantially similar to those described with respect to the UEs, network nodes, and / or hosts, such that the descriptions thereof are generally applicable to the corresponding components of the core network node 708. Example core network nodes include functions of one or more of a Mobile Switching Center (MSC), Mobility Management Entity (MME), Home Subscriber Server (HSS), Access and Mobility Management Function (AMF), Session Management Function (SMF), Authentication Server Function (AUSF), Subscription Identifier De-Concealing Function (SIDF), Unified Data Management (UDM), Security Edge Protection Proxy (SEPP), Network Exposure Function (NEF), and / or a User Plane Function (UPF). The host 716 may be under the ownership or control of a service provider other than an operator or provider of the access network 704 and / or the telecommunication network 702, and may be operated by the service provider or on behalf of the service provider. The host 716 may host a variety of applications to provide one or more service. Examples of such applications include live and pre-recorded audio / video content, data collection services such as retrieving and compiling data on various ambient conditions detected by a plurality of UEs, analytics functionality, social media, functions for controlling or otherwise interacting with remote devices, functions for an alarm and surveillance center, or any other such function performed by a server.As a whole, the communication system 700 of Figure 7 enables connectivity between theUEs, network nodes, and hosts. In that sense, the communication system 700 may be configured to operate according to predefined rules or procedures, such as specific standards that include, but are not limited to: Global System for Mobile Communications (GSM); Universal Mobile Telecommunications System (UMTS); Long Term Evolution (LTE), and / or other suitable Second, Third, Fourth, or Fifth Generation (2G, 3G, 4G, or 5G) standards, or any applicable future generation standard (e.g., Sixth Generation (6G)); Wireless Local Area Network (WLAN) standards, such as the Institute of Electrical and Electronics Engineers (IEEE) 802.11 standards (WiFi); and / or any other appropriate wireless communication standard, such as the Worldwide Interoperability for Microwave Access (WiMax), Bluetooth, Z-Wave, Near Field Communication (NFC) ZigBee, LiFi, and / or any Low Power Wide Area Network (LPWAN) standards such as LoRa and Sigfox. In some examples, the telecommunication network 702 is a cellular network that implements 3GPP standardized features. Accordingly, the telecommunication network 702 may support network slicing to provide different logical networks to different devices that are connected to the telecommunication network 702. For example, the telecommunication network 702 may provide Ultra Reliable Low Latency Communication (URLLC) services to some UEs, while providing enhanced Mobile Broadband (eMBB) services to other UEs, and / or massive Machine Type Communication (mMTC) / massive Internet of Things (IoT) services to yet further UEs. In some examples, the UEs 712 are configured to transmit and / or receive information without direct human interaction. For instance, a UE may be designed to transmit information to the access network 704 on a predetermined schedule, when triggered by an internal or external event, or in response to requests from the access network 704. Additionally, a UE may beconfigured for operating in single- or multi-Radio Access Technology (RAT) or multi-standardmode. For example, a UE may operate with any one or combination of WiFi, New Radio (NR), and LTE, i.e. being configured for Multi-Radio Dual Connectivity (MR-DC), such as EvolvedUMTS Terrestrial RAN (E-UTRAN) NR - Dual Connectivity (EN-DC).In the example, a hub 714 communicates with the access network 704 to facilitate indirect communication between one or more UEs (e.g., UE 712C and / or 712D) and network nodes (e.g., network node 710B). In some examples, the hub 714 may be a controller, router, content source and analytics, or any of the other communication devices described herein regarding UEs. For example, the hub 714 may be a broadband router enabling access to the core network 706 for the UEs. As another example, the hub 714 may be a controller that sends commands or instructions to one or more actuators in the UEs. Commands or instructions may be received from the UEs, network nodes 710, or by executable code, script, process, or other instructions in the hub 714. As another example, the hub 714 may be a data collector that acts as temporary storage for UE data and, in some embodiments, may perform analysis or other processing of the data. As another example, the hub 714 may be a content source. For example, for a UE that is a Virtual Reality (VR) headset, display, loudspeaker or other media delivery device, the hub 714 may retrieve VR assets, video, audio, or other media or data related to sensory information via a network node, which the hub 714 then provides to the UE either directly, after performing local processing, and / or after adding additional local content. In still another example, the hub 714 acts as a proxy server or orchestrator for the UEs, in particular if one or more of the UEs are low energy IoT devices. The hub 714 may have a constant / persistent or intermittent connection to the network node 710B. The hub 714 may also allow for a different communication scheme and / or schedule between the hub 714 and UEs (e.g., UE 712C and / or 712D), and between the hub 714 and the core network 706. In other examples, the hub 714 is connected to the core network 706 and / or one or more UEs via a wired connection. Moreover, the hub 714 may be configured to connect to a Machine-to-Machine (M2M) service provider over the access network 704 and / or to another UE over a direct connection. In some scenarios, UEs may establish a wireless connection with the network nodes 710 while still connected via the hub 714 via a wired or wireless connection.In some embodiments, the hub 714 may be a dedicated hub – that is, a hub whose primaryfunction is to route communications to / from the UEs from / to the network node 710B. In otherembodiments, the hub 714 may be a non-dedicated hub – that is, a device which is capable ofoperating to route communications between the UEs and the network node 710B, but which is additionally capable of operating as a communication start and / or end point for certain data channels. Figure 8 shows a UE 800 in accordance with some embodiments. As used herein, a UErefers to a device capable, configured, arranged, and / or operable to communicate wirelessly with network nodes and / or other UEs. Examples of a UE include, but are not limited to, a smartphone, mobile phone, cell phone, Voice over Internet Protocol (VoIP) phone, wireless local loopphone, desktop computer, Personal Digital Assistant (PDA), wireless camera, gaming console or device, music storage device, playback appliance, wearable terminal device, wireless endpoint, mobile station, tablet, laptop, Laptop Embedded Equipment (LEE), Laptop Mounted Equipment (LME), smart device, wireless Customer Premise Equipment (CPE), vehicle, vehicle-mounted or vehicle embedded / integrated wireless device, etc. Other examples include any UE identified by the 3GPP, including a Narrowband Internet of Things (NB-IoT) UE, a Machine Type Communication (MTC) UE, and / or an enhanced MTC (eMTC) UE. A UE may support Device-to-Device (D2D) communication, for example by implementing a 3GPP standard for sidelink communication, Dedicated Short-Range Communication (DSRC), Vehicle-to-Vehicle (V2V), Vehicle-to-Infrastructure (V2I), or Vehicle- to-Everything (V2X). In other examples, a UE may not necessarily have a user in the sense of a human user who owns and / or operates the relevant device. Instead, a UE may represent a device that is intended for sale to, or operation by, a human user but which may not, or which may not initially, be associated with a specific human user (e.g., a smart sprinkler controller). Alternatively, a UE may represent a device that is not intended for sale to, or operation by, an end user but which may be associated with or operated for the benefit of a user (e.g., a smart power meter). The UE 800 includes processing circuitry 802 that is operatively coupled via a bus 804 to an input / output interface 806, a power source 808, memory 810, a communication interface 812, and / or any other component, or any combination thereof. Certain UEs may utilize all or a subset of the components shown in Figure 8. The level of integration between the components may vary from one UE to another UE. Further, certain UEs may contain multiple instances of a component, such as multiple processors, memories, transceivers, transmitters, receivers, etc. The processing circuitry 802 is configured to process instructions and data and may be configured to implement any sequential state machine operative to execute instructions stored as machine-readable computer programs in the memory 810. The processing circuitry 802 may be implemented as one or more hardware-implemented state machines (e.g., in discrete logic, Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), etc.); programmable logic together with appropriate firmware; one or more stored computer programs, general purpose processors, such as a microprocessor or Digital Signal Processor (DSP), together with appropriate software; or any combination of the above. For example, the processing circuitry 802 may include multiple Central Processing Units (CPUs). In the example, the input / output interface 806 may be configured to provide an interface or interfaces to an input device, output device, or one or more input and / or output devices. Examples of an output device include a speaker, a sound card, a video card, a display, a monitor, a printer, an actuator, an emitter, a smartcard, another output device, or any combination thereof. An input device may allow a user to capture information into the UE 800. Examples of an input device include a touch-sensitive or presence-sensitive display, a camera (e.g., a digital camera, a digital video camera, a web camera, etc.), a microphone, a sensor, a mouse, a trackball, a directional pad, a trackpad, a scroll wheel, a smartcard, and the like. The presence-sensitive display may include a capacitive or resistive touch sensor to sense input from a user. A sensor may be, for instance, an accelerometer, a gyroscope, a tilt sensor, a force sensor, a magnetometer, an optical sensor, a proximity sensor, a biometric sensor, etc., or any combination thereof. An output device may use the same type of interface port as an input device. For example, a Universal Serial Bus (USB) port may be used to provide an input device and an output device. In some embodiments, the power source 808 is structured as a battery or battery pack. Other types of power sources, such as an external power source (e.g., an electricity outlet), photovoltaic device, or power cell, may be used. The power source 808 may further include power circuitry for delivering power from the power source 808 itself, and / or an external power source, to the various parts of the UE 800 via input circuitry or an interface such as an electrical power cable. Delivering power may be, for example, for charging of the power source 808. Power circuitry may perform any formatting, converting, or other modification to the power from the power source 808 to make the power suitable for the respective components of the UE 800 to which power is supplied. The memory 810 may be or be configured to include memory such as Random Access Memory (RAM), Read Only Memory (ROM), Programmable ROM (PROM), Erasable PROM (EPROM), Electrically EPROM (EEPROM), magnetic disks, optical disks, hard disks, removable cartridges, flash drives, and so forth. In one example, the memory 810 includes one or more application programs 814, such as an operating system, web browser application, a widget, gadget engine, or other application, and corresponding data 816. The memory 810 may store, for use by the UE 800, any of a variety of various operating systems or combinations of operating systems. The memory 810 may be configured to include a number of physical drive units, such as Redundant Array of Independent Disks (RAID), flash memory, USB flash drive, external hard disk drive, thumb drive, pen drive, key drive, High Density Digital Versatile Disc (HD-DVD) optical disc drive, internal hard disk drive, Blu-Ray optical disc drive, Holographic Digital Data Storage (HDDS) optical disc drive, external mini Dual In-line Memory Module (DIMM), Synchronous Dynamic RAM (SDRAM), external micro-DIMM SDRAM, smartcard memory such as a tamper resistant module in the form of a Universal Integrated Circuit Card (UICC) including one or more Subscriber Identity Modules (SIMs), such as a Universal SIM (USIM) and / or Internet Protocol Multimedia Services Identity Module (ISIM), other memory, or any combination thereof. The UICC may for example be an embedded UICC (eUICC), integrated UICC (iUICC) or a removable UICC commonly known as a ‘SIM card.’ The memory 810 may allow the UE 800 to access instructions, application programs, and the like stored on transitory or non-transitory memory media, to off-load data, or to upload data. An article of manufacture,such as one utilizing a communication system, may be tangibly embodied as or in the memory810, which may be or comprise a device-readable storage medium. The processing circuitry 802 may be configured to communicate with an access network or other network using the communication interface 812. The communication interface 812 may comprise one or more communication subsystems and may include or be communicatively coupled to an antenna 822. The communication interface 812 may include one or more transceivers used to communicate, such as by communicating with one or more remote transceivers of another device capable of wireless communication (e.g., another UE or a network node in an access network). Each transceiver may include a transmitter 818 and / or a receiver 820 appropriate to provide network communications (e.g., optical, electrical, frequency allocations, and so forth). Moreover, the transmitter 818 and receiver 820 may be coupled to one or more antennas (e.g., the antenna 822) and may share circuit components, software, or firmware, or alternatively be implemented separately. In the illustrated embodiment, communication functions of the communication interface 812 may include cellular communication, WiFi communication, LPWAN communication, data communication, voice communication, multimedia communication, short-range communicationssuch as Bluetooth, NFC, location-based communication such as the use of the Global PositioningSystem (GPS) to determine a location, another like communication function, or any combination thereof. Communications may be implemented according to one or more communication protocols and / or standards, such as IEEE 802.11, Code Division Multiplexing Access (CDMA), Wideband CDMA (WCDMA), GSM, LTE, NR, UMTS, WiMax, Ethernet, Transmission Control Protocol / Internet Protocol (TCP / IP), Synchronous Optical Networking (SONET), Asynchronous Transfer Mode (ATM), Quick User Datagram Protocol Internet Connection (QUIC), Hypertext Transfer Protocol (HTTP), and so forth. Regardless of the type of sensor, a UE may provide an output of data captured by its sensors, through its communication interface 812, via a wireless connection to a network node. Data captured by sensors of a UE can be communicated through a wireless connection to a network node via another UE. The output may be periodic (e.g., once every 15 minutes if it reports the sensed temperature), random (e.g., to even out the load from reporting from severalsensors), in response to a triggering event (e.g., when moisture is detected, an alert is sent), in response to a request (e.g., a user initiated request), or a continuous stream (e.g., a live video feed of a patient). As another example, a UE comprises an actuator, a motor, or a switch related to a communication interface configured to receive wireless input from a network node via a wireless connection. In response to the received wireless input the states of the actuator, the motor, or the switch may change. For example, the UE may comprise a motor that adjusts the control surfaces or rotors of a drone in flight according to the received input or to a robotic arm performing a medical procedure according to the received input. A UE, when in the form of an IoT device, may be a device for use in one or more application domains, these domains comprising, but not limited to, city wearable technology, extended industrial application, and healthcare. Non-limiting examples of such an IoT device are a device which is or which is embedded in: a connected refrigerator or freezer, a television, a connected lighting device, an electricity meter, a robot vacuum cleaner, a voice controlled smart speaker, a home security camera, a motion detector, a thermostat, a smoke detector, a door / window sensor, a flood / moisture sensor, an electrical door lock, a connected doorbell, an air conditioning system like a heat pump, an autonomous vehicle, a surveillance system, a weather monitoring device, a vehicle parking monitoring device, an electric vehicle charging station, a smart watch, a fitness tracker, a head-mounted display for Augmented Reality (AR) orVR, a wearable for tactile augmentation or sensory enhancement, a water sprinkler, an animal- oritem-tracking device, a sensor for monitoring a plant or animal, an industrial robot, an Unmanned Aerial Vehicle (UAV), and any kind of medical device, like a heart rate monitor or a remote controlled surgical robot. A UE in the form of an IoT device comprises circuitry and / or software in dependence of the intended application of the IoT device in addition to other components as described in relation to the UE 800 shown in Figure 8. As yet another specific example, in an IoT scenario, a UE may represent a machine or other device that performs monitoring and / or measurements and transmits the results of such monitoring and / or measurements to another UE and / or a network node. The UE may in this case be an M2M device, which may in a 3GPP context be referred to as an MTC device. As one particular example, the UE may implement the 3GPP NB-IoT standard. In other scenarios, a UE may represent a vehicle, such as a car, a bus, a truck, a ship, an airplane, or other equipment that is capable of monitoring and / or reporting on its operational status or other functions associated with its operation. In practice, any number of UEs may be used together with respect to a single use case. For example, a first UE might be or be integrated in a drone and provide the drone’s speed information (obtained through a speed sensor) to a second UE that is a remote controller operating the drone. When the user makes changes from the remote controller, the first UE may adjust the throttle on the drone (e.g., by controlling an actuator) to increase or decrease the drone’s speed. The first and / or the second UE can also include more than one of the functionalities described above. For example, a UE might comprise the sensor and the actuator and handle communication of data for both the speed sensor and the actuators. Figure 9 shows a network node 900 in accordance with some embodiments. As usedherein, network node refers to equipment capable, configured, arranged, and / or operable to communicate directly or indirectly with a UE and / or with other network nodes or equipment in a telecommunication network. Examples of network nodes include, but are not limited to, APs (e.g., radio APs), Base Stations (BSs) (e.g., radio BSs, Node Bs, evolved Node Bs (eNBs), NR Node Bs (gNBs)), and O-RAN nodes or components of an O-RAN node (e.g., O-RU, O-DU, O- CU). Base stations may be categorized based on the amount of coverage they provide (or, stated differently, their transmit power level) and so, depending on the provided amount of coverage, may be referred to as femto base stations, pico base stations, micro base stations, or macro base stations. A base station may be a relay node or a relay donor node controlling arelay. A network node may also include one or more (or all) parts of a distributed radio basestation such as centralized digital units, distributed units (e.g., in an O-RAN access node), and / or Remote Radio Units (RRUs), sometimes referred to as Remote Radio Heads (RRHs). Such RRUs may or may not be integrated with an antenna as an antenna integrated radio. Parts of a distributed radio base station may also be referred to as nodes in a Distributed Antenna System (DAS). Other examples of network nodes include multiple Transmission Point (multi-TRP) 5G access nodes, Multi-Standard Radio (MSR) equipment such as MSR BSs, network controllers such as Radio Network Controllers (RNCs) or BS Controllers (BSCs), Base Transceiver Stations (BTSs), transmission points, transmission nodes, Multi-Cell / Multicast Coordination Entities (MCEs), Operation and Maintenance (O&M) nodes, Operations Support System (OSS) nodes, Self-Organizing Network (SON) nodes, positioning nodes (e.g., Evolved Serving Mobile Location Centers (E-SMLCs)), and / or Minimization of Drive Tests (MDTs). The network node 900 includes processing circuitry 902, memory 904, a communication interface 906, and a power source 908. The network node 900 may be composed of multiple physically separate components (e.g., a NodeB component and an RNC component, or a BTS component and a BSC component, etc.), which may each have their own respective components. In certain scenarios in which the network node 900 comprises multiple separate components (e.g., BTS and BSC components), one or more of the separate components may be shared among several network nodes. For example, a single RNC may control multiple NodeBs. In such a scenario, each unique NodeB and RNC pair may in some instances be considered a single separate network node. In some embodiments, the network node 900 may be configured to support multiple RATs. In such embodiments, some components may be duplicated (e.g., separate memory 904 for different RATs) and some components may be reused (e.g., a same antenna 910 may be shared by different RATs). The network node 900 may also include multiple sets of the various illustrated components for different wireless technologies integrated into network node 900, for example GSM, WCDMA, LTE, NR, WiFi, Zigbee, Z-wave, Long Range Wide Area Network (LoRaWAN), Radio Frequency Identification (RFID), or Bluetooth wireless technologies. These wireless technologies may be integrated into the same or different chip or set of chips and other components within the network node 900. The processing circuitry 902 may comprise a combination of one or more of a microprocessor, controller, microcontroller, CPU, DSP, ASIC, FPGA, or any other suitable computing device, resource, or combination of hardware, software, and / or encoded logic operable to provide, either alone or in conjunction with other network node 900 components, such as the memory 904, to provide network node 900 functionality. In some embodiments, the processing circuitry 902 includes a System on a Chip (SOC). In some embodiments, the processing circuitry 902 includes one or more of Radio Frequency (RF) transceiver circuitry 912 and baseband processing circuitry 914. In some embodiments, the RF transceiver circuitry 912 and the baseband processing circuitry 914 may be on separate chips (or sets of chips), boards, or units, such as radio units and digital units. In alternative embodiments, part or all of the RF transceiver circuitry 912 and the baseband processing circuitry 914 may be on the same chip or set of chips, boards, or units. The memory 904 may comprise any form of volatile or non-volatile computer-readable memory including, without limitation, persistent storage, solid state memory, remotely mounted memory, magnetic media, optical media, RAM, ROM, mass storage media (for example, a hard disk), removable storage media (for example, a flash drive, a Compact Disk (CD), or a Digital Video Disk (DVD)), and / or any other volatile or non-volatile, non-transitory device-readable, and / or computer-executable memory devices that store information, data, and / or instructions that may be used by the processing circuitry 902. The memory 904 may store any suitable instructions, data, or information, including a computer program, software, an application including one or more of logic, rules, code, tables, and / or other instructions capable of being executed by the processing circuitry 902 and utilized by the network node 900. The memory 904 may be used to store any calculations made by the processing circuitry 902 and / or any data received via the communication interface 906. In some embodiments, the processing circuitry 902 and the memory 904 are integrated. The communication interface 906 is used in wired or wireless communication of signaling and / or data between a network node, access network, and / or UE. As illustrated, the communication interface 906 comprises port(s) / terminal(s) 916 to send and receive data, for example to and from a network over a wired connection. The communication interface 906 also includes radio front-end circuitry 918 that may be coupled to, or in certain embodiments a part of, the antenna 910. The radio front-end circuitry 918 comprises filters 920 and amplifiers 922. The radio front-end circuitry 918 may be connected to the antenna 910 and the processing circuitry 902. The radio front-end circuitry 918 may be configured to condition signals communicated between the antenna 910 and the processing circuitry 902. The radio front-end circuitry 918 may receive digital data that is to be sent out to other network nodes or UEs via a wireless connection. The radio front-end circuitry 918 may convert the digital data into a radio signal having the appropriate channel and bandwidth parameters using a combination of the filters 920 and / or the amplifiers 922. The radio signal may then be transmitted via the antenna 910. Similarly, when receiving data, the antenna 910 may collect radio signals which are then converted into digital data by the radio front-end circuitry 918. The digital data may be passed to the processing circuitry 902. In other embodiments, the communication interface 906 may comprise different components and / or different combinations of components. In certain alternative embodiments, the network node 900 does not include separate radio front-end circuitry 918; instead, the processing circuitry 902 includes radio front-end circuitry and is connected to the antenna 910. Similarly, in some embodiments, all or some of the RF transceiver circuitry 912 is part of the communication interface 906. In still other embodiments, the communication interface 906 includes the one or more ports or terminals 916, the radio front- end circuitry 918, and the RF transceiver circuitry 912 as part of a radio unit (not shown), and the communication interface 906 communicates with the baseband processing circuitry 914, which is part of a digital unit (not shown). The antenna 910 may include one or more antennas, or antenna arrays, configured to send and / or receive wireless signals. The antenna 910 may be coupled to the radio front-end circuitry 918 and may be any type of antenna capable of transmitting and receiving data and / or signals wirelessly. In certain embodiments, the antenna 910 is separate from the network node 900 and connectable to the network node 900 through an interface or port. The antenna 910, the communication interface 906, and / or the processing circuitry 902 may be configured to perform any receiving operations and / or certain obtaining operations described herein as being performed by the network node 900. Any information, data, and / or signals may be received from a UE, another network node, and / or any other network equipment. Similarly, the antenna 910, the communication interface 906, and / or the processing circuitry 902 may be configured to perform any transmitting operations described herein as being performed by the network node 900. Any information, data, and / or signals may be transmitted to a UE, another network node, and / or any other network equipment. The power source 908 provides power to the various components of the network node 900 in a form suitable for the respective components (e.g., at a voltage and current level needed for each respective component). The power source 908 may further comprise, or be coupled to, power management circuitry to supply the components of the network node 900 with power for performing the functionality described herein. For example, the network node 900 may be connectable to an external power source (e.g., the power grid or an electricity outlet) via input circuitry or an interface such as an electrical cable, whereby the external power source supplies power to power circuitry of the power source 908. As a further example, the power source 908 may comprise a source of power in the form of a battery or battery pack which is connected to, or integrated in, power circuitry. The battery may provide backup power should the external power source fail. Embodiments of the network node 900 may include additional components beyond thoseshown in Figure 9 for providing certain aspects of the network node’s functionality, includingany of the functionality described herein and / or any functionality necessary to support the subject matter described herein. For example, the network node 900 may include user interface equipment to allow input of information into the network node 900 and to allow output of information from the network node 900. This may allow a user to perform diagnostic, maintenance, repair, and other administrative functions for the network node 900. In someembodiments providing a core network node, such as core network node 708 of Figure 7, somecomponents, such as the radio front-end circuitry 918 and the RF transceiver circuitry 912 may be omitted. Figure 10 is a block diagram illustrating a virtualization environment 1000 in whichfunctions implemented by some embodiments may be virtualized. In the present context, virtualizing means creating virtual versions of apparatuses or devices which may include virtualizing hardware platforms, storage devices, and networking resources. As used herein, virtualization can be applied to any device described herein, or components thereof, and relates to an implementation in which at least a portion of the functionality is implemented as one or more virtual components. Some or all of the functions described herein may be implemented as virtual components executed by one or more Virtual Machines (VMs) implemented in one or more virtualization environments 1000 hosted by one or more of hardware nodes, such as a hardware computing device that operates as a network node, a UE, a core network node, or a host. Further, in embodiments in which the virtual node does not require radio connectivity (e.g., a core network node or host), then the node may be entirely virtualized. In some embodiments, the virtualization environment 1000 includes components defined by the O-RAN Alliance, such as an O-Cloud environment orchestrated by a Service Management and Orchestration Framework via an O-2 interface. Virtualization may facilitate distributed implementations of a network node, a UE, a core network node, or a host. Applications 1002 (which may alternatively be called software instances, virtual appliances, network functions, virtual nodes, virtual network functions, etc.) are run in the virtualization environment 1000 to implement some of the features, functions, and / or benefits of some of the embodiments disclosed herein. Hardware 1004 includes processing circuitry, memory that stores software and / or instructions executable by hardware processing circuitry, and / or other hardware devices as described herein, such as a network interface, an input / output interface, and so forth. Software may be executed by the processing circuitry to instantiate one or more virtualization layers 1006 (also referred to as hypervisors or Virtual Machine Monitors (VMMs)), provide VMs 1008A and 1008B (one or more of which may be generally referred to as VMs 1008), and / or perform any of the functions, features, and / or benefits described in relation with some embodiments described herein. The virtualization layer 1006 may present a virtual operating platform that appears like networking hardware to the VMs 1008. The VMs 1008 comprise virtual processing, virtual memory, virtual networking, or interface and virtual storage, and may be run by a corresponding virtualization layer 1006. Different embodiments of the instance of a virtual appliance 1002 may be implemented on one or more of VMs 1008, and the implementations may be made in different ways. Virtualization of the hardware is in some contexts referred to as Network Function Virtualization (NFV). NFV may be used to consolidate many network equipment types onto industry standard high volume server hardware, physical switches, and physical storage, which can be located in data centers and customer premise equipment. In the context of NFV, a VM 1008 may be a software implementation of a physical machine that runs programs as if they were executing on a physical, non-virtualized machine. Each of the VMs 1008, and that part of the hardware 1004 that executes that VM, be it hardware dedicated to that VM and / or hardware shared by that VM with others of the VMs, forms separate virtual network elements. Still in the context of NFV, a virtual network function is responsible for handling specific network functions that run in one or more VMs 1008 on top of the hardware 1004 and corresponds to the application 1002. The hardware 1004 may be implemented in a standalone network node with generic or specific components. The hardware 1004 may implement some functions via virtualization. Alternatively, the hardware 1004 may be part of a larger cluster of hardware (e.g., such as in a data center or CPE) where many hardware nodes work together and are managed via management and orchestration 1010, which, among others, oversees lifecycle management of the applications 1002. In some embodiments, the hardware 1004 is coupled to one or more radio units that each include one or more transmitters and one or more receivers that may be coupled to one or more antennas. Radio units may communicate directly with other hardware nodes via one or more appropriate network interfaces and may be used in combination with the virtual components to provide a virtual node with radio capabilities, such as a radio access node or a base station. In some embodiments, some signaling can be provided with the use of a control system 1012 which may alternatively be used for communication between hardware nodes and radio units. Although the computing devices described herein (e.g., UEs, network nodes) may include the illustrated combination of hardware components, other embodiments may comprise computing devices with different combinations of components. It is to be understood that these computing devices may comprise any suitable combination of hardware and / or software needed to perform the tasks, features, functions, and methods disclosed herein. Determining, calculating, obtaining, or similar operations described herein may be performed by processing circuitry, which may process information by, for example, converting the obtained information into other information, comparing the obtained information or converted information to information stored in the network node, and / or performing one or more operations based on the obtained information or converted information, and as a result of said processing making a determination. Moreover, while components are depicted as single boxes located within a larger box, or nested within multiple boxes, in practice, computing devices may comprise multiple different physical components that make up a single illustrated component, and functionality may be partitioned between separate components. For example, a communication interface maybe configured to include any of the components described herein, and / or the functionality of thecomponents may be partitioned between the processing circuitry and the communication interface. In another example, non-computationally intensive functions of any of such components may be implemented in software or firmware and computationally intensive functions may be implemented in hardware. In certain embodiments, some or all of the functionality described herein may be provided by processing circuitry executing instructions stored on in memory, which in certain embodiments may be a computer program product in the form of a non-transitory computer- readable storage medium. In alternative embodiments, some or all of the functionality may be provided by the processing circuitry without executing instructions stored on a separate or discrete device-readable storage medium, such as in a hard-wired manner. In any of those particular embodiments, whether executing instructions stored on a non-transitory computer- readable storage medium or not, the processing circuitry can be configured to perform the described functionality. The benefits provided by such functionality are not limited to the processing circuitry alone or to other components of the computing device, but are enjoyed by the computing device as a whole, and / or by end users and a wireless network generally. Those skilled in the art will recognize improvements and modifications to the embodiments of the present disclosure. All such improvements and modifications are considered within the scope of the concepts disclosed herein. EMBODIMENTS Group A Embodiments Embodiment 1: A method performed by a user equipment for data collection for training of one or more Artificial Intelligence, AI, / Machine Learning, ML, models or functionalities, themethod comprising: receiving (600), from a network node, first information that indicates a firstset of measurement resources; selecting (602) one or more second sets of recommendedmeasurement resources in which the UE is to perform radio measurements and / or one or morethird sets of measurement resources for prediction in which, once trained, one or more AI / MLmodels or functions available at the UE are to provide radio measurement predictions, uponperforming radio measurements in one or more second sets of measurement resources. Embodiment 2: The method of embodiment 1, wherein the one or more AI / ML models orfunctions comprise one or more AI / ML models that are part of an AI / ML functionality availableat the UE or at a node performing UE-side model training of the one or more AI / ML models forthe UE, that corresponds to radio measurement predictions. Embodiment 3: The method of embodiment 1, wherein receiving the first informationthat indicates the one or more first sets of measurement resources comprises receiving the first information that indicates the one or more first sets of measurement resources as part of a configuration for data collection for UE-side model training. Embodiment 4: The method of embodiment 1, wherein receiving the first information that indicates the one or more first sets of measurement resources comprises receiving the first information that indicates the one or more first sets of measurement resources as part of a measurement configuration for performing and reporting of the radio measurements. Embodiment 5: The method of embodiment 1, wherein receiving the first informationthat indicates the one or more first sets of measurement resources comprises receiving the first information that indicates the one or more first sets of measurement resources as part of a measurement configuration indicating a set of candidate measurement resources that can be configured by the network node to the UE to perform data collection for UE-side AI / ML model training. Embodiment 6: The method of embodiment 1, wherein selecting the one or more secondrecommended sets of measurement resources and / or the one or more third sets of measurementresources comprises selecting the one or more second recommended sets of measurement resources and the one or more third sets of measurement resources from resources included in the one or more first sets of measurement resources. Embodiment 7: The method of embodiment 1, wherein selecting the one or more secondrecommended sets of measurement resources and / or the one or more third sets of measurementresources is performed before training the one or more AI / ML models or functionalities.Embodiment 8: The method of embodiment 7, wherein selecting the one or more secondrecommended sets of measurement resources and / or the one or more third sets of measurementresources is performed upon fulfilling any one or more of the following conditions: receiving arequest from the network node or from a training entity performing UE-side AI / ML modeltraining, wherein the request is to start data collection for UE-side model training, receiving arequest to indicate applicability of the one or more AI / ML models or functionalities available atthe UE, receiving a request in response to the UE indicating capability to support the one ormore AI / ML models or functionalities, receiving a request in response to UE indicatingcapability to collect data for AI / ML training, upon determining that radio measurements for datacollection for training of the one or more AI / ML models or functionalities has not beenpreviously performed on at least part of the radio resources indicated in the one or more first setsof measurement resources, upon determining that radio measurements for data collection fortraining of the one or more AI / ML models or functionalities has not been previously performedfor the network node transmitting the first information that indicates the one or more first sets ofmeasurement resources, upon determining that radio measurements for data collection fortraining of the one or more AI / ML models or functionalities has not been previously performedin a geographic area in which the UE is located at the moment of performing the selecting, upondetermining that radio measurements for data collection for training of AIML model / functionality has not been performed since a certain amount of time in the area in which the UE is located or in the network node to which the UE is connected at the moment of doing the selection. Embodiment 9: The method of embodiment 1, wherein each of the one or more first setsof measurement resources is associated to an identifier, ID.Embodiment 10: The method of embodiment 1, wherein each of the one or more first setsof measurement resources is associated to a set ID Embodiment 11: The method of embodiment 1, wherein each of one or more resourcescomprised in the one or more first sets of measurement resources is associated to a resource ID. Embodiment 12: The method of embodiment 10, wherein the set ID for one of the one ormore first sets of measurement resources is unique within the cell. Embodiment 13: The method of embodiment 11, wherein the resource ID for oneresource within the one or more first sets of measurement resources is unique within the cell. Embodiment 14: The method of embodiment 1, further comprising transmitting (602a) tothe network node a first indication comprising: information that indicates the selected one ormore second sets of recommended measurement resources; and / or information that indicates theselected one or more third sets of measurement resources for predictions. Embodiment 15: The method of embodiment 14, wherein for each of the selected one ormore second sets of recommended measurement resources and each of the selected one or more third sets of measurement resources indicated by the information comprised in the first indication, the UE includes an associated set ID. Embodiment 16: The method of embodiment 14, wherein for each of the selected one ormore second sets of recommended measurement resources and each of the selected one or more third sets of measurement resources indicated by the information comprised in the first indication, the UE includes one or more resource IDs associated to resources within that set of measurement resources. Embodiment 17: The method of embodiment 14, further comprising, in response totransmitting the first indication, receiving (604) (e.g., from the network node) a secondindication comprising: information that indicates a second set of measurement resources onwhich the UE is to perform radio measurements for data collection for the AI / ML model(s) in order to determine radio measurement predictions in the third set(s) of measurement resources;and information that indicates a third set of measurement resources in which the trained AI / MLmodel(s) is to provide radio measurement predictions upon performing the radio measurementsbased on the second set of measurement resources. Embodiment 18: The method of embodiment 17, wherein the second set of measurementresources is equal to or a subset of the one or more second sets of recommended measurement resources. Embodiment 19: The method of embodiment 17, wherein the third set of measurementresources indicated by the information comprised in the second indication received by the UE from the network node is equal to or a subset of the one or more third sets of measurement resources indicated by the information comprised in the first indication transmitted by the UE to the network node. Embodiment 20: The method of embodiment 17, wherein the second indication isreceived by the UE as part of a configuration for performing radio measurements. Embodiment 21: The method of embodiment 17, wherein the second indication isreceived by the UE as part of a configuration for data collection for UE-side model training. Embodiment 22: The method of embodiment 17, further comprising, upon receiving thesecond indication, transmitting (e.g., to the network node) a request for radio transmissions required for performing the radio measurements on the resources included in the second and third sets of measurement resources indicated by the information comprised in the second indication. Embodiment 23: The method of embodiment 22, wherein the request comprises anassociated set ID for the second set of measurement resources and an associated set ID for the third set of measurement resources. Embodiment 24: The method of embodiment 17, further comprising, upon receiving thesecond indication, starting (608) to perform the radio measurement on the resources included in the second and third sets of measurement resources. Embodiment 25: The method of embodiment 1 or 14, further comprising, upon selectingthe one or more second sets of recommended measurement resources and the one more third sets of measurement resources for prediction (and optionally transmitting the first indication to the network node), starting (608) to perform the radio measurements on the resources included in the one or more second sets of recommended measurement resources and the one or more third sets of measurement resources for prediction.Embodiment 26: The method of embodiment 24 or 25, further comprising sending theradio measurements and an associated set ID and / or resource ID of the radio resource for which data collection was performed to a training entity performing UE-side model training of the one or more AI / ML models / functionalities. Embodiment 27: The method of any of embodiments 24, 25, 26, wherein the UE or thetraining entity performing the UE-side model training logs / stores the associated set ID or resource ID for measurement resources used for performing the measurement. Embodiment 28: The method of embodiment 26, wherein the collected measurements areused to train an AI / ML model at the training entity. Embodiment 29: The method of embodiment 27, wherein the logged set ID or resourceID is used by the UE or by the training entity to determine the radio measurement resources for which the data collection for training has been performed for the network node that configured the UE with the one or more first sets of measurement resources. Embodiment 30: The method of embodiment 24 or 25, wherein the collectedmeasurements are not reported to the network node. Embodiment 31: The method of embodiment 14, wherein the first indication istransmitted from the UE to the network node in response of any of: upon decision toretrain / finetune an existing model, wherein the decision is triggered by the network (e.g., by thenetwork node) or initiated by the UE, or triggered by the training entity performing UE-sidemodel training of the one or more AI / ML models or functions, upon receiving a reconfigurationof the first set of measurement resources, upon change in network or additional conditions (e.g.,a change in an antenna configuration or antenna pattern of the network node), a new model is tobe trained by the UE, one or more of the existing AI / ML models or functions at the UE are notfulfilling associated performance requirements, being configured by the network node to performAIML-based radio measurement prediction, upon receiving an activation request for the one ormore AI / ML models or functionalities from the network node.Embodiment 32: The method of embodiment 14, further comprising, in response totransmitting the first indication, receiving (604) a third indication indicating that the one or more second sets of recommended measurement resources and / or the one or more third sets of measurement resources are rejected. Embodiment 33: The method of embodiment 32, wherein in response to receiving thethird indication, the UE does not proceed with the AI / ML model training based on the selected second and third measurement resources.Embodiment 34: The method of embodiment 14, wherein one or more applicabilityconditions of the one or more AIML models or functionalities available at the UE are checked bythe UE prior to transmitting the first indication. Embodiment 35: The method of embodiment 1, wherein each of the one or more first setsof measurement resources comprise any of: a set of SSB for a cell; a set of CSI-RS resources fora cell; a set of SS / PBCH block resource set for a cell; a set of cells; a set of frequencies; a set of SSB for a list of cells; a set of CSI-RS resources for a list of cells; a set of SS / PBCH block resource set for a list of cells. Embodiment 36: The method of embodiment 24 or 25, wherein an output of the trainedone or more AI / ML models / functionalities at the UE is radio measurement predictions on the third set of measurement resources comprising prediction results for one or more measurement quantities, such as the RSRP, RSRQ, SINR, RSSI level, associated to the second set of measurement resources. Embodiment 37: The method of embodiment 36, wherein the radio measurementprediction results comprise any of: the measured quantities for each of the one or more resourcesin the third set of measurement resources the measured quantities for the best resources in termsof measured quantities among the resources in the second and / or third set of measurementresources, wherein the number of best resources can be a fixed or configured number themeasured quantities for the worst resources in terms of measured quantities among the resources in the second and / or third set of measurement resources, wherein the number of worst resourcescan be a fixed or configured number the average measured quantities for the resources in thesecond and / or third set of measurement resources the variance of the measured quantities for theresources in the second and / or third set of measurement resources the accuracy of the reportedpredictions results. Embodiment 38: The method of embodiment 37, wherein the radio measurementprediction results can further include: a time instance when the prediction results are valid, forexample indicated in an absolute UTC time, or in a NR time-unit in respect to when the secondset of measurement resources are measured. For example, a time-index relative to when the firstmeasurement of the second set of measurement resources are performed. For example, a time-index relative to when the last measurement of the second set of measurement resources areperformed a time-window for how long the radio measurement prediction results are valid, forexample a certain number of NR-time units from the NW receives the radio measurement prediction results. Or in respect to the time-instance in bullet above; a time stamp indicating the point in time (indicated in an absolute UTC time, or in a NR time-unit) in which the data collection for the training purposes started or stopped; a time stamp indicating the point in time (indicated in an absolute UTC time, or in a NR time-unit) in which a radio measurement prediction was performed; the location indicating the point in time (indicated in an absolute UTC time, or in a NR time-unit) in which the data collection for the training purposes started or stopped; the location indicating the point in time (indicated in an absolute UTC time, or in a NR time-unit) in which a radio measurement prediction was performed. Embodiment 39: The method of embodiment 1, wherein receiving the first informationthat indicates the one or more first sets of measurement resources comprises receiving the firstinformation via dedicated signaling (e.g., RRC signaling dedicated to the UE) or broadcastsignaling (e.g., SIB). Embodiment 40: The method of embodiment 14, wherein the first indication istransmitted via RRC signaling (UEAssistanceInformation), or MAC (MAC CE), or UCI. Embodiment 41: The method of embodiment 17 or 34, wherein the second and / or thirdindication is received via RRC dedicated signaling or MAC (MAC CE), PDCCH. Embodiment 42: The method of embodiment 34, the UE indicates availability of the oneor more AL / ML models or functionalities that are applicable to conditions comprising trainingbased on the second and third set for measurements resources. Embodiment 43: The method of any of embodiments 1 to 42, wherein a training entityfor training the one or more AI / ML models or functionalities is a function located in a RANnetwork node, gNB, or core network node, or OTT server, or UE. Embodiment 44: The method of embodiment 43, wherein if the training entity is afunction located in the UE, the data collected are transmitted from the UE lower layers to the said training entity within the UE. Group B Embodiments Embodiment 45: A method performed by a network node (e.g., a RAN node such, e.g., agNB), the method comprises: transmitting (600), to a UE (e.g., via dedicated or broadcastsignaling) information indicative of one or more first sets of measurement resources. Embodiment 46: The method of embodiment 45, further comprising receiving (602a),from the UE, a first indication comprising any of: information that indicates one or more secondsets of recommended measurement resources (set B) in which the UE is to perform radiomeasurements; and information that indicates the selected one or more third sets of measurementresources for prediction (set A) in which one or more trained AI / ML models / functionalities available at the UE are to provide radio measurement predictions.Embodiment 47: The method of embodiment 46, further comprising determining (604)(a) a second set of measurement resources on which the UE is to perform radio measurements fordata collection for the one or more AI / ML models or functionalities in order to determine radiomeasurement predictions in a third set of measurement resources and (b) the third set ofmeasurement resources, based on the one or more second sets of recommended measurementresources and the one or more third sets of measurement resources for prediction indicated by the information comprised in the first indication. Embodiment 48: A method of embodiment 47, further comprising transmitting (604) asecond indication to the UE, the second indication comprising information that indicates thedetermined second set of measurement resources and information that indicates the determinedthird set of measurement resources. Embodiment 49: The method of embodiment 48, further comprising transmitting (606)reference signals associated to resources included in the determined second and third sets of measurement resources (e.g., for the UE to perform radio measurements). Embodiment 50: The method of embodiment 45, further comprising transmitting reference signals associated to resources included in the one or more first sets of measurement resources (e.g., for the UE to perform radio measurements). Group C Embodiments Embodiment 51: A user equipment comprising: processing circuitry configured toperform any of the steps of any of the Group A embodiments; and power supply circuitryconfigured to supply power to the processing circuitry. Embodiment 52: A network node comprising: processing circuitry configured to performany of the steps of any of the Group B embodiments; power supply circuitry configured tosupply power to the processing circuitry. Embodiment 53: A user equipment (UE) comprising: an antenna configured to send andreceive wireless signals; radio front-end circuitry connected to the antenna and to processingcircuitry, and configured to condition signals communicated between the antenna and theprocessing circuitry; the processing circuitry being configured to perform any of the steps of anyof the Group A embodiments; an input interface connected to the processing circuitry andconfigured to allow input of information into the UE to be processed by the processing circuitry; an output interface connected to the processing circuitry and configured to output informationfrom the UE that has been processed by the processing circuitry; and a battery connected to theprocessing circuitry and configured to supply power to the UE.

Claims

CLAIMS1. A method performed by a User Equipment, UE, for data collection for training of one ormore Artificial Intelligence, AI, / Machine Learning, ML, models or functionalities, the method comprising: receiving (600), from a network node, first information that indicates a first set of measurement resources; and based on the first set of measurement resources, selecting (602) one or more second sets of recommended measurement resources in which the UE is to perform radio measurements and / or one or more third sets of measurement resources for prediction in which, once trained, one or moreAI / ML models or functions available at the UE are to provide radio measurement predictions,upon performing radio measurements in one or more second sets of measurement resources.

2. The method of claim 1, wherein the one or more AI / ML models or functions comprise oneor more AI / ML models that are part of an AI / ML functionality available at the UE or at a nodeperforming UE-side model training of the one or more AI / ML models for the UE, that corresponds to radio measurement predictions.

3. The method of claim 1, wherein receiving the first information that indicates the one ormore first sets of measurement resources comprises receiving the first information that indicates the one or more first sets of measurement resources as part of a configuration for data collection for UE-side model training.

4. The method of claim 1, wherein receiving the first information that indicates the one ormore first sets of measurement resources comprises receiving the first information that indicates the one or more first sets of measurement resources as part of a measurement configuration for performing and reporting of the radio measurements.

5. The method of claim 1, wherein receiving the first information that indicates the one ormore first sets of measurement resources comprises receiving the first information that indicates the one or more first sets of measurement resources as part of a measurement configurationindicating a set of candidate measurement resources that can be configured by the network nodeto the UE to perform data collection for UE-side AI / ML model training.

6. The method of any of claims 1 to 5, wherein selecting the one or more secondrecommended sets of measurement resources and / or the one or more third sets of measurementresources comprises selecting the one or more second recommended sets of measurementresources and the one or more third sets of measurement resources from resources included in theone or more first sets of measurement resources.

7. The method of any of claims 1 to 6, wherein selecting the one or more secondrecommended sets of measurement resources and / or the one or more third sets of measurement resources is performed before training the one or more AI / ML models or functionalities.

8. The method of claim 7, wherein selecting the one or more second recommended sets ofmeasurement resources and / or the one or more third sets of measurement resources is performed upon fulfilling any one or more of the following conditions: receiving a request from the network node or from a training entity performing UE-side AI / ML model training, wherein the request is to start data collection for UE-side model training, receiving a request to indicate applicability of the one or more AI / ML models or functionalities available at the UE, receiving a request in response to the UE indicating capability to support the one or more AI / ML models or functionalities, receiving a request in response to UE indicating capability to collect data for AI / ML training.

9. The method of claim 7, wherein selecting the one or more second recommended sets ofmeasurement resources and / or the one or more third sets of measurement resources is performed upon fulfilling any one or more of the following conditions: upon determining that radio measurements for data collection for training of the one or more AI / ML models or functionalities has not been previously performed on at least part of the radio resources indicated in the one or more first sets of measurement resources, upon determining that radio measurements for data collection for training of the one or more AI / ML models or functionalities have not been previously performed for the network node transmitting the first information that indicates the one or more first sets of measurement resources, upon determining that radio measurements for data collection for training of the one or more AI / ML models or functionalities have not been previously performed in a geographic area in which the UE is located at the moment of performing the selecting, upon determining that radio measurements for data collection for training of AIMLmodel / functionality have not been performed since a certain amount of time in the area in which the UE is located or in the network node to which the UE is connected at the moment of doing the selection.

10. The method of any of claims 1 to 9, further comprising transmitting (602a) to the networknode a first indication comprising: information that indicates the selected one or more second sets of recommended measurement resources; and / or information that indicates the selected one or more third sets of measurement resources for predictions.

11. The method of claim 10, wherein the first indication is transmitted via Radio ResourceControl, RRC, signaling or Medium Access Control, MAC, Control Element, CE, or Uplink Control Information, UCI.

12. The method of claim 10 or 11, wherein for each of the selected one or more second sets ofrecommended measurement resources and each of the selected one or more third sets of measurement resources indicated by the information comprised in the first indication, the UE includes an associated set ID.

13. The method of claim 10 or 11, wherein for each of the selected one or more second sets ofrecommended measurement resources and each of the selected one or more third sets of measurement resources indicated by the information comprised in the first indication, the UE includes one or more resource IDs associated to resources within that set of measurement resources.

14. The method of any of claims 10 to 13, wherein the first indication is transmitted from theUE to the network node in response of any of: upon decision to retrain or finetune an existing model, wherein the decision is network-triggered, upon receiving a reconfiguration of the first set of measurement resources, being configured by the network node to perform AIML-based radio measurement prediction,upon receiving an activation request for the one or more AI / ML models or functionalities from the network node.

15. The method of any of claims 10 to 13, wherein the first indication is transmitted from theUE to the network node in response of any of: upon decision to retrain or finetune an existing model, wherein the decision is initiated by the UE or triggered by a training entity performing UE-side model training of the one or more AI / ML models or functions, upon change in network or additional conditions, a new model is to be trained by the UE, one or more of the existing AI / ML models or functions at the UE are not fulfilling associated performance requirements,16. The method of any of claims 10 to 15, further comprising, in response to transmitting thefirst indication, receiving (604), from the network node, a second indication comprising:information that indicates a second set of measurement resources on which the UE is to perform radio measurements for data collection for the AI / ML model(s) in order to determine radio measurement predictions in the third set(s) of measurement resources; and information that indicates a third set of measurement resources in which the trained AI / MLmodel(s) is to provide radio measurement predictions upon performing the radio measurementsbased on the second set of measurement resources.

17. The method of claim 16, wherein the second set of measurement resources is equal to or asubset of the one or more second sets of recommended measurement resources.

18. The method of claim 16 or 17, wherein the third set of measurement resources indicated bythe information comprised in the second indication received by the UE from the network node is equal to or a subset of the one or more third sets of measurement resources indicated by the information comprised in the first indication transmitted by the UE to the network node.

19. The method of any of claims 1 to 13, further comprising, upon selecting the one or moresecond sets of recommended measurement resources and the one more third sets of measurement resources for prediction, starting (608) to perform the radio measurements on the resourcesincluded in the one or more second sets of recommended measurement resources and the one or more third sets of measurement resources for prediction.

20. The method of claim 1 or 19, further comprising sending the radio measurements and anassociated set ID and / or resource ID of the radio resource for which data collection was performed to a training entity performing UE-side model training of the one or more AI / ML models / functionalities.

21. The method of claim 20, wherein the collected measurements are used to train an AI / MLmodel at the training entity.

22. The method of any of claims 1 to 20, wherein the UE or the training entity performing UE-side model training stores the associated set ID or resource ID for measurement resources used for performing the measurement.

23. The method of claim 22, wherein the stored set ID or resource ID is used by the UE or bythe training entity to determine the radio measurement resources for which the data collection for training has been performed for the network node that configured the UE with the one or more first sets of measurement resources.

24. The method of any of claims 10 to 14, further comprising, in response to transmitting thefirst indication, receiving (604) a third indication indicating that the one or more second sets of recommended measurement resources and / or the one or more third sets of measurement resources are rejected.

25. The method of any of claims 10 to 14, wherein one or more applicability conditions of theone or more AI / ML models or functionalities available at the UE are checked by the UE prior to transmitting the first indication.

26. The method of any of claims 1 to 25, wherein receiving the first information that indicatesthe one or more first sets of measurement resources comprises receiving the first information via dedicated signaling or broadcast signaling.

27. The method of any of claims 1 to 26, wherein a training entity for training the one or moreAI / ML models or functionalities is a function located in the UE, and data collected istransmitted from one or more lower layers of the UE to the training entity within the UE.

28. A User Equipment, UE, (800) for data collection for training of one or more ArtificialIntelligence, AI, / Machine Learning, ML, models or functionalities, the UE (800) comprising: a communication interface (812) comprising a transmitter (818) and a receiver (820); and processing circuitry (802) associated with the communication interface (812), the processing circuitry (802) configured to cause the UE (800) to: receive (600), from a network node, first information that indicates a first set of measurement resources; and based on the first set of measurement resources, select (602) one or more second sets of recommended measurement resources in which the UE is to perform radio measurements and / or one or more third sets of measurement resources for prediction in which, once trained, one or more AI / ML models or functions available at the UE are to provide radio measurement predictions, upon performing radio measurements in one or more second sets of measurement resources.

29. The UE of claim 28, wherein the processing circuitry (802) is further configured to causethe UE (800) to perform the method of any of claims 2 to 27.

30. A method performed by a network node, the method comprises:transmitting (600) to a User Equipment, UE, information indicative of one or more firstsets of measurement resources;receiving (602a), from the UE, a first indication comprising any of:information that indicates one or more second sets of recommended measurement resources in which the UE is to perform radio measurements; and information that indicates one or more third sets of measurement resources forprediction in which one or more trained Artificial Intelligence, AI, / Machine Learning,ML, models or functionalities available at the UE are to provide radio measurementpredictions.

31. The method of claim 30, further comprising determining (604) (a) a second set ofmeasurement resources on which the UE is to perform radio measurements for data collection forthe one or more AI / ML models or functionalities in order to determine radio measurementpredictions in a third set of measurement resources and (b) the third set of measurement resources,based on the one or more second sets of recommended measurement resources and the one or morethird sets of measurement resources for prediction indicated by the information comprised in thefirst indication.

32. The method of claim 31, further comprising transmitting (604) a second indication to theUE, the second indication comprising information that indicates the determined second set of measurement resources and information that indicates the determined third set of measurement resources.

33. The method of claim 32, further comprising transmitting (606) reference signals associatedto resources included in the determined second and third sets of measurement resources.

34. A network node (900) comprising:processing circuitry (902) configured to cause the network node (900) to: transmit (600) to a User Equipment, UE, information indicative of one or more firstsets of measurement resources;receive (602a), from the UE, a first indication comprising any of:information that indicates one or more second sets of recommended measurement resources in which the UE is to perform radio measurements; and information that indicates one or more third sets of measurement resourcesfor prediction in which one or more trained Artificial Intelligence, AI, / Machine Learning, ML, models or functionalities available at the UE are to provide radio measurement predictions.

35. The network node (900) of claim 34, wherein the processing circuitry (902) is furtherconfigured to cause the network node (900) to perform the method of any of claims 31 to 33.

Images