Methods for user equipment-side artificial intelligence / machine learning models training initiated by the network

Abstract

Embodiments described herein related to methods and apparatus for user equipment(UE)-side artificial intelligence(AI) / machine learning(ML) models training. A method performed by a UE is provided. The method comprises one or more of: sending, to a radio access network, RAN, node, in a network, an indication of a capability of the UE to train and use an ML model; in response to receiving, from the RAN node, a request as to whether the ML model is applicable to a particular configuration, condition, or scenario of the RAN node or the network, sending, to the RAN node, an indication of whether the ML model is applicable to the particular configuration, condition, or scenario; and sending, to the RAN node, an indication that the UE is ready to acquire data for training the ML model.

Description

[0001] METHODS FOR USER EQUIPMENT-SIDE ARTIFICIAL INTELLIGENCE / MACHINE LEARNING MODELS TRAINING INITIATED BY THE NETWORK

[0002] TECHNICAL FIELD

[0003] Embodiments described herein relate to methods and apparatus for User Equipment-sided Artificial lntelligence(AI) / Machine Learning (ML) models training.

[0004] BACKGROUND

[0005] One of the key features of 5thGeneration (5G) New Radio (NR), compared to previous generations of wireless networks, is the ability to operate at higher frequencies (e.g., above 10 GHz). The available large transmission bandwidths in these frequency ranges can potentially provide large data rates. However, as carrier frequency increases, both path loss 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 particular direction toward the receiver. However, large radio antenna arrays - at both receiver and transmitter sides - are needed to create such highly directional beams.

[0006] To reduce hardware costs, large antenna arrays for high frequencies use time-domain analogue beamforming. The core idea of analogue beamforming is to share a single radio frequency chain between many (or, potentially, all) of the antenna elements. A limitation of analogue beamforming is that it is only possible to transmit radio energy using one beam (in one direction) at a given time.

[0007] The above limitation requires the network (NW) and user equipment (UE) to perform beam management (BM) 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 nonoverlapping time intervals, using a predetermined pattern. By measuring the quality of these reference signals at the receiver side, the best transmit and receive beams can be identified.

[0008] NR Beam management procedures

[0009] Beam management procedures in NR are defined by a set of Layer- 1 / Layer-2 (L1 / L2) procedures that establish and maintain 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.

[0010] In the case of downlink (DL) transmission from the NW to the UE, P1 / P2 / P3 beam management procedures can be performed according to Third Generation Partnership Project (3GPP) technical report (TR) 38.843 v2.0.0 (“Study on Artificial Intelligence (Al) / Machine Learning (ML) for NR air interface (Release 18)”, Dec. 2023) to overcome the challenges of establishing and maintaining the beam pairs when, for example, a UE moves or some blockage in the environment requires the beams to change. Although these scenarios are not directly mentioned in specifications, there are relevant procedures defined which enable the realization of these scenarios, examples of such realization are depicted in the corresponding figures for each scenario.

[0011] Fig. 1 below shows synchronization signal block (SSB) beam selection as part of initial access procedure according to the P1 procedure. The P1 procedure is used to enable UE measurement on different transmission / reception point (TRP) Tx beams to support selection of TRP Tx beams / UE Rx beam(s). During initial access, for example, 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, as shown in Fig. 1. Random access is then transmitted on the random access channel (RACH) resources indicated by the selected SSB. The corresponding beam will be used by 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 signalling.

[0012] For beamforming at TRP, the procedure typically includes an intra / inter-TRP Tx beam sweep from a set of different beams. For beamforming at UE, the procedure typically includes a UE Rx beam sweep from a set of different beams.

[0013] Fig. 2 below shows channel state information reference signal (CSI-RS) Tx beam selection in downlink according to the P2 procedure. The P2 procedure is used to enable UE measurement on different TRP Tx beams to possibly change inter / intra-TRP Tx beam(s). The network can use the SSB beam as an indication of which (narrow) CSI-RS beams to try; that is, the selected SSB beam can be used to define a candidate set of narrow 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 the network. 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.

[0014] The P2 procedure is performed on a possibly smaller set of beams for beam refinement 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. The UE then measures the quality of each CSI-RS beam on its current Rx beam and sends feedback about the quality of the measured beams. Thereafter, based on this feedback, gNB will decide and possibly indicate to the UE which beam will be used in future transmissions.

[0015] Fig. 3 below shows UE Rx beam selection for a corresponding CSI-RS Tx beam in DL according to the P3 procedure. The P3 procedure is used to enable UE measurement on the same TRP Tx beam to change a UE Rx beam in the case the 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.

[0016] In connected mode, P3 can be used by the UE to find the best Rx beam for corresponding Tx beam. In this case, the gNB keeps one CSI-RS Tx beam at a time, and the UE performs the sweeping and measurements on its own Rx beams for that specific Tx beam. The UE then finds the best corresponding Rx beam based on the measurements and will use it in future for reception when the gNB indicates the use of that Tx beam.

[0017] Beam measurement and reporting in NR

[0018] For beam management, a UE can be configured to report RSRP and / or signal to interference and 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 physical uplink control channel (PUCCH) or physical uplink shared channel (PUSCH) to the network node, e.g., gNB.

[0019] Reference signal configurations in NR

[0020] CSI-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.

[0021] In NR, the CSI-RS for beam management is defined as a 1- or 2-port CSI-RS resource in a CSI-RS resource set where the field repetition is present. The following three types of CSI-RS transmissions are supported:

[0022] • Periodic CSI-RS: CSI-RS is transmitted periodically in certain slots. This CSI-RS transmission is semi-statically configured using radio resource control (RRC) signalling with 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 signalling with parameters such as periodicity and slot offset. However, unlike periodic CSI-RS, dynamic signalling 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 OFDM symbol locations) for aperiodic CSI-RS are semi-statically configured. The transmission of aperiodic CSI-RS is triggered by dynamic signalling through PDCCH using the CSI request field in uplink (UL) DCI, in the same downlink control information (DCI) where the UL resources for the measurement 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.

[0023] SSB - In NR, an SSB consists of a pair of synchronization signals (SSs), physical broadcast channel (PBCH), and demodulation reference signal (DMRS) for PBCH. An SSB is mapped to 4 consecutive orthogonal frequency-division multiplexing (OFDM) symbols in the time domain and 240 contiguous subcarriers (20 resource blocks (RBs)) in the frequency domain.

[0024] 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 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 1 (SIB1).

[0025] The maximum number of SSBs within a half frame, denoted by L, depends on the frequency band. The time locations for these L candidate SSBs within a half frame depends on the subcarrier spacing (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 unused candidate positions can be used for the transmission of data or control signalling 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.

[0026] Measurement resource configurations in NR and reporting

[0027] A UE can be configured with the following:

[0028] N>1 CSI reporting settings (CSI-ReportConfig) and

[0029] M>1 resource settings (CSI-ResourceConfig). Each CSI reporting setting is linked to one or more resource setting for channel and / or interference measurement. The CSI framework is modular in the sense that several CSI reporting settings may be associated with the same Resource Setting.

[0030] The measurement resource configurations for beam management are provided to the UE by RRC information element (IE) (CSI-ResourceConfigs). One CSI-ResourceConfig contains several non-zero-power (NZP-) CSI-RS-ResourceSets and / or CSI-SSB-ResourceSets.

[0031] A UE can be configured to measure CSI-RSs using the RRC information element (IE) NZP-CSI-RS-ResourceSet. A 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:

[0032] mapping to resource elements (REs),

[0033] the number of antenna ports, and

[0034] time-domain behaviour.

[0035] Up to 64 CSI-RS resources can be grouped together in a 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.

[0036] Three types of CSI reporting are supported in NR as follows:

[0037] • Periodic CSI Reporting on PUCCH: CSI is reported periodically by a UE. Parameters such as periodicity and slot offset are configured semi-statically by higher layer RRC signalling from the network node to the UE

[0038] • 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.

[0039] • 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 is semi-statically configured by RRC but the triggering is dynamic.

[0040] 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) CSI Reference Signal Resource Indicator (CRI) / SS / PBCH Block Resource Indicator (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.

[0041] Beam Prediction The use case of beam prediction which will be standardized as part of 3GPP Rel. 19 work item RP-234039 (“New WID on Artificial Intelligence (Al) / Machine Learning (ML) for NR Air Interface” Dec. 2023) consists of spatial beam prediction, and temporal beam prediction. The core idea of this use case is to predict the “best” beam (or beams) from a Set A of beams using measurement results from another Set B of beams.

[0042] According to 3GPP TR 38.843 v2.0.0, the spatial-domain beam prediction 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. Hence, the radio measurements on the Set B of resources would be the input of an AI / ML model / functionality, whereas the radio measurements on the set A of resources would be the output of the AI / ML model / functionality.

[0043] 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 were studied in Release 18:

[0044] SetB is a subset of a Set A. This is shown below in Fig. 4, which illustrates a grid-of- beam type radiation pattern. Each row corresponds to a certain zenith angle from the antenna array and each column corresponds to a certain azimuth angle from the antenna array. Set A is a set of 8 SSB / CSI-RS beams shown in Fig. 4 (both light and dark circles), and Set B is the set of 4 beams indicated by the 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. Set A and Set B correspond to two different sets of beams. For example, Set A is a set of 30 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.

[0045] SUMMARY

[0046] The beam prediction can be performed in the gNB and / or 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 measuring certain resources, thereby saving energy, whereas from the gNB point of view, the gNB can get good radio measurement estimations from the UE without providing the measuring resources, thereby limiting the overhead over the air-interface.

[0047] 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 / machine learning (AI / ML) model / function. In particular, an AI / ML model / function may be trained to perform the beam prediction under certain applicability conditions. Such applicability conditions need to be fulfilled in order for the AI / ML 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 underwhich 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.

[0048] In order to determine whether an AI / ML model / function is applicable or not, the UE needs to assess the applicability conditions of such AI / ML 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).

[0049] AI / ML for NR Air Interface: Life cycle management (LCM)

[0050] In the physical layer, AI / ML has been introduced recently. The application of ML and Al for physical layer design and optimization is being investigated to optimize the design of the airinterface in wireless communications.

[0051] In 3GPP NR standardization work, a Release 18 study item (SI) on AI / ML for NR air interface started in May 2022 (3GPP TR 38.843). This study item has explored the benefits of augmenting the air interface with features enabling improved support of AI / ML based algorithms for enhanced performance and / or reduced complexity / overhead. Through studying a few selected use cases (CSI feedback, beam management and positioning), this SI aims to lay the foundation for future air interface use cases leveraging AI / ML techniques.

[0052] The 3GPP work is continuing with a follow-up specification work in the Release 19 AI / ML for NR air interface work item (Wl) (3GPP RP-234039). 6thGeneration (6G) systems based on 3GPP Release 20+ are expected to consider additional AI / ML use cases.

[0053] A possible high-level description of model life-cycle management (LCM) for Al on the physical layer (PHY) can include the stages and data / signal flows depicted in Fig. 6 below:

[0054] Data collection

[0055] A 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).

[0056] i. First, the model is trained by collecting measurement data for a large set of UE locations / 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.

[0057] ii. Second, when using the model for prediction (i.e. inference), measurement data for any UE to predict beams for is 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.

[0058] iii. Finally, measurements can be obtained to monitor that the model functions well, or otherwise disable it or update it.

[0059] 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 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 to train / retrain / finetune the NW-side model. The training of the NW-side model can occur in the gNB itself or in a NW-node such as the operation administration and maintenance (OAM).

[0060] For the UE-side model, the UE may need to collect measurements from the gNB signals (e.g. CSI-RS or SSB). Once the data collection is completed, the collected data should be transferred to a training entity that is in charge of training / retraining / finetuning the UE-side model based on the collected measurements, and possibly based 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 example, the UE may be trained on data for a set of resources configured by the gNB, i.e. the UE performs radio measurements on such set of resources, and based on this training the training entity will determine from this configured set of resources the set of resources (set B) that the UE needs to measure to perform the predictions on another set of resources (set A).

[0061] For the case of the 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 core network (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.

[0062] There currently exist certain challenge(s). For example, a UE may not possess any applicable trained UE-side AI / ML model, i.e. a model that is trained based on configurations and / or conditions that are consistent across the training and inference phases, to be applied to the cell served by a gNB. Hence, the UE may need to perform data collection to train / retrain / finetune an AI / ML model / functionality for the configurations and / or conditions for which it has no applicable model. For the data collection for training, the UE may need additional assistance and signals sent by a gNB; however, the gNB may not be aware that the UE needs this.

[0063] Some previous proposals provide methods in which the UE requests the network to generate signals according to specific configurations / conditions for which the UE does not have a trained model. The UE signals to the network the needed configurations / conditions for signal generation; although the UE may not have complete information regarding the detailed options for configurations at the gNB and it may only know certain abstract information regarding the gNB configurations or conditions, e.g. only an associated ID may be available from the network based on the configurations. Hence, improvements in training the needed model are desired.

[0064] Certain aspects of the disclosure and their embodiments may provide solutions to these or other challenges.

[0065] Embodiments of the present disclosure include a method for enabling a UE for data collection for training by indicating to the network / gNB, in response to a network / gNB’s request, whether the UE has an applicable model for given network / gNB conditions / configurations / scenarios / etc. If not, then the network / gNB can use those conditions / configurations / scenarios / etc. for configuring data collection for model training.

[0066] Alternatively or in addition, the UE can transmit an indication to the network (e.g., to a RAN node, gNB), indicating the need to perform data collection for the sake of training one or more AI / ML model and / or functionality. The indication may also include one or more radio resources and / or configurations that need to be configured at the UE to allow the data collection for the training of the UE-side AI / ML model(s) / functionality(ies) according to specific network / gNB conditions / configurations / scenarios / etc.

[0067] Alternatively or in addition, the UE can indicate its preference of when to stop the training phase, e.g. as an estimated time duration or stop moment before the training phase starts, as a stop indication after the UE trained enough, as a stop indication after the UE collected enough data, and / or by indicating the size of the dataset to be collected for training. The indication(s) may be conveyed in a message to the network node, e.g. a field in a message (medium access control (MAC) / RRC message), or conveyed by using certain radio resources for transmitting it (e.g. in a configured grant or in certain RACH resources / preambles / partitions).

[0068] In response to the transmission of the indication from the UE (including either explicit requested configurations for training or the report of the applicability of the model for a given configuration / condition / scenario / etc. requested by the network), or based on performance monitoring at the network and detecting degraded model performance, the UE may indicate readiness and / or willingness to train a model (or re-train a model or fine-tune a model), or the UE may acknowledge readiness and or the willingness to train a model (or re-train a model, or fine- tune a model) following a request from the network checking whether the UE is ready and or willing to train a model (or re-train a model, or fine-tune a model).

[0069] The UE may receive from the RAN node (e.g. gNB) a command and / or message / information to allow the UE to (re)train an AI / ML model / functionality; the command or message / information received by the UE may relate to or specify a configuration that allows the UE’s AI / ML model / functionality to later be applicable to the gNB under certain configurations / conditions / scenarios.

[0070] The gNB / network may decide start / stop of the training phase. The network may use the UE’s preference of when to stop the training phase, e.g. using the estimate before the training phase starts, or using an indication from the UE after it trained enough, or using the requested size of the dataset to be collected for training.

[0071] The gNB / network may trigger data collection for training and stops data collection for training using L1 / L2 signalling.

[0072] Certain embodiments may provide one or more of the following technical advantage(s). The proposed method allows the network / gNB to become aware when one or more UEs need to train (or re-train or fine-tune) an AI / ML model / functionality to operate in the coverage area of this gNB. Additionally, the gNB may become aware of the radio resources that one or more UEs need to collect / measure to perform the AI / ML model / functionality training.

[0073] Another advantage of the proposed method is that it enables the network / gNB to implicitly infer the configurations / conditions for which the UE’s model need to be trained based on the UE’s acknowledgment to a model applicability request from the network. Hence, in some embodiments, there may be no need for the UE to send the configurations / conditions to be used for configuring the training. This reduces the required signalling and the needed messages to be exchanged.

[0074] In addition, the UE usually has limited information regarding the detailed configurations at the gNB and it may only know certain abstract information regarding the gNB configurations or conditions, e.g. only an associated ID may be provided from a NW node to the UE. Hence, the UE may not be capable of instructing the gNB for the configurations or conditions to use for generating signals for data collection and UE training. The proposed method provides an alternative approach for configuring the gNB for training the needed model that address this challenge.

[0075] According to a first aspect, there is provided a method performed by a user equipment (UE) that is configured to train and use a machine learning (ML) model. The method can comprise any one or more of the following steps (in any suitable order): (i) sending, to a radio access network (RAN) node in a network, an indication of a capability of the UE to train and use the ML model; (ii) in response to receiving, from a RAN node, a request as to whether the ML model is applicable to a particular configuration, condition, or scenario of the RAN node or the network, sending, to the RAN node, an indication of whether the ML model is applicable to the particular configuration, condition, or scenario; and (iii) sending, to the RAN node, an indication that the UE is ready to acquire data for training the ML model.

[0076] According to a second aspect, there is provided a method performed by a RAN node in a network with a UE. The method can comprise any one or more of the following steps (in any suitable order): (i) determining, based on performance monitoring, that the UE requires data for training a machine learning (ML) model of the UE; (ii) receiving, from the UE, an indication of a capability of the UE to train and use the ML model; (iii) in response to a request as to whether the ML model is applicable to a particular configuration, condition, or scenario of the RAN node or the network, receiving, from the UE, an indication of whether the ML model is applicable to the particular configuration, condition or scenario; and (iv) receiving, from the UE, an indication that the UE is ready to acquire data for training the ML model.

[0077] According to a third aspect, there is provided a computer program product comprising a computer readable medium having computer readable code embodied therein, the computer readable code being configured such that, on execution by a suitable computer or processor, the computer or processor is caused to perform the method according to the first aspect, the second aspect, or any embodiments thereof.

[0078] According to a fourth aspect, there is provided a user equipment (UE) configured to perform the method according to the first aspect, the second aspect, or any embodiments thereof.

[0079] According to a fifth aspect, there is provided a user equipment (UE) comprising a processor and a memory, said memory containing instructions executable by said processor whereby said UE is operative to perform the method according to the first aspect, the second aspect, or any embodiments thereof.

[0080] According to a sixth aspect, there is provided a radio access network (RAN) node, configured to perform the method according to the first aspect, the second aspect, or any embodiments thereof.

[0081] According to a seventh aspect, there is provided a radio access network (RAN) node comprising a processor and a memory, said memory containing instructions executable by said processor whereby said RAN node is operative to perform the method according to the first aspect, the second aspect, or any embodiments thereof.

[0082] BRIEF DESCRIPTION OF THE DRAWINGS

[0083] For a better understanding of the embodiments of the present disclosure, and to show how it may be put into effect, reference will now be made, by way of example only, to the accompanying drawings. Some of the embodiments contemplated herein will now be described more fully with reference to the accompanying drawings, in which:

[0084] Fig. 1 shows a SSB beam selection as part of initial access procedure according to P1 scenario;

[0085] Fig. 2 shows CSI-RS Tx beam selection in downlink according to P2 scenario;

[0086] Fig. 3 shows UE Rx beam selection for corresponding CSI-RS Tx beam in DL according to P3 scenario;

[0087] Fig. 4 is an example where Set B is a subset of Set A;

[0088] Fig. 5 is an example where Set A is a set of narrow beams and Set B is a set of wide beams; Fig. 6 is a diagram illustrating a functional framework of model LCM for Al for air interface; Fig. 7 is a signalling diagram illustrating an example implementation of the techniques described herein with network initiation and implicit UE acknowledgement to start training;

[0089] Fig. 8 is a signalling diagram illustrating an example implementation of the techniques described herein with network initiation and explicit UE acknowledgment to start training;

[0090] Fig. 9 is a flow chart illustrating a method in accordance with some embodiments;

[0091] Fig. 10 is a flow chart illustrating a method in accordance with some embodiments;

[0092] Fig. 11 shows an example of a communication system in accordance with some embodiments;

[0093] Fig. 12 shows a UE in accordance with some embodiments;

[0094] Fig. 13 shows a RAN network node in accordance with some embodiments; and

[0095] Fig. 14 is a block diagram illustrating a virtualization environment in which functions implemented by some embodiments may be virtualized.

[0096] DETAILED DESCRIPTION

[0097] 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.

[0098] Embodiments of the present disclosure include a method for enabling a UE for data collection for training by indicating to the network / gNB, in response to a network / gNB’s request, whether the UE has an applicable model for given network / gNB conditions / configurations / scenarios / etc. If not, then the network / gNB can use those conditions for configuring data collection for model training.

[0099] Alternatively or in addition, the UE transmits an indication to the network (e.g., to a RAN node, gNB), indicating the need to perform data collection for the sake of training one or more AI / ML model and / or functionality. The indication may also include one or more radio resources and / or configurations that need to be configured at the UE to allow the data collection for the training of the UE-side AI / ML model(s) / functionality(ies) according to specific network / gNB conditions / configurations / scenarios / etc.

[0100] Alternatively or in addition, the UE can indicate its preference of when to stop the training phase, e.g. as an estimated time duration or stop moment before the training phase starts, as a stop indication after the UE trained enough, as a stop indication after the UE collected enough data, and / or by indicating the size of the dataset to be collected for training. The indication(s) may be conveyed in a message to the network node, e.g. a field in a message (MAC / RRC message), or conveyed by using certain radio resources for transmitting it (e.g. in a configured grant or in certain RACH resources / preambles / partitions).

[0101] Fig. 7 illustrates the following example implementation. The gNB may correspond to the RAN node QQ300 of Figure 13. The UE may correspond to the UE QQ200 of the Figure 12.

[0102] 1) The network / gNB may request the UE’s capability. This can be part of UECapabilityEnquiry, Stepl illustrated in Fig. 7.

[0103] 2) The UE may report its AI / ML capability / functionality, for example its AI / ML-based beam management (BM) capability. This can be part of UECapabilityreporting, Step2 illustrated in Fig. 7.

[0104] 3) The network / gNB may request the applicability of the BM functionality / capability for a given configuration, where the configuration for example may include set A (i.e. the indices of beams in set A introduced in Section 2.2.3), set B (i.e. the indices of beams in set B as introduced in Section 2.2.3). This can be part of RRCReconfiguration, Step3 illustrated in Fig. 7.

[0105] 4) The UE may report the applicability of the functionality for the given configuration (e.g. set A or set B). If the UE does not have an applicable model then it may also report a flag train_flag with a value of 0 or 1 in addition to the applicability reporting. Then the report may either indicate that there is an applicable model, or that there is no applicable model and train_flag=O when the UE does not want training, or there is no applicable model and train_flag=1 when the UE request to train a model. This can be part of Applicable functionality reporting, Step4 illustrated in Fig. 7. If the UE indicates that is has an applicable model, then the method proceeds to Step7 in Fig. 7.

[0106] 5) If the functionality is not applicable for the given configuration, then the network may configure the UE for training and data collection for that configuration, where the configuration may include set A, set B, and / or the length of dataset to be collected (i.e. the number of resources to be allocated for training reference signals). This can be part of RRCReconfiguration, Step5 illustrated in Fig. 7.

[0107] 6) The network may trigger the data collection by signalling the UE, e.g. the start and the end of the data collection session.

[0108] • Alternatively, the data collection may be started right after sending the configuration signal and / or stopped by sending an updated configuration signal.

[0109] 7) The UE may report applicable functionality based on the updated list of the trained models. This can be part of Applicable functionality reporting, Step6 illustrated in Fig. 7.

[0110] 8) The network may configure the UE for inference. This can be performed as part of RRCReconfiguration, Step7 in Fig. 7. This step is also performed if the network determines in Step4 that the functionality is applicable.

[0111] In another embodiment, a UE may start data collection for the training of UE-side Al model when the UE is in RRCJnactive mode or in RRCJdle mode rather than RRC_connected mode, which may be configured by the network or may be predefined at the UE side or may be indicated by the OTT server. Additionally or alternatively, the network may be aware which RRC mode(s) the UE can support for data collection of the training of Al model (e.g. UE-side Al model).

[0112] Fig. 8 below illustrates another example in which an explicit signal is sent from UE to the network in Step 5-a to acknowledge the availability and the interest of the UE to start a training session. The network may initiate data collection using L1 / L2 signalling following receiving this acknowledgment.

[0113] The following describes exemplary steps that can be performed by a UE in accordance with particular embodiments. The method 900 may be performed by a User Equipment (UE) or wireless device (e.g. the UE QQ112 or UE QQ200 as described later with reference to Figs. Hand 12 respectively). The UE may perform the methods in response to executing suitably formulated computer readable code. The computer readable code may be embodied or stored on a computer readable medium, such as a memory chip, optical disc, or other storage medium. The computer readable medium may be part of a computer program product. In these methods, the UE is configured to train and use an ML model. The method may comprise any one or more of the three steps set out below. That is, an exemplary method may comprise just one of the three steps, or multiple ones of the three steps, with those multiple steps being performed in any suitable order. The steps are:

[0114] sending 910 an indication of a capability of the UE to train and use the ML model to a RAN node;

[0115] in response to receiving (from a RAN node) a request as to whether the ML model is applicable to a particular configuration, condition or scenario of the RAN node or the network, sending 920, to the RAN node, an indication of whether the ML model is applicable to the particular configuration, condition, or scenario;

[0116] sending 930 an indication to the RAN node that the UE is ready to acquire data for training the ML model.

[0117] The UE may determine whether the ML model is applicable to a particular configuration, condition or scenario in a number of different ways. For example, this determining may be performed by comparing network assistance information (NAI) that is received for inference to NAI that the UE received for training of its existing ML model. If they are not the same, it may be determined (e.g. reported) that training data is required. Alternatively, from a list of configurations, conditions or scenarios, a subset of configurations, conditions or scenarios can be selected for which consistency across training and inference is essential. When the network requests whether the ML model of the UE is applicable to a particular configuration, condition or scenario of the RAN node or the network, the UE can check whether these subsets of configurations, conditions or scenarios are the same as the ones for training.

[0118] The following describes exemplary steps that can be performed by a RAN node in accordance with particular embodiments. The method 1000 may be performed by the RAN network node QQ110 or RAN network node QQ300 as described later with reference to Fig. Hand 13 respectively. The RAN node may perform the methods in response to executing suitably formulated computer readable code. The computer readable code may be embodied or stored on a computer readable medium, such as a memory chip, optical disc, or other storage medium. The computer readable medium may be part of a computer program product. The method may comprise any one or more of the three steps set out below. That is, an exemplary method may comprise just one of the four steps, or multiple ones of the four steps, with those multiple steps being performed in any suitable order. The steps are:

[0119] determining 1010, based on performance monitoring, that the UE requires data for training an ML model of the UE;

[0120] receiving 1020, from the UE, an indication of a capability of the UE to train and use the ML model;

[0121] in response to a request as to whether the ML model is applicable to a particular configuration, condition, or scenario of the RAN node or the network, receiving 1030, from the UE, an indication of whether the ML model is applicable to the particular configuration, condition or scenario; and

[0122] receiving 1040, from the UE, an indication that the UE is ready to acquire data for training the ML model.

[0123] With regard to the RAN node determining that the UE requires data fortraining or re-training or fine tuning an ML model based on performance monitoring, the RAN node can determine that the UE requires data for training if degraded performance is detected. For example, the performance using a given performance metric can be compared to a pre-set threshold, and if the performance measure is lower than the threshold then the performance degradation can be detected. Alternatively, the performance of the AI / ML model can be compared to the legacy method using a specific performance metric, and if the performance measure is lower than a threshold, then degraded performance can be detected.

[0124] Fig. 11 shows an example of a communication system QQ100 in accordance with some embodiments. In the example, the communication system QQ100 includes a telecommunication network QQ102 that includes an access network QQ104, such as a radio access network (RAN), and a core network QQ106, which includes one or more core network nodes QQ108. The access network QQ104 includes one or more access network nodes, such as access network nodes QQ110a and QQ110b (one or more of which are also referred to as RAN network nodes or RAN nodes QQ110 herein), or any other similar 3rdGeneration Partnership Project (3GPP) access nodes or non-3GPP access points (AP). 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 QQ102 includes one or more Open-RAN (ORAN) network nodes. An ORAN network node is a node in the telecommunication network QQ102 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 QQ102, including one or more network nodes QQ110 and / or core network nodes QQ108.

[0125] Examples of an ORAN network node include an open radio unit (0-Rll), an open distributed unit (O-DU), an open central unit (O-CU), including an O-CU control plane (O-CU-CP) or an O-Cll user plane (O-CU-UP), a RAN intelligent controller (RIC) (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 node may be a logical node in a physical node. Furthermore, an ORAN network node may be implemented 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 Orchestration (SMO) Framework via an 0-2 interface defined by the O-RAN Alliance or comparable technologies.

[0126] The network nodes QQ110 facilitate direct or indirect connection of wireless devices (also referred to interchangeably herein as user equipment (UE)), such as by connecting UEs QQ112a, QQ112b, QQ112c, and QQ112d (one or more of which may be generally referred to as UEs QQ112) to the core network QQ106 over one or more wireless connections. The access network nodes QQ110 may be, for example, access points (APs) (e.g. radio access points), base stations (BSs) (e.g. radio base stations, Node Bs, evolved Node Bs (eNBs) and New Radio (NR) NodeBs (gNBs)). 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 QQ100 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 QQ100 may include and / or interface with any type of communication, telecommunication, data, cellular, radio network, and / or other similar type of system.

[0127] The wireless devices / UEs QQ112 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 QQ110 and other communication devices. Similarly, the access network nodes QQ110 are arranged, capable, configured, and / or operable to communicate directly or indirectly with the UEs QQ112 and / or with other network nodes or equipment in the telecommunication network QQ102 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 QQ102.

[0128] In the depicted example, the core network QQ106 connects the access network nodes QQ110 to one or more host computing systems, such as host QQ116. 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 QQ106 includes one more core network nodes (e.g. core network node QQ108) that are structured with hardware and software components. Features of these components may be substantially similar to those described with respect to the wireless devices / UEs, access network nodes, and / or hosts, such that the descriptions thereof are generally applicable to the corresponding components of the core network node QQ108. 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).

[0129] The host QQ116 may be under the ownership or control of a service provider other than an operator or provider of the access network QQ104 and / or the telecommunication network QQ102. The host QQ116 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.

[0130] As a whole, the communication system QQ100 of Fig. 11 enables connectivity between the wireless devices / UEs, network nodes, and hosts. In that sense, the communication system 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 2ndGeneration (2G), 3rdGeneration (3G), 4thGeneration (4G), 5thGeneration (5G) standards, or any applicable future generation standard (e.g. 6thGeneration (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.

[0131] In some examples, the telecommunication network QQ102 is a cellular network that implements 3GPP standardized features. Accordingly, the telecommunications network QQ102 may support network slicing to provide different logical networks to different devices that are connected to the telecommunication network QQ102. For example, the telecommunications network QQ102 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 loT services to yet further UEs.

[0132] In some examples, the UEs QQ112 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 QQ104 on a predetermined schedule, when triggered by an internal or external event, or in response to requests from the access network QQ104. Additionally, a UE may be configured for operating in single- or multi-Radio Access Technology (RAT) or multistandard mode. For example, a UE may operate with any one or combination of Wi-Fi, NR (New Radio) and LTE, i.e. being configured for multi-radio dual connectivity (MR-DC), such as E-UTRAN (Evolved-UTRA (UMTS Terrestrial Radio Access) Network) New Radio - Dual Connectivity (EN-DC).

[0133] In the example, the hub QQ114 communicates with the access network QQ104 to facilitate indirect communication between one or more UEs (e.g., UE QQ112c and / or QQ112d) and network nodes (e.g., network node QQ110b). In some examples, the hub QQ114 may be a controller, router, content source and analytics, or any of the other communication devices described herein regarding UEs. For example, the hub QQ114 may be a broadband router enabling access to the core network QQ106 for the UEs. As another example, the hub QQ114 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 QQ110, or by executable code, script, process, or other instructions in the hub QQ114. As another example, the hub QQ114 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 QQ114 may be a content source. For example, for a UE that is a VR device, display, loudspeaker, or other media delivery device, the hub QQ114 may retrieve VR assets, video, audio, or other media or data related to sensory information via a network node, which the hub QQ114 then provides to the UE either directly, after performing local processing, and / or after adding additional local content. In still another example, the hub QQ114 acts as a proxy server or orchestrator for the UEs, in particular if one or more of the UEs are low energy Internet of Things (loT) devices.

[0134] The hub QQ114 may have a constant / persistent or intermittent connection to the network node QQ110b. The hub QQ114 may also allow for a different communication scheme and / or schedule between the hub QQ114 and UEs (e.g., UE QQ112c and / or QQ112d), and between the hub QQ114 and the core network QQ106. In other examples, the hub QQ114 is connected to the core network QQ106 and / or one or more UEs via a wired connection. Moreover, the hub QQ114 may be configured to connect to a machine-to-machine (M2M) service provider over the access network QQ104 and / or to another UE over a direct connection. In some scenarios, UEs may establish a wireless connection with the network nodes QQ110 while still connected via the hub QQ114 via a wired or wireless connection. In some embodiments, the hub QQ114 may be a dedicated hub - that is, a hub whose primary function is to route communications to / from the UEs from / to the network node QQ110b. In other embodiments, the hub QQ114 may be a nondedicated hub - that is, a device which is capable of operating to route communications between the UEs and network node QQ110b, but which is additionally capable of operating as a communication start and / or end point for certain data channels.

[0135] Fig. 12 shows a wireless device or UE QQ200 in accordance with some embodiments. The UE QQ200 presents additional details of some embodiments of the UE QQ112 of Fig. 11. As used herein, a wireless device / UE refers to a device capable, configured, arranged and / or operable to communicate wirelessly with network nodes and / or other UEs. Examples of a wireless device / UE include, but are not limited to, a smart phone, mobile phone, cell phone, voice over IP (VoIP) phone, wireless local loop phone, desktop computer, personal digital assistant (PDA), wireless cameras, gaming console or device, music storage / playback device, wearable terminal device, wireless endpoint, mobile station, tablet, laptop, laptop-embedded equipment (LEE), laptop-mounted equipment (LME), an Augmented Reality (AR) or Virtual Reality (VR) device, wireless customer-premise equipment (CPE), vehicle, vehicle-mounted or vehicle embedded / integrated wireless device, etc. Other examples include any UE identified by the 3rd Generation Partnership Project (3GPP), including a narrow band internet of things (NB-loT) UE, a machine type communication (MTC) UE, and / or an enhanced MTC (eMTC) UE.

[0136] A wireless device / 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).

[0137] The UE QQ200 includes processing circuitry QQ202 that is operatively coupled via a bus QQ204 to an input / output interface QQ206, a power source QQ208, a memory QQ210, a communication interface QQ212, and / or any other component, or any combination thereof. Certain UEs may utilize all or a subset of the components shown in Fig. QQ2. 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.

[0138] The processing circuitry QQ202 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 QQ210. The processing circuitry QQ202 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 QQ202 may include multiple central processing units (CPUs). The processing circuitry QQ202 may be configured to cause the UE QQ202 to perform the methods as described herein, such as method 900.

[0139] In the example, the input / output interface QQ206 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 QQ200. 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.

[0140] In some embodiments, the power source QQ208 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 QQ208 may further include power circuitry for delivering power from the power source QQ208 itself, and / or an external power source, to the various parts of the UE QQ200 via input circuitry or an interface such as an electrical power cable. Delivering power may be, for example, for charging of the power source QQ208. Power circuitry may perform any formatting, converting, or other modification to the power from the power source QQ208 to make the power suitable for the respective components of the UE QQ200 to which power is supplied.

[0141] The memory QQ210 may be or be configured to include memory such as random access memory (RAM), read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), magnetic disks, optical disks, hard disks, removable cartridges, flash drives, and so forth. In one example, the memory QQ210 includes one or more application programs QQ214, such as an operating system, web browser application, a widget, gadget engine, or other application, and corresponding data QQ216. The memory QQ210 may store, for use by the UE QQ200, any of a variety of various operating systems or combinations of operating systems.

[0142] The memory QQ210 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 random access memory (SDRAM), external micro-DIMM SDRAM, smartcard memory such as 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 Integrated SIM (ISIM), other memory, or any combination thereof. The UICC may for example be an embedded UICC (eUlCC), integrated UICC (iUICC) ora removable UICC commonly known as ‘SIM card’. The memory QQ210 may allow the UE QQ200 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 memory QQ210, which may be or comprise a device-readable storage medium.

[0143] The processing circuitry QQ202 may be configured to communicate with an access network or other network using the communication interface QQ212. The communication interface QQ212 may comprise one or more communication subsystems and may include or be communicatively coupled to an antenna QQ222. The communication interface QQ212 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 QQ218 and / or a receiver QQ220 appropriate to provide network communications (e.g., optical, electrical, frequency allocations, and so forth). Moreover, the transmitter QQ218 and receiver QQ220 may be coupled to one or more antennas (e.g., antenna QQ222) and may share circuit components, software or firmware, or alternatively be implemented separately.

[0144] In the illustrated embodiment, communication functions of the communication interface QQ212 may include cellular communication, Wi-Fi communication, LPWAN communication, data communication, voice communication, multimedia communication, short-range communications such as Bluetooth, near-field communication, location-based communication such as the use of the global positioning system (GPS) or other Global Navigation Satellite System (GNSS) to determine a location, another like communication function, or any combination thereof. Communications may be implemented in according to one or more communication protocols and / or standards, such as IEEE 802.11, Code Division Multiplexing Access (CDMA), Wideband Code Division Multiple Access (WCDMA), GSM, LTE, New Radio (NR), UMTS, WiMax, Ethernet, transmission control protocol / internet protocol (TCP / IP), synchronous optical networking (SONET), Asynchronous Transfer Mode (ATM), QUIC, Hypertext Transfer Protocol (HTTP), and so forth.

[0145] Regardless of the type of sensor, a UE may provide an output of data captured by its sensors, through its communication interface QQ212, 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 several sensors), 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).

[0146] 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.

[0147] A UE, when in the form of an Internet of Things (loT) 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 loT device are a device which is or which is embedded in: a connected refrigerator or freezer, a TV, 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 wearable for tactile augmentation or sensory enhancement, a water sprinkler, an animal- or item-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 loT device comprises circuitry and / or software in dependence of the intended application of the loT device in addition to other components as described in relation to the UE QQ200 shown in Fig. 12.

[0148] As yet another specific example, in an loT 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-loT standard. In other scenarios, a UE may represent a vehicle, such as a car, a bus, a truck, a ship and an airplane, or other equipment that is capable of monitoring and / or reporting on its operational status or other functions associated with its operation.

[0149] 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.

[0150] Fig. 13 shows a network node, access network node or RAN node QQ300 in accordance with some embodiments. As used herein, access network node or RAN network node refers to equipment capable, configured, arranged and / or operable to communicate directly or indirectly with a UE and / or with other RAN network nodes or equipment, or core network nodes, in a telecommunication network. Examples of access network nodes include, but are not limited to, access points (APs) (e.g. radio access points), base stations (BSs) (e.g. radio base stations, Node Bs, evolved Node Bs (eNBs) and NR NodeBs (gNBs)), Open-RAN (O-RAN) nodes or components of an O-RAN node (e.g., O-RU, O-DU, O-CU).

[0151] 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 a relay. A network node may also include one or more (or all) parts of a distributed radio base station 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 remote radio units 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).

[0152] 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 base station 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).

[0153] The RAN network node QQ300 includes a processing circuitry QQ302, a memory QQ304, a communication interface QQ306, and a power source QQ308. The RAN network node QQ300 may be composed of multiple physically separate components (e.g., a NodeB component and a 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 RAN network node QQ300 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 RAN network node QQ300 may be configured to support multiple radio access technologies (RATs). In such embodiments, some components may be duplicated (e.g., separate memory QQ304 for different RATs) and some components may be reused (e.g., a same antenna QQ310 may be shared by different RATs). The RAN network node QQ300 may also include multiple sets of the various illustrated components for different wireless technologies integrated into network node QQ300, for example GSM, WCDMA, LTE, NR, WiFi, Zigbee, Z-wave, 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 RAN network node QQ300.

[0154] The processing circuitry QQ302 may comprise a combination of one or more of a microprocessor, controller, microcontroller, central processing unit, digital signal processor, application-specific integrated circuit, field programmable gate array, 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 QQ300 components, such as the memory QQ304, to provide RAN network node QQ300 functionality. For example, the processing circuitry QQ302 may be configured to cause the RAN network node to perform the methods as described herein, such as method 1000.

[0155] In some embodiments, the processing circuitry QQ302 includes a system on a chip (SOC). In some embodiments, the processing circuitry QQ302 includes one or more of radio frequency (RF) transceiver circuitry QQ312 and baseband processing circuitry QQ314. In some embodiments, the radio frequency (RF) transceiver circuitry QQ312 and the baseband processing circuitry QQ314 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 RF transceiver circuitry QQ312 and baseband processing circuitry QQ314 may be on the same chip or set of chips, boards, or units.

[0156] The memory QQ304 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, random access memory (RAM), read-only memory (ROM), mass storage media (for example, a hard disk), removable storage media (for example, a flash drive, a Compact Disk (CD) or a Digital Video Disk (DVD)), and / or any other volatile or non-volatile, non-transitory device-readable and / or computer-executable memory devices that store information, data, and / or instructions that may be used by the processing circuitry QQ302. The memory QQ304 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 QQ302 and utilized by the RAN node QQ300. The memory QQ304 may be used to store any calculations made by the processing circuitry QQ302 and / or any data received via the communication interface QQ306. In some embodiments, the processing circuitry QQ302 and memory QQ304 is integrated.

[0157] The communication interface QQ306 is used in wired or wireless communication of signalling and / or data between network nodes, the access network, the core network, and / or UE. As illustrated, the communication interface QQ306 comprises port(s) / terminal(s) QQ316 to send and receive data, for example to and from a network over a wired connection. The communication interface QQ306 also includes radio front-end circuitry QQ318 that may be coupled to, or in certain embodiments a part of, the antenna QQ310. Radio front-end circuitry QQ318 comprises filters QQ320 and amplifiers QQ322. The radio front-end circuitry QQ318 may be connected to an antenna QQ310 and processing circuitry QQ302. The radio front-end circuitry may be configured to condition signals communicated between antenna QQ310 and processing circuitry QQ302. The radio front-end circuitry QQ318 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 QQ318 may convert the digital data into a radio signal having the appropriate channel and bandwidth parameters using a combination of filters QQ320 and / or amplifiers QQ322. The radio signal may then be transmitted via the antenna QQ310. Similarly, when receiving data, the antenna QQ310 may collect radio signals which are then converted into digital data by the radio front-end circuitry QQ318. The digital data may be passed to the processing circuitry QQ302. In other embodiments, the communication interface may comprise different components and / or different combinations of components.

[0158] In certain alternative embodiments, the RAN node QQ300 does not include separate radio front-end circuitry QQ318, instead, the processing circuitry QQ302 includes radio front-end circuitry and is connected to the antenna QQ310. Similarly, in some embodiments, all or some of the RF transceiver circuitry QQ312 is part of the communication interface QQ306. In still other embodiments, the communication interface QQ306 includes one or more ports or terminals QQ316, the radio front-end circuitry QQ318, and the RF transceiver circuitry QQ312, as part of a radio unit (not shown), and the communication interface QQ306 communicates with the baseband processing circuitry QQ314, which is part of a digital unit (not shown).

[0159] The antenna QQ310 may include one or more antennas, or antenna arrays, configured to send and / or receive wireless signals. The antenna QQ310 may be coupled to the radio front-end circuitry QQ318 and may be any type of antenna capable of transmitting and receiving data and / or signals wirelessly. In certain embodiments, the antenna QQ310 is separate from the network node QQ300 and connectable to the network node QQ300 through an interface or port.

[0160] The antenna QQ310, communication interface QQ306, and / or the processing circuitry QQ302 may be configured to perform any receiving operations and / or certain obtaining operations described herein as being performed by the network node. Any information, data and / or signals may be received from a UE, another network node and / or any other network equipment. Similarly, the antenna QQ310, the communication interface QQ306, and / or the processing circuitry QQ302 may be configured to perform any transmitting operations described herein as being performed by the network node. Any information, data and / or signals may be transmitted to a UE, another network node and / or any other network equipment.

[0161] The power source QQ308 provides power to the various components of network node QQ300 in a form suitable for the respective components (e.g., at a voltage and current level needed for each respective component). The power source QQ308 may further comprise, or be coupled to, power management circuitry to supply the components of the network node QQ300 with power for performing the functionality described herein. For example, the network node QQ300 may be connectable to an external power source (e.g., the power grid, an electricity outlet) via an input circuitry or interface such as an electrical cable, whereby the external power source supplies power to power circuitry of the power source QQ308. As a further example, the power source QQ308 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.

[0162] Embodiments of the network node QQ300 may include additional components beyond those shown in Fig. 13 for providing certain aspects of the network node’s functionality, including any of the functionality described herein and / or any functionality necessary to support the subject matter described herein. For example, the network node QQ300 may include user interface equipment to allow input of information into the network node QQ300 and to allow output of information from the network node QQ300. This may allow a user to perform diagnostic, maintenance, repair, and other administrative functions for the network node QQ300. In some embodiments providing a core network node, such as core network node 108 of Fig. QQ1, some components, such as the radio front-end circuitry QQ318 and the RF transceiver circuitry QQ312 may be omitted.

[0163] Fig. 14 is a block diagram illustrating a virtualization environment QQ400 in which functions 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 virtual environments QQ400 hosted by one or more of hardware nodes, such as a hardware computing device that operates as a network node, access network node, RAN node, UE, core network node, or 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 QQ400 includes components defined by the O-RAN Alliance, such as an O-Cloud environment orchestrated by a Service Management and Orchestration Framework via an 0-2 interface. Virtualization may facilitate distributed implementations of an access network node, network node, RAN node, UE, core network node, or host.

[0164] Applications QQ402 (which may alternatively be called software instances, virtual appliances, network functions, virtual nodes, virtual network functions, etc.) are run in the virtualization environment QQ400 to implement some of the features, functions, and / or benefits of some of the embodiments disclosed herein.

[0165] Hardware QQ404 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, input / output interface, and so forth. Software may be executed by the processing circuitry to instantiate one or more virtualization layers QQ406 (also referred to as hypervisors or virtual machine monitors (VMMs)), provide VMs QQ408a and QQ408b (one or more of which may be generally referred to as VMs QQ408), and / or perform any of the functions, features and / or benefits described in relation with some embodiments described herein. The virtualization layer QQ406 may present a virtual operating platform that appears like networking hardware to the VMs QQ408.

[0166] The VMs QQ408 comprise virtual processing, virtual memory, virtual networking or interface and virtual storage, and may be run by a corresponding virtualization layer QQ406. Different embodiments of the instance of a virtual appliance QQ402 may be implemented on one or more of VMs QQ408, 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.

[0167] In the context of NFV, a VM QQ408 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 QQ408, and that part of hardware QQ404 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 QQ408 on top of the hardware QQ404 and corresponds to the application QQ402.

[0168] Hardware QQ404 may be implemented in a standalone network node with generic or specific components. Hardware QQ404 may implement some functions via virtualization. Alternatively, hardware QQ404 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 QQ410, which, among others, oversees lifecycle management of applications QQ402. In some embodiments, hardware QQ404 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 signalling can be provided with the use of a control system QQ412 which may alternatively be used for communication between hardware nodes and radio units.

[0169] 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 may be configured to include any of the components described herein, and / or the functionality of the components 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.

[0170] 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.

[0171] The foregoing merely illustrates the principles of the disclosure. Various modifications and alterations to the described embodiments will be apparent to those skilled in the art in view of the teachings herein. It will thus be appreciated that those skilled in the art will be able to devise numerous systems, arrangements, and procedures that, although not explicitly shown or described herein, embody the principles of the disclosure and can be thus within the scope of the disclosure. Various exemplary embodiments can be used together with one another, as well as interchangeably therewith, as should be understood by those having ordinary skill in the art.

[0172] The following statements outline some exemplary features of the techniques presented in this disclosure:

[0173] A1. A method at one UE for indicating either explicitly or implicitly to one network that data collection is needed for training at the UE. The indication explicitly or implicitly includes one or more of the following pieces of information

[0174] o request to the NW to allow starting data collection for training or for training of at least one functionality;

[0175] o information that the UE does not have an applicable model or an applicable functionality in terms of at least one of given network and gNB condition and configuration and scenario;

[0176] o information about data collection for training of one functionality in terms of at least one of network and gNB condition and configuration and scenario; o RRC mode(s) used for the data collection.

[0177] A2. A method according to A1, wherein the configuration indicated by the UE may also include one or more radio resources or configuration(s) that need(s) to be configured at the UE to allow to train the UE-side.

[0178] A3. A method according to A1, wherein the UE indicates its preference of when to stop the training phase using one or a combination of the following methods:

[0179] • using an estimated training duration before the training phase starts

[0180] • by identifying, during the training phase, when it is trained enough using a measure to quantify the quality of the trained model, and then signalling to the network that it can stop the training phase

[0181] • by indicating the size of the dataset to be collected for training

[0182] • using an estimated data collection time duration before the collection phase starts

[0183] • by identifying, during the data collection phase, when the collected data is enough, and then signalling to the network that it can stop the data collection phase

[0184] A4. A method wherein the UE receives L1 / L2 signalling from the network, to trigger data collection for training and stop data collection for training.

[0185] A5. A method wherein the UE sends to the network an acknowledgement that it can start data collection for training, as a response to a network request.

[0186] A6. A method of A1 , wherein the UE may explicitly or implicitly indicate the network that the UE will move from RRC_connected mode to another RRC mode (e.g. RRCJdle mode, RRCJnactive mode) for data collection for training, and this information indication may be a response to a network request.

[0187] A7. A method of A1, wherein the UE may move back from the RRC mode (e.g. RRCJdle mode, RRCJnactive mode) to RRC_connected mode when the data collection stops or temporally stops.

[0188] A8. A method of A7, wherein the UE may receive the indication from the network, where the indication explicitly or implicitly include the information of the stop of the data collection or the temporal stop of the data collection.

[0189] A9. A method of A8, wherein the UE may report its capability about supported RRC mode(s) for data collection for training purpose.

[0190] B1. A method at a network node to decide that data collection is needed by a UE for training (or re-training or fine-tuning) an AI / ML model / functionality, wherein: (i) the NW receives and explicit training request from the UE; or (ii) the NW receives an indication from the UE that an AI / ML model is not applicable for a given configuration / condition and NW implicitly finds that training for the given configurations / condition is needed; or (iii) the NW detects on its own based on performance monitoring that the performance is degraded and training is needed for the given configuration / condition.

[0191] B2. A method according to B1, wherein a command and / or message / information is sent to the UE to allow the UE to (re)train an AI / ML model / functionality.

[0192] B3. A method according to B2, wherein the network uses the UE’s preference of when to stop the training phase, using one or a combination of the following methods:

[0193] • using an estimated training duration that the UE signalled before the training phase started

[0194] • by receiving an indication from the UE, during the training phase, where the UE signals that it is trained enough

[0195] • by receiving from the UE an indication about the size of the dataset to be collected for training.

[0196] B4. A method according to B3, wherein the network triggers data collection for training and stops data collection fortraining using L1 / L2 signalling.

[0197] B5. A method wherein the message from the NW to trigger data collection can contain a configuration of the data collection resources and / or a request to the UE to acknowledge that it can start data collection for training. EMBODIMENTS

[0198] Group A Embodiments

[0199] 1. A method performed by a user equipment, UE, that is configured to train and use a machine learning, ML, model, the method comprising one or more of:

[0200] sending, to a radio access network, RAN, node, in a network, an indication of a capability of the UE to train and use the ML model;

[0201] in response to receiving, from a RAN node, a request as to whether the ML model is applicable to a particular configuration, condition, or scenario of the RAN node or the network, sending, to the RAN node, an indication of whether the ML model is applicable to the particular configuration, condition, or scenario; and

[0202] sending, to the RAN node, an indication that the UE is ready to acquire data for training the ML model.

[0203] 2. The method of embodiment 1 , wherein the indication of the capability of the UE to train and use the ML model is sent in response to receiving a capability enquiry from the RAN node.

[0204] 3. The method of embodiment 1 or 2, wherein the indication that the UE is ready to acquire data for training the ML model is sent in response to receiving, from the RAN node, a request for the UE to indicate whether the UE is ready to acquire data for training the ML model.

[0205] 4. The method of any of embodiments 1-3, wherein the indication of whether the ML model is applicable to the particular configuration, condition or scenario further comprises an indication of whether the UE wants to train the ML model for the particular configuration, condition or scenario.

[0206] 5. The method of any of embodiments 1-3, wherein the method further comprises:

[0207] sending, to the RAN node, an indication of whether the ML model is to be trained for the particular configuration, condition or scenario.

[0208] 6. The method of embodiment 4 or 5, wherein the indication of whether the ML model is to be trained for the particular configuration, condition or scenario comprises a value for a one-bit flag.

[0209] 7. The method of any of embodiments 4-6, wherein the UE can indicate that the ML model is not applicable for the particular configuration, condition or scenario, and indicate whether the ML model is to be trained for the particular configuration, condition or scenario.

[0210] 8. The method of any of embodiments 1-7, wherein the method further comprises: acquiring data for training the ML model; and

[0211] training the ML model.

[0212] 9. The method of embodiment 8, wherein the data for training the ML model is acquired when the UE is in an inactive or idle mode.

[0213] 10. The method of any of embodiments 1-9, wherein the method further comprises:

[0214] sending, to the RAN node, an indication of one or more radio resources and / or configurations to be configured to enable the UE to train the ML model for the particular configuration, condition or scenario.

[0215] 11. The method of any of embodiments 1-10, wherein the indication that the UE is ready to acquire data for training the ML model is an indication that acquisition of the data for training the ML model is to start.

[0216] 12. The method of any of embodiments 1-11, wherein the method further comprises:

[0217] sending, to the RAN node, an indication of when acquisition of data fortraining of the ML model is to stop.

[0218] 13. The method of embodiment 12, wherein the indication of when acquisition of data for training of the ML model is to stop comprises any one or more of:

[0219] a duration of a data acquisition session;

[0220] an end time of the data acquisition session;

[0221] an amount of data to be acquired during the data acquisition session;

[0222] an indication that enough data has been acquired; and / or

[0223] an indication that the network node can stop the data acquisition session.

[0224] 14. The method of any of embodiments 1-13, wherein the method further comprises:

[0225] sending, to the RAN node, an indication of which modes the UE is able to use to acquire data for training the ML model.

[0226] 15. The method of embodiment 14, wherein the modes are Radio Resource Control (RRC) modes.

[0227] 16. The method of any of embodiments 14 or 15, wherein the modes comprise an idle and / or inactive mode. 17. The method of any of embodiments 1-16, wherein the indications are sent to the RAN node and / or received from the RAN node in any one or more of: Medium Access Control, MAC, signalling; Radio Resource Control, RRC, signalling; Layer 1, L1, signalling, for example signalling within a Channel State Information, CSI, framework; and Layer 2, L2, signalling.

[0228] 18. The method of any of embodiments 1-17, wherein the ML model is for predicting a first property of one or more first beams in a first set of beams based on a second property of one or more second beams in a second set of beams.

[0229] Group B Embodiments

[0230] 19. A method performed by a radio access network, RAN, node in a network with a user equipment, UE, the method comprising one or more of:

[0231] determining, based on performance monitoring, that the UE requires data for training a machine learning, ML, model of the UE;

[0232] receiving, from the UE, an indication of a capability of the UE to train and use the ML model; in response to a request as to whether the ML model is applicable to a particular configuration, condition, or scenario of the RAN node or the network, receiving, from the UE, an indication of whether the ML model is applicable to the particular configuration, condition or scenario; and

[0233] receiving, from the UE, an indication that the UE is ready to acquire data for training the ML model.

[0234] 20. The method of embodiment 19, wherein the indication of the capability of the UE to train and use the ML model is received in response to sending a capability enquiry to the UE.

[0235] 21. The method of embodiment 19 or 20, wherein the indication that the UE is ready to acquire data for training the ML model is received in response to sending, to the UE, a request for the UE to indicate whether the UE is ready to acquire data for training the ML model.

[0236] 22. The method of any of embodiments 19-21, wherein the indication of whether the ML model is applicable to the particular configuration, condition or scenario further comprises an indication of whether the UE wants to train the ML model for the particular configuration, condition or scenario.

[0237] 23. The method of any of embodiments 19-21, wherein the method further comprises: receiving, from the UE, an indication of whether the ML model is to be trained for the particular configuration, condition or scenario.

[0238] 24. The method of embodiment 22 or 23, wherein the indication of whether the ML model is to be trained for the particular configuration, condition or scenario comprises a value for a one-bit flag.

[0239] 25. The method of any of embodiments 22-24, wherein the UE can indicate that the ML model is not applicable for the particular configuration, condition or scenario, and indicate whether the ML model is to be trained for the particular configuration, condition or scenario.

[0240] 26. The method of any of embodiments 19-25, wherein the method further comprises:

[0241] receiving, from the UE, an indication of one or more radio resources and / or configurations to be configured to enable the UE to train the ML model for the particular configuration, condition or scenario.

[0242] 27. The method of any of embodiments 19-26, wherein the indication that the UE is ready to acquire data for training the ML model is an indication that acquisition of the data for training the ML model is to start.

[0243] 28. The method of any of embodiments 19-27, wherein the method further comprises:

[0244] receiving, from the UE, an indication of when acquisition of data for training of the ML model is to stop.

[0245] 29. The method of embodiment 28, wherein the indication of when acquisition of data for training of the ML model is to stop comprises any one or more of:

[0246] a duration of a data acquisition session;

[0247] an end time of the data acquisition session;

[0248] an amount of data to be acquired during the data acquisition session;

[0249] an indication that enough data has been acquired; and / or

[0250] an indication that the network node can stop the data acquisition session.

[0251] 30. The method of any of embodiments 19-31, wherein the method further comprises:

[0252] receiving, from the UE, an indication of which modes the UE is able to use to acquire data for training the ML model. 31. The method of embodiment 30, wherein the modes are Radio Resource Control, RRC, modes.

[0253] 32. The method of any of embodiments 30 or 31 , wherein the modes comprise an idle and / or inactive mode.

[0254] 33. The method of any of embodiments 19-32, wherein the indications are received from the UE and / or sent to the UE in any one or more of: Medium Access Control, MAC, signalling; Radio Resource Control, RRC, signalling; Layer 1, L1, signalling; and Layer 2, L2, signalling.

[0255] 34. The method of any of embodiments 19-33, wherein the ML model is for predicting a first property of one or more first beams in a first set of beams based on a second property of one or more second beams in a second set of beams.

[0256] Group C Embodiments

[0257] 35. A computer program product comprising a computer readable medium having computer readable code embodied therein, the computer readable code being configured such that, on execution by a suitable computer or processor, the computer or processor is caused to perform the method of any of the Group A embodiments and the Group B embodiments.

[0258] 36. A user equipment, UE, configured to perform the method of any of the Group A embodiments.

[0259] 37. A user equipment, UE, comprising a processor and a memory, said memory containing instructions executable by said processor whereby said UE is operative to perform the method of any of the Group A embodiments.

[0260] 38. A radio access network, RAN, node, configured to perform the method of any of the Group B embodiments.

[0261] 39. A radio access network, RAN, node comprising a processor and a memory, said memory containing instructions executable by said processor whereby said RAN node is operative to perform the method of any of the Group B embodiments.

[0262] 40. A user equipment, UE, comprising:

[0263] processing circuitry configured to cause the user equipment to perform any of the steps of any of the Group A embodiments; and power supply circuitry configured to supply power to the processing circuitry.

[0264] 41. A radio access network, RAN, node, comprising:

[0265] processing circuitry configured to cause the RAN node to perform any of the steps of any of the Group B embodiments;

[0266] power supply circuitry configured to supply power to the processing circuitry.

[0267] 42. A user equipment, UE, comprising:

[0268] an antenna configured to send and receive wireless signals;

[0269] radio front-end circuitry connected to the antenna and to processing circuitry, and configured to condition signals communicated between the antenna and the processing circuitry;

[0270] the processing circuitry being configured to perform any of the steps of any of the Group A embodiments;

[0271] an input interface connected to the processing circuitry and configured to allow input of information into the UE to be processed by the processing circuitry;

[0272] an output interface connected to the processing circuitry and configured to output information from the UE that has been processed by the processing circuitry; and

[0273] a battery connected to the processing circuitry and configured to supply power to the UE.

Claims

CLAIMS1. A method (900) performed by a user equipment, UE, that is configured to train and use a machine learning, ML, model, the method comprising one or more of:Sending (910), to a radio access network, RAN, node, in a network, an indication of a capability of the UE to train and use the ML model;in response to receiving, from the RAN node, a request as to whether the ML model is applicable to a particular configuration, condition, or scenario of the RAN node or the network, sending (920), to the RAN node, an indication of whether the ML model is applicable to the particular configuration, condition, or scenario; andsending (930), to the RAN node, an indication that the UE is ready to acquire data for training the ML model.

2. The method (900) of claim 1 , wherein the indication of the capability of the UE to train and use the ML model is sent in response to receiving a capability enquiry from the RAN node.

3. The method (900) of claim 1 or 2, wherein the indication that the UE is ready to acquire data for training the ML model is sent in response to receiving, from the RAN node, a request for the UE to indicate whether the UE is ready to acquire data for training the ML model.

4. The method (900) of any of claims 1-3, wherein the indication of whether the ML model is applicable to the particular configuration, condition or scenario further comprises an indication of whether the UE requests to train the ML model for the particular configuration, condition or scenario.

5. The method (900) of any of claims 1-3, wherein the method further comprises:sending, to the RAN node, an indication of whether the ML model is to be trained for the particular configuration, condition or scenario.

6. The method (900) of claims 4 or 5, wherein the indication of whether the ML model is to be trained for the particular configuration, condition or scenario comprises a value for a one-bit flag.

7. The method (900) of any of claims 4-6, wherein the UE indicates that the ML model is not applicable for the particular configuration, condition or scenario, and indicates whether the ML model is to be trained for the particular configuration, condition or scenario.

8. The method (900) of any of claims 1-7, wherein the method further comprises:acquiring data for training the ML model; andtraining the ML model.

9. The method (900) of claim 8, wherein the data for training the ML model is acquired when the UE is in an inactive mode or idle mode.

10. The method (900) of any of claims 1-9, wherein the method further comprises:sending, to the RAN node, an indication of one or more radio resources and / or configurations to be configured to enable the UE to train the ML model for the particular configuration, condition or scenario.

11. The method (900) of any of claims 1-10, wherein the indication that the UE is ready to acquire data for training the ML model is an indication that acquisition of the data for training the ML model is to start.

12. The method (900) of any of claims 1-11, wherein the method further comprises:sending, to the RAN node, an indication of when acquisition of data fortraining of the ML model is to stop.

13. The method (900) of claims 12, wherein the indication of when acquisition of data for training of the ML model is to stop comprises any one or more of:a duration of a data acquisition session;an end time of the data acquisition session;an amount of data to be acquired during the data acquisition session;an indication that enough data has been acquired; and / oran indication that the network node can stop the data acquisition session.

14. The method (900) of any of claims 1-13, wherein the method further comprises:sending, to the RAN node, an indication of which modes the UE is configured to acquire data for training the ML model.

15. The method (900) of claim 14, wherein the modes are Radio Resource Control (RRC) modes.

16. The method (900) of any of claims 14 or 15, wherein the modes comprise an idle mode and / or inactive mode.

17. The method (900) of any of claims 1-16, wherein the indications are sent to the RAN node and / or received from the RAN node in any one or more of: Medium Access Control, MAC, signalling; Radio Resource Control, RRC, signalling; Layer 1, L1, signalling, for example signalling within a Channel State Information, CSI, framework; and Layer 2, L2, signalling.

18. The method (900) of any of claims 1-17, wherein the ML model is for predicting a first property of one or more first beams in a first set of beams based on a second property of one or more second beams in a second set of beams.

19. A method (1000) performed by a radio access network, RAN, node in a network with a user equipment, UE, the method comprising one or more of:Determining (1010), based on performance monitoring, that the UE requires data for training a machine learning, ML, model of the UE;Receiving (1020), from the UE, an indication of a capability of the UE to train and use the ML model;in response to a request as to whether the ML model is applicable to a particular configuration, condition, or scenario of the RAN node or the network, receiving (1030), from the UE, an indication of whether the ML model is applicable to the particular configuration, condition or scenario; andreceiving (1040), from the UE, an indication that the UE is ready to acquire data for training the ML model.

20. The method (1000) of claim 19, wherein the indication of the capability of the UE to train and use the ML model is received in response to sending a capability enquiry to the UE.

21. The method (1000) of claim 19 or 20, wherein the indication that the UE is ready to acquire data for training the ML model is received in response to sending, to the UE, a request for the UE to indicate whether the UE is ready to acquire data for training the ML model.

22. The method (1000) of any of claims 19-21, wherein the indication of whether the ML model is applicable to the particular configuration, condition or scenario further comprises an indication of whether the UE requests to train the ML model for the particular configuration, condition or scenario.

23. The method (1000) of any of claims 19-21, wherein the method further comprises:receiving, from the UE, an indication of whether the ML model is to be trained for the particular configuration, condition or scenario.

24. The method (1000) of claims 22 or 23, wherein the indication of whether the ML model is to be trained for the particular configuration, condition or scenario comprises a value for a one-bit flag.

25. The method (1000) of any of claims 22-24, wherein the UE indicates that the ML model is not applicable for the particular configuration, condition or scenario, and indicates whether the ML model is to be trained for the particular configuration, condition or scenario.

26. The method (1000) of any of claims 19-25, wherein the method further comprises:receiving, from the UE, an indication of one or more radio resources and / or configurations to be configured to enable the UE to train the ML model for the particular configuration, condition or scenario.

27. The method (1000) of any of claims 19-26, wherein the indication that the UE is ready to acquire data for training the ML model is an indication that acquisition of the data for training the ML model is to start.

28. The method (1000) of any of claims 19-27, wherein the method further comprises:receiving, from the UE, an indication of when acquisition of data for training of the ML model is to stop.

29. The method (1000) of claims 28, wherein the indication of when acquisition of data for training of the ML model is to stop comprises any one or more of:a duration of a data acquisition session;an end time of the data acquisition session;an amount of data to be acquired during the data acquisition session;an indication that enough data has been acquired; and / oran indication that the network node can stop the data acquisition session.

30. The method (1000) of any of claims 19-31, wherein the method further comprises:receiving, from the UE, an indication of which modes the UE is able to use to acquire data for training the ML model.

31. The method (1000) of claims 30, wherein the modes are Radio Resource Control, RRC, modes.

32. The method (1000) of any of claims 30 or 31, wherein the modes comprise an idle mode and / or inactive mode.

33. The method (1000) of any of claims 19-32, wherein the indications are received from the UE and / or sent to the UE in any one or more of: Medium Access Control, MAC, signalling; Radio Resource Control, RRC, signalling; Layer 1, L1, signalling; and Layer 2, L2, signalling.

34. The method (1000) of any of claims 19-33, wherein the ML model is for predicting a first property of one or more first beams in a first set of beams based on a second property of one or more second beams in a second set of beams.

35. A computer program product comprising a computer readable medium having computer readable code embodied therein, the computer readable code being configured such that, on execution by a suitable computer or processor, the computer or processor is caused to perform the method (900) of any of claims 1 to 18 and the method (1000) of any of claims 19-34.

36. A user equipment, UE, configured to perform one or more of:send, to a radio access network, RAN, node, in a network, an indication of a capability of the UE to train and use the ML model;in response to receive, from a RAN node, a request as to whether the ML model is applicable to a particular configuration, condition, or scenario of the RAN node or the network, send, to the RAN node, an indication of whether the ML model is applicable to the particular configuration, condition, or scenario; andsend, to the RAN node, an indication that the UE is ready to acquire data for training the ML model.

37. The UE of claim 36, further configured to perform the method of any of claims 2-18.

38. A user equipment, UE, comprising a processor and a memory, said memory containing instructions executable by said processor whereby said UE is operative to perform the method (900) of any of claims 1-18.

39. A radio access network, RAN, node, configured to perform one or more of:determine, based on performance monitoring, that the UE requires data for training a machine learning, ML, model of the UE;receive, from the UE, an indication of a capability of the UE to train and use the ML model; in response to a request as to whether the ML model is applicable to a particular configuration, condition, or scenario of the RAN node or the network, receive, from the UE, anindication of whether the ML model is applicable to the particular configuration, condition or scenario; andreceive, from the UE, an indication that the UE is ready to acquire data for training the ML model.

40. The RAN node of claim 39, further configured to perform the method of any of claims 20-34.

41. A radio access network, RAN, node comprising a processor and a memory, said memory containing instructions executable by said processor whereby said RAN node is operative to perform the method (1000) of any of the claims 19-34.

42. A user equipment, UE, comprising:processing circuitry configured to cause the user equipment to perform any of the steps of any of the claims 1-18; andpower supply circuitry configured to supply power to the processing circuitry.

43. A radio access network, RAN, node, comprising:processing circuitry configured to cause the RAN node to perform any of the steps of any of the claims 19-34;power supply circuitry configured to supply power to the processing circuitry.

44. A user equipment, UE, comprising:an antenna configured to send and receive wireless signals;radio front-end circuitry connected to the antenna and to processing circuitry, and configured to condition signals communicated between the antenna and the processing circuitry;the processing circuitry being configured to perform any of the steps of any of the claims 1-18;an input interface connected to the processing circuitry and configured 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 information from the UE that has been processed by the processing circuitry; anda battery connected to the processing circuitry and configured to supply power to the UE.

Images