Managing data collection

Abstract

The present disclosure provides a method performed by a user equipment (UE) for managing data collection. The method comprises performing one or more actions to control a data collection session at the user equipment when one or more conditions are fulfilled. The data collection session is a session in which data is collected for an artificial intelligence or machine learning (AI / ML) model.

Description

MANAGING DATA COLLECTIONTECHNICAL FIELD

[0001] The present disclosure relates to methods for managing data collection, and a user equipment and network node configured to perform those methods.BACKGROUND

[0002] Artificial Intelligence (Al) and Machine Learning (ML) have been investigated, both in academia and industry, as promising tools to optimize the design of the air-interface in wireless communication networks. Example use cases include using autoencoders for Channel State Information (CSI) compression to reduce the feedback overhead and improve channel prediction accuracy; using deep neural networks for classifying Line-of-Sight (LOS) and Non- LOS (NLOS) conditions to enhance the positioning accuracy; and using reinforcement learning for beam selection at the network (NW) side and / or the User Equipment (UE) side to reduce the signalling overhead and beam alignment latency; using deep reinforcement learning to learn an optimal precoding policy for complex Multiple Input Multiple Output (MIMO) precoding problems.

[0003] In Third Generation Partnership Project (3GPP) New Radio (NR) standardization work, a new Release 18 (Rel-18) study item on Al or ML (AI / ML) for the NR air interface started in May 2022. This study item will explore 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 study item aims at laying the foundation for future air-interface use cases leveraging AI / ML techniques.

[0004] The analysis carried out during the Rel-18 is now considered in the context of Release 19 (Rel-19). Additionally, during the Rel-19, a new study item addressing AI / ML for mobility has been approved. In the context of this new study item, 3GPP will investigate methods for cell-level measurement predictions, and mobility event predictions. These mobility event predictions can, for example, comprise Radio Link Failure (RLF), handover failure (HOF), mobility -related events predictions such as A3 (neighbour becomes offset better than special cell (SpCell)) or A5 (SpCell becomes worse than threshold! and neighbour becomes better than threshold2), etc.

[0005] Data collection is a useful tool that allows the training entity to generate a modelsuitable for a specific device. In particular, related to the case of AI / ML applied to Radio Access Network (RAN) use cases (e.g. beam management, positioning accuracy enhancements, cell or frequency level measurement predictions, mobility event predictions, etc.), the AI / ML model may be UE-sided (e.g. tailored for specific UEs) or NW-sided (e.g. tailored for specific network nodes, such as specific NR Node Bs (gNBs). In order for RAN schemes based on AI / ML models to outperform conventional non-AI / ML based schemes, the device (UE or network node (e.g. gNB) in this case) may collect data so that the training entity can generate a model suitable for the device inference. Otherwise, if the collected data set during the training does not match the inputs during the inference, then it is proven that AI / ML may not provide the expected benefits.

[0006] There currently exist certain challenge(s). The capability of a UE to collect data is an important feature for AI / ML model training. However, this comes at the expense of the UE memory consumption, which is limited.SUMMARY

[0007] As mentioned earlier, while the capability of a UE to collect data is an important feature for AI / ML model training, this comes at the expense of the UE memory consumption. Certain aspects of the disclosure and their embodiments may provide solutions to these or other challenges.

[0008] Accordingly, in one aspect, there is provided a first method performed by a user equipment (UE) for managing data collection. The first method comprises performing one or more actions to control a data collection session at the user equipment when one or more conditions are fulfilled. The data collection session is a session in which data is collected for an artificial intelligence or machine learning (AI / ML) model.

[0009] In another aspect, there is provided a UE comprising processing circuitry configured to cause the UE to perform one or more actions to control a data collection session at the user equipment when one or more conditions are fulfilled. The data collection session is a session in which data is collected for an AI / ML model.

[0010] In another aspect, there is provided a computer program comprising instructions which, when executed by processing circuitry of a UE, cause the UE to perform the first method.

[0011] In another aspect, there is provided a computer program product, embodied on a non-transitory machine-readable medium, comprising instructions which are executable by processing circuitry of a UE to cause the UE to perform the first method.BRIEF DESCRIPTION OF THE DRAWINGS

[0012] For a beter 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, in which:

[0013] Fig. 1 is a flow chart illustrating a method in accordance with some embodiments;

[0014] Fig. 2 shows an example of a communication system in accordance with some embodiments;

[0015] Fig. 3 shows a UE in accordance with some embodiments;

[0016] Fig. 4 shows a network node in accordance with some embodiments; and

[0017] Fig. 5 is a block diagram illustrating a virtualization environment in which functions implemented by some embodiments may be virtualized.DETAILED DESCRIPTION

[0018] 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 mater to those skilled in the art.

[0019] Generally, all terms used herein are to be interpreted according to their ordinary meaning in the relevant technical field, unless a different meaning is clearly given and / or is implied from the context in which it is used. All references to a / an / the element, apparatus, component, means, step, etc. are to be interpreted openly as referring to at least one instance of the element, apparatus, component, means, step, etc., unless explicitly stated otherwise. The steps of any methods disclosed herein do not have to be performed in the exact order disclosed, unless a step is explicitly described as following or preceding another step and / or where it is implicit that a step must follow or precede another step. Any feature of any of the embodiments disclosed herein may be applied to any other embodiment, wherever appropriate. Likewise, any advantage of any of the embodiments may apply to any other embodiments, and vice versa.

[0020] Other objectives, features and advantages of the enclosed embodiments will be apparent from the following description.

[0021] As described earlier, data collection is a useful tool that allows the training entity to generate a model suitable for a specific device. The AI / ML model may be UE-sided (e.g. tailored for specific UEs) or NW-sided (e.g. tailored for specific network nodes, such as specific NR Node Bs (gNBs).

[0022] Related to NW-side models, it has been assumed so far in 3GPP that the network node (e.g. gNB) and / or the Operation Administration and Maintenance (0AM) node can be in charge of collecting data from the radio access network (RAN) for the purpose of NW-side model training. If the network node (e.g. gNB) is responsible, it is assumed that the network node may configure the UE with a set of resources (e.g. Channel State Information Reference Signal (CSI-RS) resources or Synchronization Signal Block (SSB) resource sets) in which the UE is to collect measurements, such as for a certain amount of time. Then, the UE can report what it has measured to the network node (e.g. gNB), such as via Radio Resource Control (RRC) signalling. Then, the training can be performed in the network node (e.g. gNB) itself, or in another node controlled by the network node (e.g. gNB) vendor such as an Over-the-Top (OTT) server handled by the network node vendor.

[0023] A similar approach can apply for the case in which the 0AM does the NW-side training. In this case, the 0AM may request the network node (e.g. gNB) to provide to the UE a certain configuration according to which the UE is to perform certain measurements, and collect data. Once the data collection is completed, the UE can transfer the collected data to the 0AM, e.g. using the Minimization of Drive Tests (MDT) framework such as the immediate MDT or the logged MDT.

[0024] In particular, in RAN2, the benefit of allowing the UE to log the data intended for the NW-side model training has been discussed. Since this type of data does not have any stringent latency requirement, it is beneficial for the UE and for the network (e.g. in terms of UE power consumption, or spectral efficiency) if the UE can log the measured data (e.g. the beam, cell, and / or frequency level qualities), and transmit that data at a later point in time, rather than transmitting the data immediately upon performing the corresponding measurement (as it is, for example, for conventional Layer 1 (LI) measurements, which are transmitted on Uplink Control Information (UCI)). This reduces the power consumed by the UE to continuously access the channel to transmit data that does not have stringent latency requirements, and also reduces the impact on the spectral efficiency, which instead can be used for transmission of data that has a higher priority or more stringent latency requirements.

[0025] In particular, in RAN2#126 meeting, the following has been agreed:Agreements for beam management:• For gNB centric and 0AM centric (for RRC signalling between UE and gNB), reporting multiple instances of logged LI measurement result from UE to gNB via a RRC message as configured by gNB is an optional feature.For Further Study (FFS) how to handle case when single RRC message is not sufficient. FFS if there will be any further enhancement needed pending RANI agreement.• Immediate MDT is the baseline framework for OAM-centric data collection for the training of a network-sided model.• Enhance the immediate MDT framework to support periodical reporting. FFS whether and what event-based reporting is supported and FFS on network request reporting.

[0026] From the above agreements, it turns out that RAN2 has agreed in RAN2# 126 that the UE can support logging of LI measurements (e.g. beam level measurements) and transmit them via RRC signalling, e.g. periodically, or potentially based on events or upon network request. This method can be used both for the network node (e.g. gNB)-centric approach, since the RRC protocol is handled by the network node (e.g. gNB), and for the OAM-centric approach via the immediate MDT framework, since the immediate MDT is based on existing RRC measurement procedures for configuration and reporting with some extensions for location information. The logging of measurements implies that the UE may send this logged data in multiple RRC messages, particularly in case the size of the logged data is larger than the maximum supported size of a Packet Data Convergence Protocol Service Data Unit (PDCP SDU) that conveys the RRC message.

[0027] Immediate MDT (which, as per the above agreements, will be used by RAN2 as a baseline for NW-side data collection) is based on existing RRC measurement procedures for configuration and reporting with some extensions for location information, and the measurement information in NR includes Ml (downlink (DL) signal quantities measurement results for serving cell and for intra-frequency, inter-frequency, and / or inter-Radio Access Technology (RAT) neighbours cells, such as including cell and / or beam level measurement for NR cells only), M2 (power headroom measurement), M4 (PDCP SDU data volume measurement), M5 (average UE throughput measurement), M6 (packet delay measurement), M7 (packet loss rate measurement), M8 (Received Signal Strength Indicator (RS SI) measurement for Wireless Local Area Network (WLAN) and / or Bluetooth measurement) and M9 (Round Trip Time (RTT) measurement for WLAN measurement).

[0028] For Ml, the measurement collection triggers can be event-triggered measurement reports according to the existing Radio Resource Management (RRM) configuration for eventssuch as Al, A2, A3, A4, A5, A6, Bl or B2; or periodic, A2 event-triggered, or A2 event triggered periodic measurement report according to MDT specific measurement configuration. The events Al to A6 can be referred to herein as Ax events. The events Bl to B2 can be referred to herein as Bx events.

[0029] The Ax and Bx events can be defined, as follows:• Event Al : Serving cell becomes better than a threshold• Event A2: Serving cell becomes worse than a threshold• Event A3: Neighbour cell becomes offset better than a SpCell• Event A4: Neighbour cell becomes better than a threshold• Event A5: SpCell becomes worse than a first threshold (thresholdl) and neighbour cell becomes better than a second threshold (threshold2)• Event A6: Neighbour cell becomes offset better than a Secondary Cell (SCell)• Event Bl : Inter RAT neighbour cell becomes better than a threshold• Event B2: Primary Cell (PCell) becomes worse than a first threshold (thresholdl) and inter RAT neighbour cell becomes better than a second threshold (threshold2)

[0030] As mentioned earlier, the capability of a UE to collect data is an important feature for AI / ML model training. However, this comes at the expense of the UE memory consumption, which is limited. The capability of a UE to store or log measurements is an important feature to facilitate data collection for AI / ML model training. However, this also comes at the expense of the UE memory consumption, which is limited.

[0031] Certain aspects of the disclosure and their embodiments may provide solutions to these or other challenges.

[0032] Certain embodiments may provide one or more of the following technical advantage(s). An improved method for a user equipment to manage data collection is provided by allowing a UE to control a session in which the data collection is performed in a certain way when one or more certain conditions are fulfilled. This allows, for example, resources to be conserved and signalling to be reduced. The embodiments disclosed herein can, for example, comprise methods for the UE to handle the UE memory allocated by the UE for storing collected data for the purpose of training an AI / ML model (or AI / ML functionality), and enablethe UE to manage stored measurements during data collection for NW-side model training. The teachings of certain embodiments may improve the data rate, latency, and / or power consumption.

[0033] Fig. 1 depicts a method in accordance with particular embodiments. The method may be performed by a UE or wireless device (e.g. the UE 212 or UE 300 as described later with reference to Figs. 2 and 3 respectively). The method is for managing data collection. The method begins at step 102 with performing one or more actions to control a data collection session at the UE when one or more conditions are fulfilled. The data collection session is a session in which data is collected for an artificial intelligence or machine learning (AI / ML) model.

[0034] It may be that performing the one or more actions to control the data collection session when the one or more conditions are fulfilled comprises starting a first data collection session for a first time when one or more first conditions are fulfilled.

[0035] The one or more first conditions may comprise any one or more of: a condition that a cell level measurement quantity of one or more cells is above or below (e.g. less than or greater than) a threshold, is within a range, or is different from another one or more cells; a condition that a beam level measurement quantity of one or more beams is above or below (e.g. less than or greater than) a threshold, is within a range, or is different from another one or more beams; a condition that the user equipment is at a predefined location; a condition that the user equipment starts a timer; a condition that a mobility event occurs, such as any one or more of Al, A2, A3, A4, A5, A6, Bl, and B2 (e.g. as defined earlier); a condition that the user equipment detects a mobility event, such as a handover failure or a radio link failure; a condition that the user equipment receives, from a network node, an indication to start the first data collection session; and a condition that the user equipment receives, from a network node, a Layer 3 (L3) configuration for the first data collection session. Thus, a method performed by the network node may comprise transmitting, to the UE, one or both of: an indication to start the first data collection session, and an L3 configuration for the first data collection session.

[0036] It may be that performing the one or more actions to control the data collection session when the one or more conditions are fulfilled comprises starting a first data collection session for a subsequent time (i.e. resuming the first data collection) when one or more second conditions are fulfilled. The one or more second conditions may comprise any one or more of: a condition that one or more third conditions for stopping the first data collection session are no longer fulfilled; and a condition that the user equipment receives a request, from a networknode, to start the first data collection session for the subsequent time. Thus, the method performed by the network node may comprise transmitting, to the UE, the request to start the first data collection session for the subsequent time.

[0037] It may be that performing the one or more actions to control the data collection session when the one or more conditions are fulfilled comprises starting a second data collection session when one or more fourth conditions are fulfilled. The second data collection session may be started subsequent to starting a first data collection. The one or more fourth conditions may comprise any one or more of: a condition that the user equipment stops the first data collection session; a condition that the user equipment transmits some or all of the data collected in the first data collection session; a condition that the user equipment receives, from a network node, a request to transmit the data collected in the first data collection session; and a condition that the user equipment discards the data collected in the first data collection session. Thus, the method performed by the network node may comprise transmitting, to the UE, the request to transmit the data collected in the first data collection session.

[0038] It may be that performing the one or more actions to control the data collection session when the one or more conditions are fulfilled comprises stopping the data collection session when one or more third conditions are fulfilled. It may be that stopping the data collection session comprises stopping the data collection session permanently, or stopping the data collection session temporarily (i.e. pausing the data collection session). The one or more third conditions may comprise any one or more of: a condition that the user equipment has reached a maximum storage capacity; a condition that a memory of the user equipment is full; a condition that the user equipment executes or completes a handover; a condition that the user equipment receives a release message; a condition that the user equipment exits an area of interest; a condition that the user equipment fulfils one or more radio conditions; a condition that a data collection timer expires; a condition that a mobility event, such as a handover failure or a radio link failure, is detected; a condition that the user equipment changes a mobility state or speed; and a condition that one or more conditions for starting the data collection session are no longer fulfilled.

[0039] Although not illustrated in Fig. 1, the method may comprise transmitting, to a network node, information signalling (or indicating) that the data collection session has stopped. Thus, the method performed by the network node may comprise receiving, from the UE, information signalling that the data collection session has stopped. The information signalling that the data collection session has stopped may comprise any one or more of: information indicative of the one or more third conditions that are fulfilled; informationindicative of a point in time at which the data collection session stopped; information indicative of the data collected in the data collection session before the data collection session stopped; information indicative of whether or not data collected in the data collection session is available for transmission; and information indicative of a memory status of the user equipment.

[0040] It may be that performing the one or more actions to control the data collection session when the one or more conditions are fulfilled comprises discarding some or all of the data collected in the data collection session when one or more fifth conditions are fulfilled. The data may be discarded from a memory of the user equipment. The one or more fifth conditions may comprise any one or more of: a condition that one or more third conditions for stopping the data collection session are fulfilled; a condition that the user equipment fails to transmit, within a predefined time, the data collected in the data collection session; and a condition that the user equipment receives, from a network node, a request to release a first configuration associated with the data collection session. Thus, the method performed by the network node may comprise transmitting, to the UE, the request to release the first configuration.

[0041] Although not illustrated in Fig. 1, the method may comprise storing the data in a memory of the user equipment according to a first configuration associated with the data collection session.

[0042] Although also not illustrated in Fig. 1, the method may comprise transmitting, to a network node, some or all of the data collected in the data collection session. Thus, the method performed by the network node may comprise receiving, from the UE, some or all of the data collected in the data collection session. The data collected in the data collection session may be transmitted according to a second configuration associated with the data collection session. The second configuration may comprise one or both of: a periodicity for the transmission of some or all of the data collected in the data collection session; and at least one event for triggering the transmission of some or all of the data collected in the data collection session.

[0043] Although not illustrated in Fig. 1, the method may comprise acquiring a first configuration for the data collection session. The first configuration may comprise the one or more conditions. It may be that acquiring the first configuration comprises retrieving the first configuration from a standard specification, or receiving the first configuration from a network node. Thus, the method performed by the network node may comprise transmitting, to the UE, the first configuration. The first configuration may enable the user equipment to store the data collected in the data collection session until the data is transmitted to a network node. The first configuration may be associated with the AI / ML model.

[0044] It may be that, for each of the one or more conditions, the first configuration for the data collection session comprises an associated second configuration for the data collection session. For a condition that a cell-level measurement is less than a threshold, the associated second configuration may comprise a configuration for the user equipment to start the data collection session on one or more predefined cells. For a condition that the user equipment starts the data collection session at execution of a handover from a first network node to a second network node, the associated second configuration may comprise a configuration for the user equipment to collect data on a different set of cells in the data collection session. For a condition that the user equipment starts the data collection session upon receiving, from a network node, an indication to start the first data collection session, the associated second configuration may comprise a configuration for the user equipment to collect data on one or more predefined beams in the data collection session.

[0045] The data collected in the data collection session may comprise one or more radio measurements.

[0046] The disclosure is relevant to 3GPP Technical Specification (TS) 37.320 V18.2.0. Additional information may also be found in the document(s) provided in the Appendix.

[0047] There is the possibility for a UE to report, to the network node (e.g. gNB), the availability of logged data, such as when the UE storage capacity exceeds a certain limit, or when the UE memory is full. It can be advantageous for the UE to be required (e.g. depending on the data collection configuration) to initiate multiple data collection sessions, which each may have the purpose to train, for example, a different NW-side model. It may thus be beneficial to provide a method for the UE to handle these multiple data collection sessions (e.g. considering the limited storage capacity), and the related radio measurements. It may also be beneficial to provide a method for the UE to ensure that only one data collection session is ongoing at a time, e.g. in a case where the UE does not support the possibility to handle multiple ongoing data collection sessions at the same time.

[0048] Upon receiving a report from the UE of the availability of logged data, the network node (e.g. gNB) can request the UE to transmit the stored measurements. It may thus be beneficial to provide a method for the UE to transmit this availability indication. This can be particularly beneficial, for example, in a case where the availability indication is not transmitted by the UE immediately upon determining that the storage capacity becomes limited. For example, in a case where the UE is configured by the network node (e.g. gNB) to periodically report the collected data, it may happen that by the time the collected data is reported, the UE storage capacity is already exceeded or the data collection has already stopped, without anypossibility for the network to know that. It may also be beneficial to provide the network node (e.g. gNB) with knowledge of the reason for the UE reporting the availability indication to the network node (e.g. gNB).

[0049] It may be that the UE can stop the data collection when the UE storage capacity is exceeded and / or when the memory is full. It may thus be beneficial to provide a method for the manner in which the UE is to handle the memory once the data collection is stopped, such as a method for the UE to handle the stored data once the memory (or part of it) is freed up, or once the data collection is resumed.

[0050] It will be understood that the UE reaching a maximum storage capacity is just one possible scenario that the UE may be capable of handling. The UE may also (e.g. be required to) manage its memory and hence the stored measurements in other circumstances, e.g. when a Handover (HO) is performed or when an RLF occurs. None of these scenarios have been considered in the prior art.

[0051] There are provided herein methods performed by a UE for managing data collection. The methods comprise performing one or more actions to control a data collection session at the UE when one or more conditions are fulfilled. The data collection session is a session in which data is collected for an artificial intelligence or machine learning (AI / ML) model. There are also provided herein corresponding methods that can be performed by a network node (e.g. gNB).

[0052] There are provided herein methods for a UE to handle a UE memory, allocated by the UE, for storing collected data for the purpose of training an AI / ML model (or AI / ML functionality).

[0053] The methods can, for example, comprise the UE handling one or more data collection sessions, and optionally also informing a network node (e.g. gNB) about the UE stopping the data collection when, for example, the UE reaches a maximum storage capacity and / or the memory is full.

[0054] The methods may comprise the UE discarding, from the UE memory, at least some of the data collected and stored, in conjunction with certain events.

[0055] The methods may comprise the UE managing a data collection timer (e.g. starting, stopping and / or resuming the data collection timer), such as in conjunction with certain events.

[0056] There are disclosed herein methods for a UE to manage stored measurements during data collection for (e.g. NW-side) model training. It will be noted that the embodiments disclosed herein may be described primarily in terms of NR, but the embodiments are applicable also to other networks.

[0057] The UE may receive a data collection configuration from the network for the UE to perform measurements (e.g. radio measurements) for data collection, such as for the purpose of training a NW-side model (or functionality). Such data collection configuration may also enable the UE to store (or log) the collected data, such as until it is transmitted to the network (e.g. according to a data collection reporting configuration).

[0058] The data collection configuration can also be referred to herein as a “first configuration” or, more specifically, a “first configuration associated with a data collection session”. The data collection configuration can be associated with (or associated to) a specific AI / ML model (or AI / ML functionality), such as any one or more of an AI / ML-based beam management, AI / ML-based mobility, and AI / ML-based positioning, etc.

[0059] The data collection configuration may comprise any one or more of the following:• One or more conditions for the UE to start performing data collection, e.g. to start performing the measurements (e.g. radio measurements) for data collection. These one or more conditions may be referred to herein as one or more first conditions, one or more starting conditions, or one or more starting data collection conditions. The starting data collection conditions can, for example, comprise any one or more of the following: o the cell / beam level measurement quantity of a beam / cell / group of beams / group of cells / neighbouring cells is above or below a threshold, or within a range, or better / worse / offset better / offset worse than a second beam / cell / group of beams / cells; o the UE location; o the UE starting certain timers, such as any one or more of T310 (e.g. a timer that starts upon detecting physical layer problems for a PCell), T312 (e.g. a timer that starts upon triggering a measurement report for a measurement identity for which T312 has been configured while T310 timer is running), T311 (e.g. a timer that starts upon initiating an RRC connection re-establishment procedure), and T304 (e.g. a timer that starts at reception of an RRC connection re-configuration message comprising a Mobility Control Information message); o the UE detecting RLF and / or HOF; o the UE receiving a starting indication from the network node (e.g. gNB), wherein the starting indication may, for example, be an RRCreconfiguration or a command sent by a Medium Access Control (MAC) Control Element (CE) or physical (PHY) layer (Downlink Control Information (DCI)); and o the fulfilment of certain mobility-related events, such as any one or more of the events Al, A2, A3, A4, A5, A6, Bl, and B2.• One or more conditions for the UE to stop or pause performing data collection, e.g. to stop or pause performing measurements (e.g. radio measurements). These one or more conditions may be referred to herein as one or more third conditions, or one or more stopping conditions (or one or more stopping data collection conditions).• One or more conditions for the UE to resume performing the radio measurements for data collection, i.e. conditions for the UE to resume performing data collection, said resuming data collection conditions. These one or more conditions may be referred to herein as one or more second conditions, or one or more resuming conditions (or one or more resuming data collection conditions).

[0060] The network node (e.g. gNB) may transmit the starting indication to the UE. The network node (e.g. gNB) may transmit the one or more starting data collection conditions to the UE, such as by transmitting a data collection configuration comprising the one or more starting data collection conditions to the UE. For any one or more (e.g. each) of the one or more starting data collection conditions, the network node (e.g. gNB) may include in the data collection configuration an associated measurement (e.g. radio measurement) configuration.

[0061] For example, if a starting condition is a cell level measurement being below (or less than) a certain threshold, then the network node (e.g. gNB) may configure the UE to start performing (e.g. radio) measurements (e.g. periodically or aperiodically) on a specific set of cells. On the other hand, for example, if the UE starts the data collection at the execution of a handover (e.g. when a timer T304 is started) from a first network node (e.g. gNB) to a second network node (e.g. gNB), then the first network node may configure the UE to perform data collection on another set of cells. In yet another example, if the UE starts performing the data collection upon receiving an explicit indication or configuration from the network node (e.g. gNB), then a (e.g. radio) measurement configuration may configure the UE to perform measurements (e.g. periodically or aperiodically) on a specific set of beams, e.g. representedby a set of CSI-RS resources, Synchronization Signal (SS) blocks, or Physical Broadcast Channel (PBCH) blocks.

[0062] The UE may start a data collection session upon fulfilling a starting data collection condition, or a set of starting data collections conditions. In an example, the UE may have ongoing (e.g. may have started and not stopped) multiple data collection sessions, e.g. each associated with (or associated to) a different starting data collection condition (or different sets of starting data collection conditions). In another example, the UE may start a second data collection session only after stopping a first data collection session started at a previous point in time. This method can imply that only one data collection session can be ongoing at a time. In another example, the UE may start a second data collection session only after transmitting all or parts of the data associated to first data collection session started at a previous point in time. In another example, the UE may start a second data collection session only after receiving a request from a network node (e.g. gNB) to transmit the data associated with (or associated to) the first data collection session started at a previous point in time. Thus, the network node (e.g. gNB) may transmit this request to the UE. In another example, the UE may start a second data collection session only after discarding the data associated with (or associated to) the first data collection session started at a previous point in time.

[0063] The data collected in a data collection session may be transmitted according to a reporting configuration. The reporting configuration can also be referred to herein as a “second configuration” or, more specifically, a “second configuration associated with a data collection session”, a data collection reporting configuration, or a measurement report configuration. The reporting configuration of collected data may comprise, for example, a periodicity for the reporting of the collected data (or parts of it), or one or more events for the reporting of the collected data (or parts of it). For the latter case (i.e. event-driven reporting), the reporting configuration may comprise at least one trigger event for the transmission of collected data or at least part of it. The triggering event may, for example, be the UE fulfilling at least one of the conditions for the stopping of data collection. Other triggering events may, for example, comprise the UE fulfilling the conditions for the stopping and / or resuming of the data collection. For the former case (periodic-reporting), the reporting configuration may indicate the reporting periodicity from the point in time at which (or in which) the starting or resuming data collection conditions are fulfilled, or from the point in time at which (or in which) the stopping data collection conditions are fulfilled.

[0064] As for the measurement (e.g. radio measurement) configuration, the reporting configuration can be different depending on the specific starting condition. For example, if thedata collection is started by the UE at reception of an explicit network node (e.g. gNB) indication or configuration, and the UE is configured to periodically perform measurements (e.g. radio measurements), then the associated reporting configuration can indicate periodic reporting of the collected data and may also include the reporting periodicity. Thus, the network node (e.g. gNB) may transmit this explicit indication or configuration to the UE. In another example, the reporting configuration may indicate the UE to report the collected data in conjunction with a certain event. For example, if the UE starts data collection due to cell level quality or beam level quality being below (or less than) a certain threshold, then the reporting configuration may indicate the UE to report the collected measurement results periodically, from the point in time at which (or in which) the starting data collection conditions are fulfilled, i.e. from the point in time at which (or in which) the UE has collected data to transmit, until there is data available for transmission in the UE memory. Alternatively, the reporting configuration may indicate the UE to report the collected measurement results periodically, from the point in time at which (or in which) the stopping data collection conditions are fulfilled, i.e. from the point in time at which (or in which) the UE has stopped collecting data, until there is data available for transmission in the UE memory.

[0065] The stopping data collection conditions can, for example, comprise any one or more of the following:• The UE memory allocated for the storing of data exceeding a certain threshold or becoming full. o According to this method, for example, once the memory that the UE allocated for storing the collected data is full, or exceeds a maximum storage threshold, the UE may stop performing the data collection. o The UE may store separately the data associated with (or associated to) different AI / ML data collection functionalities. For example, the UE may store separately data collected for the purpose of AI / ML beam management, or AI / ML mobility management, etc. The UE may store separately data collected for the purpose of UE-side data collection and NW-side data collection. In such cases, the UE may consider the memory as full when the maximum storage capacity allocated for that specific AI / ML functionality is reached.• The UE executing or completing a handover, or receiving a release message. o According to this method, for example, the UE may upon receiving or executing an RRC reconfiguration with sync for a PCell handover, or for a Primary Secondary Cell (PSCell) change stop the data collection. Similarly, for example, the UE may upon receiving a release message (e.g. to release an RRC connection or to suspend the RRC connection) stop the data collection. o It may be the case that a decision on whether or not the UE is to stop the data collection at a HO depends on the cell or network node (e.g. gNB) to which the UE performs the HO. For example, if the HO is performed to a cell which is controlled by the same network node (e.g. gNB) that configured the UE to perform the data collection, then the UE may not stop performing the data collection, because even after performing the handover the collected data can be retrieved by the same network node (e.g. gNB). If a cell to which the UE performs the handover is controlled (or hosted) by a second network node (e.g. gNB) that is different from (or different than) the first network node (e.g. gNB) that configured the UE to perform a data collection, the UE may keep performing the data collection if, for example, the target network node (e.g. gNB) can fetch the data collected by the UE and send that data to the source network node (e.g. gNB). If the second network node (e.g. gNB) cannot fetch such collected data (such as in case the Xn interface between the first and second network nodes (e.g. gNBs) does not support the transmission of such collected data from the second network node (e.g. gNB) to the first network node (e.g. gNB)), then the UE may stop the data collection. o It may be the case that a decision on whether or not the UE is to stop the data collection at a HO is configured by a network node (e.g. gNB). For example, the network node (e.g. gNB) configuring the UE to perform the data collection may indicate whether, for the cells or for the network nodes (e.g. gNBs) to which the UE is handed-over or the UE may be handed-over, the UE is to continue or stop the data collection.• The UE exiting an area of interest.• Fulfilling one or more radio conditions, such as the following: o The UE may have started the data collection upon fulfilling certain radio conditions, such as upon one or more radio measurement quantities (e.g. any one or more of a Reference signal received power (RSRP), a Reference signal received quality (RSRQ), a Signal to Interference and Noise Ratio (SINR), an RSSI, and a Signal to Noise Ratio (SNR)) being above or below (e.g. greater than or less than) a certain configured threshold, and / or upon fulfilling any one or more other conditions listed in the starting data collection conditions, and / or upon fulfilling one or more certain mobility related events (such as any one or more Ax mobility events). Hence, once the conditions for the starting of data collection are not fulfilled anymore, the UE may stop the data collection. Alternatively, the network node (e.g. gNB) may have configured other radio conditions for the stopping of data collection, such as one or more radio measurement quantities (RSRP, RSRQ, SINR, RSSI, SNR) being above or below (e.g. greater than or less than) a certain configured threshold.• Expiring of a data collection timer. o A network node (e.g. gNB) may have configured the UE with a timer that the UE starts when a data collection starts. Hence, at the expiry of such a data collection timer, the UE may stop performing the data collection.• Detecting an RLF or HOF. o The UE may stop a data collection upon detecting an RLF or HOF. It may be the case that a decision on whether or not the data collection is stopped depends on whether a re-establishment occurs in the same or different cell, as the cell in which the UE was configured to perform the data collection, or in a cell of the same or different network node (e.g. gNB), as the network node (e.g. gNB) in which the UE was configured to perform the data collection.• UE changing mobility state and / or speed.• Conditions for starting the data collection not fulfilled any longer.

[0066] Any one or more of the above conditions may be specified in a standard specification and, for example, not included in the data collection configuration. For example, it may be specified in the standard that at the expiry of the data collection time, or at the time of detecting an RLF / HOF, or at the time of receiving a release message (e.g. for the release or suspension of the RRC connection), the UE is to stop the data collection session. Conversely, stopping conditions (e.g. related to radio conditions) may be included in the data collection configuration.

[0067] Some of the above conditions may imply the stopping of all the ongoing data collection sessions, i.e. the data collection sessions started and not yet stopped. For example, upon receiving an RRC release message, or upon executing (or completing) a handover, or upon detecting an RLF / HOF, all the ongoing data collection sessions may be stopped. Some of the above conditions may imply the stopping only of specific ongoing data collection sessions. For example, if a data collection session is stopped due to the starting data collection condition(s) no longer being fulfilled, the UE may only stop the concerned started data collection session whose starting data collection condition(s) are no longer fulfilled.

[0068] The UE may transmit an indication to a network node (gNB) about the stopping of the data collection associated to a started data collection session. Thus, the network node (gNB) may receive such an indication from the UE. Such an indication of the stopped data collection may comprise, for example, any one or more of the following information:• The one or more of the stopping data collection conditions for which the UE has stopped the data collection. o For example, the UE may indicate that the reason for stopping the data collection is that the maximum amount of data storage was reached for the data collection associated to the concerned AI / ML model (or AI / ML functionality), and / or that the stored data exceeded a certain threshold.• Indicating the time-related information associated with (or associated to) the point in time at which (or in which) the data collection was stopped. o For example, the UE may indicate the point in time (e.g. through a timestamp) at which (or in which) the UE stopped the data collection; or the time gap between the point in time at which (or in which) the UEstopped the data collection and the point in time at which (or in which) the indication is transmitted; or the time gap between the point in time at which (or in which) the UE transmitted for the last time the collected data (or parts of it) and the point in time at which (or in which) the indication is transmitted. o This method may be particularly beneficial in certain cases. For example, if the UE is configured to periodically report the collected data every 5 time units (e.g. at TO, T5, T10, etc.) and the data collection is stopped by the UE at time Tl, then the UE at time T5 may transmit in the indication one of the above time references to inform the network node (e.g. gNB) that the UE has stopped the data collection at time Tl .Indicating information associated with (e.g. associated to) the last measurement(s) performed before stopping the data collection. o For example, the UE may indicate the point in time (e.g. through a timestamp) at which (or in which) the UE performed the last radio measurement(s) for the purpose of data collection for a certain AI / ML model (or AI / ML functionality), before the data collection was stopped; or the UE may indicate to the network node (e.g. gNB) the time gap between the point in time at which (or in which) the UE performed the last measurement(s) for the purpose of data collection of a certain AI / ML model (or AI / ML functionality), and the point in time at which (or in which) the data collection was stopped, or the point in time at which (or in which) the indication is transmitted. o This method may be particularly beneficial in certain cases. For example, if the UE is configured to periodically report the collected data every 10 time units (e.g. at TO, T10, T20, etc.) and to perform (e.g. radio) measurements for the data collection purpose every 4 time units (e.g. at TO, T4, T8, etc.), and the data collection is stopped by the UE at time T7, then the UE at time T10 may transmit to the network node (e.g. gNB) one of the above time references to inform the network node (e.g. gNB) that the last radio measurement(s) that the UE performed was at time T4.Indicating that there is or there is not collected data stored by the UE available for transmission. o For example, the transmission of the indication may imply that the UE is indicating that there is data, collected for the purpose of data collection of a certain AI / ML model (or AI / ML functionality), stored in the UE memory and that the data is available for transmission. o It may be that the UE does not transmit the indication if, at the moment of stopping the data collection, there is no data collected available for transmission. This can happen, for example, in case the event(s) for stopping the data collection are fulfilled when there is no data stored available for transmission, e.g. the data collection is ongoing (such as where the UE is still performing (e.g. radio) measurements for the purpose of data collection), but the collected data up to this point in time was previously transmitted by the UE, or the data collection is ongoing but no (e.g. radio) measurement for the purpose of data collection has been performed yet, or the collected data was discarded upon the UE fulfilling one or more conditions for discarding the collected data. If the indication is transmitted to the network node (e.g. gNB), the UE implicitly indicates that it has collected data available for transmission. o The UE may transmit the indication even if, at the moment of stopping the data collection, there is no data collected available for transmission. In such a case, the indication may comprise the information (i.e. a first information) to indicate that the UE has stopped the data collection, and a second explicit information to indicate that the UE does not have any data available for transmission. o The UE may further include the amount of data associated with (e.g. associated to) the data collection session that is available for transmission in the UE memory (e.g. in kilobyte (KB)), and not yet transmitted.Indicating the UE memory status. o For example, when transmitting the indication, the UE may further include additional information about the UE memory status, such asthe amount of memory or storage left or already occupied (e.g. in KB), for storing the data for the purpose of data collection of the AI / ML model (or AI / ML functionality).

[0069] The indication may include (e.g. also include among any one or more of the above information), an identity of the data collection session for which the indication is sent, i.e. the data collection session whose stopping data collection condition(s) are fulfilled. The identity of the data collection session may be determined, for example, by the UE at the starting of the data collection, and may be signalled to the network node (e.g. gNB) upon the starting of the data collection session. Thus, the network node (e.g. gNB) may receive identity of the data collection session from the UE. The identity of the data collection session may correspond to a starting data collection condition. Hence, the UE may indicate the starting data collection condition. Thus, the network node (e.g. gNB) may receive the starting data collection condition from the UE. The identity of the data collection session may correspond to a configuration identity indicated by the network node (e.g. gNB) as part of the data collection configuration, e.g. a configuration identity may be associated with (e.g. associated to) a starting data collection condition, or to a (e.g. radio) measurement configuration, and it may correspond to the starting data collection condition for which the data collection session is started, and to the (e.g. radio) measurement configuration according to which the data collection is performed for the data collection session.

[0070] The UE may indicate the AI / ML model (or AI / ML functionality) identity associated with (or associated to) the data collection session for which the stopping data collection condition(s) is fulfilled. In case all the started data collection sessions are stopped, the UE may indicate the identity of the stopped data collection sessions, or a flag indicating that all the started data collection sessions are stopped. Alternatively, the specific stopping data collection condition included in the indication may implicitly indicate that all the data collection sessions are stopped.

[0071] According to any of the methods described herein, the UE may for example transmit the indication to the network node (e.g. gNB) indicating that the UE has stopped performing the data collection (indicating, for example, the one or more stopping conditions that were fulfilled), and may also transmit an indication indicating that there is still data available associated with (e.g. associated to) this data collection session that needs to be transmitted to the network node (e.g. gNB). Thus, the network node (e.g. gNB) may receive, from the UE, the indication indicating that the UE has stopped performing the data collectionand may also receive the indication indicating that there is still data available associated with this data collection session. The network node (e.g. gNB) may in response, for example, reconfigure the UE such that it does not need any longer to perform the associated (e.g. radio) measurement, and request the UE to transmit all the remaining data (e.g. in successive RRC messages) after the UE indicates that the data collection session is stopped, or let the UE transmit according to the already configured reporting configuration (e.g. periodically) the remaining data. The network node (e.g. gNB) may stop transmitting reference signals in which the UE was performing the (e.g. radio) measurement associated with (e.g. associated to) the stopped data collection session.

[0072] Any one or more of the above-described indications may be transmitted in the same message as, or in a different message from, the message in which the collected data (or parts of it) are transmitted.

[0073] For example, the message comprising any one or more of the indications can be UEAssistancelnformation submitted by the RRC layer for transmission, e.g. at the moment of fulfilling the conditions for stopping the data collection.

[0074] In another example, the message comprising any one or more of the indications can be a “complete” message, such as an RRCReconfigurationComplete, an RRCReestablishmentComplete, and RRCResumeComplete, and / or RRCSetupComplete message. For example, upon completing a HO or a PSCell change, the UE may indicate (implicitly or explicitly) in the RRCReconfigurationComplete message that the data collection was stopped at the time of executing the HO, and the UE may further indicate, as disclosed earlier, whether or not there is still data available for transmission to the network node (e.g. gNB), and may indicate the amount of data available for transmission to the network node (e.g. gNB). In another example, upon resuming or setting up an RRC connection, the UE may indicate (implicitly or explicitly) in the RRCSetupComplete or RRCResumeComplete message that the data collection was stopped at the time of performing the RRC release or suspension, and the UE may further indicate, as disclosed earlier, whether or not there are still data available for transmission to the network node (e.g. gNB), and may indicate the amount of data available for transmission to the network node (e.g. gNB). In another example, upon re-establishing an RRC connection, the UE may indicate in the RRCReestablishmentComplete message that the data collection was stopped at the time of detecting a RLF or HOF, and the UE may further indicate (implicitly or explicitly), as disclosed earlier, whether there is still data available for transmission to the network node (e.g. gNB) or not, and may indicate the amount of data available for transmission to the network node (gNB).

[0075] Any one or more of the above-described indications may be transmitted in the same message in which the collected data (or parts of it) are transmitted. For example, any one or more of the indications may be included in an RRC message conveying a report with the collected data, e.g. a measurement report with the collected measurement results. The RRC message may be transmitted, for example, according to the data collection reporting configuration, such as in a periodic fashion or upon the network node (e.g. gNB) request, or upon fulfilling the stopping condition(s).

[0076] The data collected by the UE and stored (or logged) by the UE in the UE memory may be discarded by the UE when (or whenever) one or more conditions are fulfilled. These one or more conditions may be referred to herein as one or more fifth conditions, or one or more discarding conditions (or one or more discarding data collection conditions). The discarding may be for all the collected data stored in the UE memory and not yet transmitted at the moment of fulfilling the discarding data collection condition(s), or it may be only for collected data associated with (e.g. associated to) a data collection session. This discarding method can be used for the UE to free up the memory, and possibly start another data collection session.

[0077] The discarding data collection conditions can, for example, comprise any one or more of the following:• Fulfilling one or more of the stopping data collection conditions. o In some cases, at the stopping of data collection, the UE may also discard the associated stored data. However, this can depend on the specific fulfilled stopping data collection condition(s). For example, if the UE executes or completes a HO, or the UE receives a release message, or the UE detects an HOF or an RLF, and there is stored data yet to be transmitted, the remaining stored data may be discarded by the UE. Otherwise, in case other stopping data collection condition(s) are fulfilled, the UE may keep for some time the collected data in the UE memory before discarding them. For example, if the UE memory becomes full or it exceeds a certain storage capacity, the UE may not discard the data, rather the UE may wait for some time in order to transmit the remaining available collected data not yet transmitted to the network node (e.g. gNB). Similarly, if the (e.g. radio) condition(s) for which the UE started the data collection are no longer fulfilled, theUE may stop the data collection but it may not discard the stored data, rather it may wait for some time in order to transmit the remaining available collected data not yet transmitted to the network node (e.g. gNB). o It may be the case that whether or not the UE is to discard the collected data at HO is configured by the network node (e.g. gNB). For example, the network node (e.g. gNB) configuring the UE to perform the data collection may indicate whether for the cells or for the network nodes (e.g. gNBs) to which the UE is handed-over or may be handed-over, the UE is to keep or discard the already collected data. This can depend, for example, on whether or not the cell to which the UE performs the handover is controlled or hosted by a second network node (e.g. gNB) different from (or different than) the first network node (e.g. gNB) that configured the UE to perform data collection. In this case, if the second network node (e.g. gNB) does not support the transmission of such remaining stored data from the second network node (e.g. gNB) to the first network node (e.g. gNB), then the UE may discard the stored data. o Upon receiving an RRC release message, e.g. releasing or suspending the RRC connection (i.e. upon entering RRC IDLE or RRC INACTIVE state), the UE may discard all the stored data. o Upon detecting an RLF or HOF, the UE may discard all the stored data. It may be that the discarding only occurs if the UE enters an RRC IDLE state (e.g. an RRC re-establishment procedure fails), or if the UE re-establishes its RRC connection in a cell or network node (e.g. gNB) different from (or different than) the cell or network node (e.g. gNB) in which the UE detected the RLF or HOF.• Not yet transmitted the available collected data within a certain discarding time, o For example, a discarding timer may be started by the UE upon transmitting the indication to the network node (e.g. gNB) of the stopped data collection. Thus, the network node (e.g. gNB) may receive, from the UE, the indication of the stopped data collection. In another example, the discarding timer may be started by the UE at thestopping of the data collection timer, which may be stopped when the UE fulfils one or more stopping data collection conditions. o If, within a certain discarding time, the UE has not transmitted yet the collected data (all or parts of it), the UE may discard the remaining available data not yet transmitted. In such a case, the discarding timer may be stopped (and may be cleared) upon transmitting all or parts of the collected data. o The UE may discard the collected data, only if at the expiry of the discard time the UE has not transmitted yet the oldest data among the collected data stored in the UE memory, such as the first message containing the oldest performed (e.g. radio) measurement stored in the UE memory. In such a case, the discarding timer may be stopped (and may be cleared) upon transmitting the oldest data among the collected data. o The UE may discard the collected data, only if at the expiry of the discard time the UE has not yet received a request from the network node (e.g. gNB) to transmit the collected data stored in the UE memory. This may, for example, be adopted in case the UE is configured to transmit the collected data upon network node (e.g. gNB) request. In such a case, the discarding timer may be stopped (and may be cleared) upon receiving the network node (e.g. gNB) request. Thus, the network node (e.g. gNB) may transmit this request to the UE.• Receiving a configuration from the network node (e.g. gNB) to release the data collection configuration for the AI / ML model (or AI / ML functionality). Thus, the network node (e.g. gNB) may transmit this configuration to the UE. o For example, in case the UE receives from the network node (e.g. gNB) a configuration to release the data collection configuration for the UE to perform data collection for a certain AI / ML model (or AI / ML functionality), the UE may discard all the data available in the UE memory associated with (e.g. associated to) the one or more data collection sessions corresponding to the AI / ML model (or AI / ML functionality).

[0078] When discarding the data, the UE may start discarding the data starting from the oldest stored data. When discarding the data, the UE may discard all the data associated with (e.g. associated to) one or more data collection sessions, e.g. considering only those data collection sessions whose stopping data collection condition(s) are fulfilled or all the data collection sessions for which there is data available for transmission to the network node (e.g. gNB) but that has not yet been transmitted.

[0079] The UE may resume a stopped data collection session in any one or more of the following cases (i.e. the resuming data collection conditions can, for example, comprise any one or more of the following):• Stopping data collections condition(s) no longer fulfilled. o For example, if the UE stopped the data collection due to UE memory becoming full or exceeding a threshold, and the UE then starts transmitting the collected data (e.g. starting with the transmission of the oldest stored data), then the UE may resume the data collection. Resuming the data collection may imply the UE resuming performing (e.g. radio) measurements for the purpose of data (e.g. AI / ML data) collection for an AI / ML model (or AI / ML functionality), and resuming the storing of the data associated with (or associated to) the performed (e.g. radio) measurement.• Receiving a request from the network node (e.g. gNB) to resume the data collection. Thus, the network node (e.g. gNB) may transmit this request to the UE. o For example, before resuming the data collection the UE may wait for an explicit request from the network node (e.g. gNB) to resume the data collection. If the UE stopped the data collection due to the UE memory becoming full or exceeding a threshold, then the UE may wait for the network node (e.g. gNB) to transmit a request to resume the data collection. For example, on the basis of the data transmitted by the UE, and on the current buffer status, the network node (e.g. gNB) may determine that the UE is to resume the data collection. Hence, the network node (e.g. gNB) may send a request to the UE to do that.

[0080] Resuming the data collection may imply the UE resuming the stopped data collection timer, or clearing and restarting the data collection timer. Resuming the data collection may imply the UE stopping the discarding timer.

[0081] The following embodiments are also provided, which may be performed by a UE or wireless device (e.g. the UE 212 or UE 300 as described later with reference to Figs. 2 and 3 respectively):Al. A method at a UE for the purpose of NW-side data collection for training an AI / ML model / functionality, the method comprising any one or more of the following for a data collection configuration:• Starting the data collection session based on the data collection configuration in response of fulfilling starting data collection conditions;• Storing the radio measurements associated to the started data collection session and performed according to radio measurement configuration associated to the data collection session;• Reporting the radio measurements performed according to a data collection reporting configuration associated to the data collection session;• Stopping data collection session in response of fulfilling stopping data collection conditions;• Transmitting indication to the network node (e.g. gNB) of stopped data collection session; and• Discarding stored collected measurements associated to the data collection session, in response of fulfilling discarding conditions.A2. The method of Al, further comprising resuming data collection in response of fulfilling resuming data collection conditionsA3. The method of Al or A2, wherein the data collection configuration comprises the starting / stopping / discarding / resuming data collection conditions, an associated radio measurement configuration, and associated data collection reporting configuration.A4. The method of any of Al to A3, wherein a radio measurement configuration is associated to at least one starting data collection condition.A5. The method of any of Al to A4, wherein the data collection reporting configuration is associated to at least one starting data collection condition.A6. The method of any of Al to A5, wherein the reporting of the radio measurements starts from the point in time in which the data collection session is started until there are data, associated to the said data collection session, that are available in the memory for transmission.A7. The method of any of Al to A6, wherein a data collection configuration is associated to a certain AI / ML model / functionality.A8. The method of any of Al to A7, wherein a data collection session is associated to a data collection configuration.A9. The method of any of Al to A8, wherein the stopping / discarding data collection conditions are common or different for different data collection sessions started according to different starting conditions.A10. The method of any of Al to A9, wherein stopping data collections conditions may be any of:• The UE memory allocated for the storing of data exceeding a certain threshold or becoming full;• The UE executing or completing a handover, or receiving a release message;• The UE exiting an area of interest;• Fulfilling radio conditions;• Expiring of a data collection timer;• Detecting an RLF or HOF;• UE changing mobility state / speed; andConditions for starting the data collection not fulfilled any longer.Al l. The method of any of Al to A10, wherein transmitting the indication to the network node (e.g. gNB) of the stopped data collection for a data collection session comprises any of:• Indicating one or more of the stopping data collection conditions for which the UE has stopped the data collection;• Indicating the time-related information associated to the point in time in which the data collection was stopped;• Indicating information associated to the last measurements performed before stopping the data collection;• Indicating that there are or there are not collected data stored by the UE available for transmission; and• Indicating the UE memory status.A12: The method of any of Al to Al 1, wherein the discarding conditions may be any of:• Fulfilling one of the stopping data collection conditions;• Not yet transmitted the available collected data within a certain discarding time; and• Receiving configuration from the network node (e.g. gNB) to release the data collection configuration for the AI / ML model / functionality.Al 3: The method of any of Al to Al 2, wherein the resuming conditions may be any of:• Stopping data collections conditions no longer fulfilled; and• Receiving an indication from the network node (e.g. gNB) to resume the data collection.A14: The method of any of Al to A13, wherein starting the data collection comprises starting a data collection timer and stopping the data collection comprises any of:• stopping the data collection timer, if started; andclearing the data collection timer, if started.Al 5: The method of any of Al to Al 4, wherein stopping the data collection comprises stopping performing radio measurements for the purpose of NW-side data collection, and resuming the data collection comprises resuming performing radio measurements for the purpose of NW-side data collectionAl 6: The method of discarding the stored data collection comprises any of:• Discarding all the stored collected data; and• Discarding the stored collected data starting from the oldest stored data;Al 7: The method of any of Al to Al 6, wherein the indication is transmitted to the network node (e.g. gNB) in the same message in which the stored collected data or parts of it are transmitted.Al 8: The method of any of Al to Al 7, wherein resuming the data collection comprises:• Resuming the stopped data collection timer; and• Clearing and restarting the data collection timer.Al 9. The method of any of Al to Al 8, wherein a stopping data collection condition stops all the started data collection sessions, or one or more of all the started data collection session.A20. The method of any of Al to Al 9, wherein a second data collection session can be started only if:• the first data collection session is stopped;• all or parts of the collected data associated to the first data collection have been transmitted to the network node (e.g. gNB);• it is received a request from the network node (e.g. gNB) to transmit the data associated to the first data collection session; and / or• all or parts of the stored data associated to first data collection session are discarded from the UE memory.

[0082] There is also provided a method performed by a network node (e.g. the network node 210 or network node 400 as described later with reference to Figs. 2 and 4 respectively). The method can comprise any one or more of the steps described herein in relation to a network node.

[0083] There is also provided a system comprising a UE as described herein (e.g. the UE 212 or UE 300 as described later with reference to Figs. 2 and 3 respectively) and a network node as described herein (e.g. the network node 210 or network node 400 as described later with reference to Figs. 2 and 4 respectively). A method performed by the system can comprise the method described herein in respect of the UE and the method described herein in respect of the network node.

[0084] Fig. 2 shows an example of a communication system 200 in accordance with some embodiments.

[0085] In the example, the communication system 200 includes a telecommunication network 202 that includes an access network 204, such as a radio access network (RAN), and a core network 206, which includes one or more core network nodes 208. The access network 204 includes one or more access network nodes, such as network nodes 210a and 210b (one or more of which may be generally referred to as network nodes 210), or any other similar 3rd Generation Partnership Project (3GPP) access nodes or non-3GPP access points (APs). Moreover, as will be appreciated by those of skill in the art, a network node is not necessarily limited to an implementation in which a radio portion and a baseband portion are supplied and integrated by a single vendor. Thus, it will be understood that network nodes include disaggregated implementations or portions thereof. For example, in some embodiments, the telecommunication network 202 includes one or more Open-RAN (ORAN) network nodes. An ORAN network node is a node in the telecommunication network 202 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 202, including one or more network nodes 210 and / or core network nodes 208.

[0086] Examples of an ORAN network node include an open radio unit (O-RU), an open distributed unit (O-DU), an open central unit (O-CU), including an O-CU control plane (O- CU-CP) or an O-CU user plane (O-CU-UP), a RAN intelligent controller (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 combinationthereof (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 Al, Fl, Wl, El, 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 Framework via an 0-2 interface defined by the 0-RAN Alliance or comparable technologies.

[0087] The network nodes 210 facilitate direct or indirect connection of user equipment (UE) (also referred to interchangeably herein as wireless device), such as by connecting UEs 212a, 212b, 212c, and 212d (one or more of which may be generally referred to as UEs 212) to the core network 206 over one or more wireless connections. The network nodes 210 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) Node Bs (gNBs). Unless otherwise indicated, the term ‘network node’ as used herein refers to network nodes 210 and core network nodes 208.

[0088] 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 200 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 200 may include and / or interface with any type of communication, telecommunication, data, cellular, radio network, and / or other similar type of system.

[0089] The UEs 212 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 210 and other communication devices. Similarly, the network nodes 210 are arranged, capable, configured, and / or operable to communicate directly or indirectly with the UEs 212 and / or with other network nodes or equipment in the telecommunication network 202 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 202.

[0090] In the depicted example, the core network 206 connects the network nodes 210 to one or more host computing systems, such as host 216. 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 206 includes one more core network nodes (e.g., core network node 208) that are structured with hardware and software components. Features of these components may be substantially similar to those described with respect to the UEs, network nodes, and / or hosts, such that the descriptions thereof are generally applicable to the corresponding components of the core network node 208. 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).

[0091] The host 216 may be under the ownership or control of a service provider other than an operator or provider of the access network 204 and / or the telecommunication network 202. The host 216 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.

[0092] As a whole, the communication system 200 of Fig. 2 enables connectivity between the 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 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.

[0093] In some examples, the telecommunication network 202 is a cellular network that implements 3GPP standardized features. Accordingly, the telecommunications network 202 may support network slicing to provide different logical networks to different devices that are connected to the telecommunication network 202. For example, the telecommunications network 202 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.

[0094] In some examples, the UEs 212 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 204 on a predetermined schedule, when triggered by an internal or external event, or in response to requests from the access network 204. Additionally, a UE may be configured for operating in single- or multi- Radio Access Technology (RAT) or multi-standard 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).

[0095] In the example, the hub 214 communicates with the access network 204 to facilitate indirect communication between one or more UEs (e.g., UE 212c and / or 212d) and network nodes (e.g., network node 210b). In some examples, the hub 214 may be a controller, router, content source and analytics, or any of the other communication devices described herein regarding UEs. For example, the hub 214 may be a broadband router enabling access to the core network 206 for the UEs. As another example, the hub 214 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 210, or by executable code, script, process, or other instructions in the hub 214. As another example, the hub 214 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 214 may be a content source. For example, for a UE that is a VR device, display, loudspeaker, or other media delivery device, the hub 214 may retrieve VR assets, video, audio, or other media or data related to sensory information via a network node, which the hub 214 then provides to the UE either directly, after performing local processing, and / or after adding additional local content. In still another example, the hub 214 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.

[0096] The hub 214 may have a constant / persistent or intermitent connection to the network node 210b. The hub 214 may also allow for a different communication scheme and / or schedule between the hub 214 and UEs (e.g., UE 212c and / or 212d), and between the hub 214 and the core network 206. In other examples, the hub 214 is connected to the core network 206 and / or one or more UEs via a wired connection. Moreover, the hub 214 may be configured to connect to a machine-to-machine (M2M) service provider over the access network 204 and / or to another UE over a direct connection. In some scenarios, UEs may establish a wireless connection with the network nodes 210 while still connected via the hub 214 via a wired or wireless connection. In some embodiments, the hub 214 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 210b. In other embodiments, the hub 214 may be a non-dedicated hub - that is, a device which is capable of operating to route communications between the UEs and network node 210b, but which is additionally capable of operating as a communication start and / or end point for certain data channels.

[0097] Fig. 3 shows a UE 300 in accordance with some embodiments. The UE 300 presents additional details of some embodiments of the UE 212 of Fig. 2. As used herein, a UE refers to a device capable, configured, arranged and / or operable to communicate wirelessly with network nodes and / or other UEs. Examples of a UE include, but are not limited to, a 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-IoT) UE, a machine type communication (MTC) UE, and / or an enhanced MTC (eMTC) UE.

[0098] A UE may support device-to-device (D2D) communication, for example by implementing a 3 GPP 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).

[0099] The UE 300 includes processing circuitry 302 that is operatively coupled via a bus 304 to an input / output interface 306, a power source 308, a memory 310, a communication interface 312, and / or any other component, or any combination thereof. Certain UEs may utilize all or a subset of the components shown in Fig. 3. 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.

[0100] The processing circuitry 302 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 310. The processing circuitry 302 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 302 may include multiple central processing units (CPUs). The processing circuitry 302 may be configured to cause the UE 302 to perform the methods described herein in relation to the UE, such as the methods as described with reference to Fig. 1.

[0101] In the example, the input / output interface 306 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 300. 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 inputdevice. For example, a Universal Serial Bus (USB) port may be used to provide an input device and an output device.

[0102] In some embodiments, the power source 308 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 308 may further include power circuitry for delivering power from the power source 308 itself, and / or an external power source, to the various parts of the UE 300 via input circuitry or an interface such as an electrical power cable. Delivering power may be, for example, for charging of the power source 308. Power circuitry may perform any formatting, converting, or other modification to the power from the power source 308 to make the power suitable for the respective components of the UE 300 to which power is supplied.

[0103] The memory 310 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 310 includes one or more application programs 314, such as an operating system, web browser application, a widget, gadget engine, or other application, and corresponding data 316. The memory 310 may store, for use by the UE 300, any of a variety of various operating systems or combinations of operating systems.

[0104] The memory 310 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 (eUICC), integrated UICC (iUICC) or a removable UICC commonly known as ‘SIM card’. The memory 310 may allow the UE 300 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, suchas one utilizing a communication system may be tangibly embodied as or in the memory 310, which may be or comprise a device-readable storage medium.

[0105] The processing circuitry 302 may be configured to communicate with an access network or other network using the communication interface 312. The communication interface 312 may comprise one or more communication subsystems and may include or be communicatively coupled to an antenna 322. The communication interface 312 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 318 and / or a receiver 320 appropriate to provide network communications (e.g., optical, electrical, frequency allocations, and so forth). Moreover, the transmitter 318 and receiver 320 may be coupled to one or more antennas (e.g., antenna 322) and may share circuit components, software or firmware, or alternatively be implemented separately.

[0106] In the illustrated embodiment, communication functions of the communication interface 312 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 / intemet protocol (TCP / IP), synchronous optical networking (SONET), Asynchronous Transfer Mode (ATM), QUIC, Hypertext Transfer Protocol (HTTP), and so forth.

[0107] Regardless of the type of sensor, a UE may provide an output of data captured by its sensors, through its communication interface 312, 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).

[0108] 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.

[0109] 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 300 shown in Fig. 3.

[0110] 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-IoT 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.

[0111] 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 mayadjust 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.

[0112] Fig. 4 shows a network node 400 in accordance with some embodiments. As used herein, network node refers to equipment capable, configured, arranged and / or operable to communicate directly or indirectly with a UE and / or with other network nodes or equipment, in a telecommunication network. Examples of network nodes include, but are not limited to, 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).

[0113] 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).

[0114] 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 / multi cast 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).

[0115] The network node 400 includes a processing circuitry 402, a memory 404, a communication interface 406, and a power source 408. The network node 400 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 network node 400 comprises multiple separate components (e.g., BTS and BSC components), one or more of the separatecomponents may be shared among several network nodes. For example, a single RNC may control multiple NodeBs. In such a scenario, each unique NodeB and RNC pair, may in some instances be considered a single separate network node. In some embodiments, the network node 400 may be configured to support multiple radio access technologies (RATs). In such embodiments, some components may be duplicated (e.g., separate memory 404 for different RATs) and some components may be reused (e.g., a same antenna 410 may be shared by different RATs). The network node 400 may also include multiple sets of the various illustrated components for different wireless technologies integrated into network node 400, 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 network node 400.

[0116] The processing circuitry 402 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 400 components, such as the memory 404, to provide network node 400 functionality. For example, the processing circuitry 402 may be configured to cause the network node to perform the methods described herein in relation to the network node (e.g. gNB).

[0117] In some embodiments, the processing circuitry 402 includes a system on a chip (SOC). In some embodiments, the processing circuitry 402 includes one or more of radio frequency (RF) transceiver circuitry 412 and baseband processing circuitry 414. In some embodiments, the radio frequency (RF) transceiver circuitry 412 and the baseband processing circuitry 414 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 412 and baseband processing circuitry 414 may be on the same chip or set of chips, boards, or units.

[0118] The memory 404 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 computerexecutable memory devices that store information, data, and / or instructions that may be usedby the processing circuitry 402. The memory 404 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 402 and utilized by the network node 400. The memory 404 may be used to store any calculations made by the processing circuitry 402 and / or any data received via the communication interface 406. In some embodiments, the processing circuitry 402 and memory 404 is integrated.

[0119] The communication interface 406 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 406 comprises port(s) / terminal(s) 416 to send and receive data, for example to and from a network over a wired connection. The communication interface 406 also includes radio front-end circuitry 418 that may be coupled to, or in certain embodiments a part of, the antenna 410. Radio front-end circuitry 418 comprises filters 420 and amplifiers 422. The radio front-end circuitry 418 may be connected to an antenna 410 and processing circuitry 402. The radio front-end circuitry may be configured to condition signals communicated between antenna 410 and processing circuitry 402. The radio front-end circuitry 418 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 418 may convert the digital data into a radio signal having the appropriate channel and bandwidth parameters using a combination of filters 420 and / or amplifiers 422. The radio signal may then be transmitted via the antenna 410. Similarly, when receiving data, the antenna 410 may collect radio signals which are then converted into digital data by the radio front-end circuitry 418. The digital data may be passed to the processing circuitry 402. In other embodiments, the communication interface may comprise different components and / or different combinations of components.

[0120] In certain alternative embodiments, the network node 400 does not include separate radio front-end circuitry 418, instead, the processing circuitry 402 includes radio front-end circuitry and is connected to the antenna 410. Similarly, in some embodiments, all or some of the RF transceiver circuitry 412 is part of the communication interface 406. In still other embodiments, the communication interface 406 includes one or more ports or terminals 416, the radio front-end circuitry 418, and the RF transceiver circuitry 412, as part of a radio unit (not shown), and the communication interface 406 communicates with the baseband processing circuitry 414, which is part of a digital unit (not shown).

[0121] The antenna 410 may include one or more antennas, or antenna arrays, configured to send and / or receive wireless signals. The antenna 410 may be coupled to the radio front-endcircuitry 418 and may be any type of antenna capable of transmitting and receiving data and / or signals wirelessly. In certain embodiments, the antenna 410 is separate from the network node 400 and connectable to the network node 400 through an interface or port.

[0122] The antenna 410, communication interface 406, and / or the processing circuitry 402 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 410, the communication interface 406, and / or the processing circuitry 402 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.

[0123] The power source 408 provides power to the various components of network node 400 in a form suitable for the respective components (e.g., at a voltage and current level needed for each respective component). The power source 408 may further comprise, or be coupled to, power management circuitry to supply the components of the network node 400 with power for performing the functionality described herein. For example, the network node 400 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 408. As a further example, the power source 408 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.

[0124] Embodiments of the network node 400 may include additional components beyond those shown in Fig. 4 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 400 may include user interface equipment to allow input of information into the network node 400 and to allow output of information from the network node 400. This may allow a user to perform diagnostic, maintenance, repair, and other administrative functions for the network node 400. In some embodiments providing a core network node, such as core network node 108 of FIG. 2, some components, such as the radio front-end circuitry 418 and the RF transceiver circuitry 412 may be omitted.

[0125] Fig. 5 is a block diagram illustrating a virtualization environment 500 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 500 hosted by one or more of hardware nodes, such as a hardware computing device that operates as a network 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 500 includes components defined by the O-RAN Alliance, such as an O-Cloud environment orchestrated by a Service Management and Orchestration (SMO) Framework via an 0-2 interface. Virtualization may facilitate distributed implementations of a network node, UE, core network node, or host.

[0126] Applications 502 (which may alternatively be called software instances, virtual appliances, network functions, virtual nodes, virtual network functions, etc.) are run in the virtualization environment Q400 to implement some of the features, functions, and / or benefits of some of the embodiments disclosed herein.

[0127] Hardware 504 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 506 (also referred to as hypervisors or virtual machine monitors (VMMs)), provide VMs 508a and 508b (one or more of which may be generally referred to as VMs 508), and / or perform any of the functions, features and / or benefits described in relation with some embodiments described herein. The virtualization layer 506 may present a virtual operating platform that appears like networking hardware to the VMs 508.

[0128] The VMs 508 comprise virtual processing, virtual memory, virtual networking or interface and virtual storage, and may be run by a corresponding virtualization layer 506. Different embodiments of the instance of a virtual appliance 502 may be implemented on one or more of VMs 508, 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 volumeserver hardware, physical switches, and physical storage, which can be located in data centers, and customer premise equipment.

[0129] In the context of NFV, a VM 508 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 508, and that part of hardware 504 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 508 on top of the hardware 504 and corresponds to the application 502.

[0130] Hardware 504 may be implemented in a standalone network node with generic or specific components. Hardware 504 may implement some functions via virtualization. Alternatively, hardware 504 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 510, which, among others, oversees lifecycle management of applications 502. In some embodiments, hardware 504 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 512 which may alternatively be used for communication between hardware nodes and radio units.

[0131] 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, andfunctionality 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.

[0132] 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.

[0133] Other embodiments of the present disclosure are defined in the following numbered statements:Group A EmbodimentsEmbodiment 1. A method performed by a user equipment (e.g. the UE 212 or UE 300 as described earlier with reference to Figs. 2 and 3 respectively) for managing data collection, the method comprising: performing one or more actions to control a data collection session at the user equipment when one or more conditions are fulfilled, wherein the data collection session is a session in which data is collected for an artificial intelligence or machine learning, AI / ML, model.Embodiment 2. The method of embodiment 1, wherein: performing the one or more actions to control the data collection session when the one or more conditions are fulfilled comprises:starting a first data collection session for a first time when one or more first conditions are fulfilled.Embodiment 3. The method of embodiment 2, wherein: the one or more first conditions comprise any one or more of: a condition that a cell level measurement quantity of one or more cells meets a threshold, is within a range, or is different from another one or more cells; a condition that a beam level measurement quantity of one or more beams meets a threshold, is within a range, or is different from another one or more beams; a condition that the user equipment is at a predefined location; a condition that the user equipment starts a timer; a condition that a mobility event occurs, such as any one or more of Al, A2, A3, A4, A5, A6, Bl, and B2 (e.g. as defined earlier); a condition that the user equipment detects a mobility event, such as a handover failure or a radio link failure; a condition that the user equipment receives, from a network node, an indication to start the first data collection session; and a condition that the user equipment receives, from a network node, a Layer 3 (L3) configuration for the first data collection session.Embodiment 4. The method of any of the preceding embodiments, wherein: performing the one or more actions to control the data collection session when the one or more conditions are fulfilled comprises: starting a first data collection session for a subsequent time (i.e. resuming the first data collection) when one or more second conditions are fulfilled.Embodiment 5. The method of embodiment 4, wherein: the one or more second conditions comprise any one or more of: a condition that one or more third conditions for stopping the first data collection session are no longer fulfilled; and a condition that the user equipment receives a request, from a network node, to start the first data collection session for the subsequent time.Embodiment 6. The method of any of the preceding embodiments, wherein:performing the one or more actions to control the data collection session when the one or more conditions are fulfilled comprises: starting a second data collection session when one or more fourth conditions are fulfilled, wherein the second data collection session is started subsequent to starting a first data collection.Embodiment 7. The method of any of the preceding embodiments, wherein: the one or more fourth conditions comprise any one or more of: a condition that the user equipment stops the first data collection session; a condition that the user equipment transmits some or all of the data collected in the first data collection session; a condition that the user equipment receives, from a network node, a request to transmit the data collected in the first data collection session; and a condition that the user equipment discards the data collected in the first data collection session.Embodiment 8. The method of any of the preceding embodiments, wherein: performing the one or more actions to control the data collection session when the one or more conditions are fulfilled comprises: stopping the data collection session when one or more third conditions are fulfilled.Embodiment 9. The method of embodiment 8, wherein: stopping the data collection session comprises: stopping the data collection session permanently; or stopping the data collection session temporarily (i.e. pausing the data collection session).Embodiment 10. The method of embodiment 9, wherein: the one or more third conditions comprise any one or more of: a condition that the user equipment has reached a maximum storage capacity; a condition that a memory of the user equipment is full; a condition that the user equipment executes or completes a handover; a condition that the user equipment receives a release message;a condition that the user equipment exits an area of interest; a condition that the user equipment fulfils one or more radio conditions; a condition that a data collection timer expires; a condition that a mobility event, such as a handover failure or a radio link failure, is detected; a condition that the user equipment changes a mobility state or speed; and a condition that one or more conditions for starting the data collection session are no longer fulfilled.Embodiment 11. The method of any of embodiments 8 to 10, the method comprising: transmitting, to a network node, information signalling that the data collection session has stopped.Embodiment 12. The method of embodiment 11, wherein: the information signalling that the data collection session has stopped comprises any one or more of: information indicative of the one or more third conditions that are fulfilled; information indicative of a point in time at which the data collection session stopped; information indicative of the data collected in the data collection session before the data collection session stopped; information indicative of whether or not data collected in the data collection session is available for transmission; and information indicative of a memory status of the user equipment.Embodiment 13. The method of any of the preceding embodiments, wherein: performing the one or more actions to control the data collection session when the one or more conditions are fulfilled comprises: discarding some or all of the data collected in the data collection session when one or more fifth conditions are fulfilled.Embodiment 14. The method of embodiment 13, wherein: the data is discarded from a memory of the user equipment.Embodiment 15. The method of embodiment 13 or 14, wherein: the one or more fifth conditions comprise any one or more of: a condition that one or more third conditions for stopping the data collection session are fulfilled; a condition that the user equipment fails to transmit, within a predefined time, the data collected in the data collection session; and a condition that the user equipment receives, from a network node, a request to release a first configuration associated with the data collection session.Embodiment 16. The method of any of the preceding embodiments, the method comprising: storing the data in a memory of the user equipment according to a first configuration associated with the data collection session.Embodiment 17. The method of any of the preceding embodiments, the method comprising: transmitting, to a network node, some or all of the data collected in the data collection session.Embodiment 18. The method of embodiment 17, wherein: the data collected in the data collection session is transmitted according to a second configuration associated with the data collection session.Embodiment 19. The method of embodiment 18, wherein: the second configuration comprises one or both of: a periodicity for the transmission of some or all of the data collected in the data collection session; and at least one event for triggering the transmission of some or all of the data collected in the data collection session.Embodiment 20. The method of any of the preceding embodiments, the method comprising: acquiring a first configuration for the data collection session, wherein the first configuration comprises the one or more conditions.Embodiment 21. The method of embodiment 20, wherein: acquiring the first configuration comprises:retrieving the first configuration from a standard specification; or receiving the first configuration from a network node.Embodiment 22. The method of embodiment 20 or 21, wherein: the first configuration enables the user equipment to store the data collected in the data collection session until the data is transmitted to a network node.Embodiment 23. The method of any of embodiments 20 to 22, wherein: the first configuration is associated with the AI / ML model.Embodiment 24. The method of any of embodiments 20 to 23, wherein: for each of the one or more conditions, the first configuration for the data collection session comprises an associated second configuration for the data collection session.Embodiment 25. The method of embodiment 24, wherein: for a condition that a cell-level measurement is less than a threshold, the associated second configuration comprises a configuration for the user equipment to start the data collection session on one or more predefined cells; for a condition that the user equipment starts the data collection session at execution of a handover from a first network node to a second network node, the associated second configuration comprises a configuration for the user equipment to collect data on a different set of cells in the data collection session; and for a condition that the user equipment starts the data collection session upon receiving, from a network node, an indication to start the first data collection session, the associated second configuration comprises a configuration for the user equipment to collect data on one or more predefined beams in the data collection session.Embodiment 26. The method of any of the preceding embodiments, wherein: the data collected in the data collection session comprises one or more radio measurements.Group B EmbodimentsEmbodiment 27. A method performed by a network node (e.g. the network node 210 ornetwork node 400 as described earlier with reference to Figs. 2 and 4 respectively) for managing data collection, the method comprising: any one or more of the steps described herein in relation to the network node.Group C EmbodimentsEmbodiment 28. A user equipment, UE, comprising processing circuitry configured to cause the UE to perform the method of any of the Group A embodiments.Embodiment 29. The UE of the previous embodiment, wherein the UE comprises at least one memory for storing instructions which, when executed by the processing circuitry, cause the UE to perform the method of any of the Group A embodiments.Embodiment 30. A network node comprising processing circuitry configured to cause the network node to perform the method of any of the Group B embodiments.Embodiment 31. The network node of the previous embodiment, wherein the network node comprises at least one memory for storing instructions which, when executed by the processing circuitry, cause the network node to perform the method of any of the Group B embodiments.Embodiment 32. A user equipment for managing data collection, comprising: 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.Embodiment 33. A network node for managing data collection, the network node comprising: processing circuitry configured to cause the network node to perform any of the steps of any of the Group B embodiments; power supply circuitry configured to supply power to the processing circuitry.Embodiment 34. A user equipment (UE) for managing data collection, the 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 cause the user equipment to perform any of the steps of any of the Group A embodiments; 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; and a battery connected to the processing circuitry and configured to supply power to the UE.Group D EmbodimentsEmbodiment 35. A computer program comprising instructions which, when executed by processing circuitry of a user equipment, cause the user equipment to perform the method according to any of the Group A embodiments.Embodiment 36. A computer program comprising instructions which, when executed by processing circuitry of a network node, cause the network node to perform the method according to any of the Group B embodiments.Embodiment 37. A computer program product, embodied on anon-transitory machine- readable medium, comprising instructions which are executable by processing circuitry of a user equipment to cause the user equipment to perform the method according to any of the Group A embodiments.Embodiment 38. A computer program product, embodied on a non-transitory machine- readable medium, comprising instructions which are executable by processing circuitry of a network node to cause the network node to perform the method according to any of the Group B embodiments.

[0134] It should be noted that the above-mentioned embodiments illustrate rather than limit the idea, and that those skilled in the art will be able to design many alternativeembodiments without departing from the scope of the appended claims. The word “comprising” does not exclude the presence of elements or steps other than those listed in a claim, “a” or “an” does not exclude a plurality, and a single processor or other unit may fulfil the functions of several units recited in the claims. Any reference signs in the claims shall not be construed so as to limit their scope.APPENDIXSGPP TSG-RAN WG2 #127 DocNumberMaastricht, Netherlands, 19th - 23th August 2024Agenda Item: 8.1.3Source: EricssonTitle: NW-side data collection for beam management use casesDocument for: Discussion1 IntroductionThe topic of NW-side data collection was discussed during the Rel.18 SI, and different technical enhancements to support this feature were included in the TR 38.843. In this paper, we first provide an overview of the Rel.18 discussion, and then we draw some proposals for the Rel. 19 work item.2 DiscussionRelated to this topic, the following agreements were reached during the WI meetings in RAN2In the following, we further develop the expected technical impacts related to this topic, taking into account the above agreements and the online discussion during the last meeting.2.1 How to handle the case of collected data exceeding single RRC message sizeThe first issue to address from the above agreements is the “FFS how to handle case when single RRC message is not sufficient”.Reporting multiple instances of logged LI measurement result from UE to gNB is a useful feature that allows the UE to avoid continuously transmitting reports of individual measurement results which will not be used anyhow for “real-time” decisions at the gNB, thereby saving the UE power consumption and data overhead. However, it can happen that by doing that all the data collected by the UE may not fit a single RRC message. It was discussed then by RAN2 how to address this issue, e.g. by supporting RRC segmentation for such use case.We first notice that UL RRC segmentation is supported in legacy for the transmission of UECapabilitylnformation and MeasurementReportAppLayer, which is used for the transmission of QoE-related information. For the case of QoE, the data to be transmitted are application layer measurements, and as such, they are generated by the application layer and injected in the RRC layer that in turn would send this data to the gNB as an octet string. Hence, the segmentation is motivated by the fact that the application layer may pass to RRC a bunch of application layer data which could not fit the maximum supported size of a PDCP SDU. Thus, segmentation is needed at RRC in such case. Similar argument holds for the case of UECapabilitylnformation: in that the case the data are generated within the RAN, but the capability IES are so many, that a single message is not enough, and some of the IES need to be transmitted in different RRC segments.UL RRC segmentation is used in legacy when the data to be transmited are generated outside the RAN (i.e. as in QoE) and hence no control of the maximum supported size of a PDCP SDU can be guaranteed; or when the amount of IES to be transmited in a single container is so large that the message exceeds the maximum supported side.The case of AIML data collection is different in our view. Data are generated in the RAN at RRC level, and they should just include the radio measurement results performed at different points in time. Even though we have not agreed yet on the details of the data that the UE should collect, it is very unlikely that information associated to the radio measurement results taken at a certain point in time will exceed the maximum supported size. As an example, at a given point in time the UE may store the RSRP results, cell / beams information, possibly location / time info, but certainly such info will not exceed the maximum supported PDCP side.Hence, rather than on QoE- / UECapability Information-like approach we should get inspiration from the logged MDT. As a reference the logged measurement report in logged MDT looks as follows in TS 38.331:In logged MDT, the logged measurement results are included in the logMeasInfoList. If UE cannot transmit in the RRC message all the logged measurements stored by the UE, the UE signals to the network via logMeasAvailable flag that there are still logged data available for transmission to the gNB. No standardized RRC segmentation is specified for this case. It is simply the UE implementation that based on the current size of the UL RRC message determines how large should be the information included in the logMeasInfoList. That is possible because the size of the entries of the logMeasInfoList (i.e. LogMeasInfo) are very much below the maximum supported size.In the logged MDT. the logged measurements stored by the UE are signalled in a list of logged measurement results (i.e. logMeasInfoList). The UE implementation can determine how many entries to include in this list such that the maximum PDCP SDU size is not exceeded. No standardized RRC segmentation procedure is specified.The logged MDT use case is very similar to our use case in AIML. We do not need to specify a standardized RRC segmentation procedure for the reporting of collected data for NW-side model training. The collected data can be included in a measurement results list, where each entry corresponds to measurements performed at different points in time. If the overall amount of collected data exceeds the maximum PDCP SDU size, it is the UE implementation that makes sure to populate such measurement result list accordingly. This would reduce a lot the standardization effort needed to define an RRC segmentation procedure. Additionally, this procedure allows the UE to continue the transmission of the logged measurement after HO, or after reconnecting to the network (e.g. after reestablishment, after resuming, or after re-entering connected mode after an RLF). This is not possible with the RRC segments, because an individual RRC segment is not decodable on its own.The reporting of AIML collected data for NW-side model training resembles the reporting of measurement results for logged MDT. because the collected data are generated at RAN level (unlike QoE). and the information associated to measurements results collected at a given point in time do not exceed the maximum PDCP SDU supported size (unlike UECapability Information).Given the above considerations, we propose the following:The collected AIML-specific data stored by the UE are signalled in a list whose entries include information associated to radio measurements taken at different points in time (as for the logged MPT),The UE implementation can determine how many entries to include in the list radio measurements information, such that the maximum PDCP SDU size is not exceeded. No standardized RRC segmentation procedure is specified (as for the logged MPT),Once discussed / agreed the above, RAN2 can further discuss how to transmit the remaining collected AIML data to the gNB. To this end, we can again get inspiration from the logged MPT, i.e. the UE indicates to the gNB that there available collected data to transmit, and then the gNB can further request the UE to transmit such remaining samples. Or the UE can simply continue the transmission of the remaining samples in following RRC messages (e.g. based on the priority of the SRB allocated to data collection), or postpone the transmission to the following transmission occasion for the AIML reporting, e.g. in case the UE is configured to periodically report the collected data.In case all the collected data do not fit into a single RRC message. RAN2 to discuss: a. Whether and how the UE should inform the network about remaining collected data to be transmitted. b. When the UE should transmit remaining collected data, e.g. in following RRC message(s) based on SRB priority, upon gNB request, at the next periodic transmission occasion, etc.2.2 When the UE should perform the radio measurements for NW-side data collectionFor the case of beam management, the NW may configure the UE with a specific set of CSI- RS / SSB resources specifically configured for training purposes. On such resources, the UE will then start performing layer- 1 measurements and log the measurement results and any possible useful information associated to it. From the point of view of the gNB, this set of CSI-RS / SSB resources used for training purposes may correspond to the set A and set B, because (similar to the UE-side data collection) during the NW-side data collection the gNB would need to know the results on all the beams so that during the inference the gNB just needs to configure the set B and derive via the AIML model the prediction results on the setA. At the same time, the UE would need to perform the legacy measurements for legacy “real time” scheduling decision on another set of CSI-RS / SSB resources.The UE should perform measurements based on a L3 configuration indicating the resources (CSI-RS / SSB) specifically configured for NW-side data collection purposes.When the logging should start is something that RAN2 should discuss. The logging may start upon receiving such configuration from the NW, and it may last for some time depending on NW decisions, or it may start upon fulfilling certain events (as for MDT). For example, if the network needs to collect data for training a model to improve the system performances in regions with poor coverage, it might be useful to configure the UE to start the data collection when the UE ends up in poor coverage regions, or in proximity of cell borders.RAN2 to consider the following mechanisms for the starting of the NW-side data collection procedure: c. The UE starts the data collection upon receiving a L3 configuration for NW- side data collection d. The UE starts the data collection upon fulfilling certain events, e.g. the UE starts the data collection when it ends up in poor coverage regions.As mentioned above, the data collection can continue for certain time configured by the network (as in logged MDT), or it can continue until certain events are fulfilled. For example, the data collection can continue until the UE is in poor radio coverage reason. Further, we need to consider potential UE-side issues that may cause the stopping of the data collection. For example, the UE can become memory limited, in which case the data collection could stop.RAN2 to consider the following mechanisms for the stopping of the NW-side data collection procedure: e. The UE continues data collection for a certain configurable time (as in logged MDT) f The UE continues data collection until certain events are fulfilled, e.g. until the UE is in poor radio coverage reasons g. UE-side reasons, e.g. UE becoming memory limited2.3 How the UE should report the collected dataIn the last RAN2#126 meeting, it was agreed to support the periodical reporting. It is currently FFS whether event-driven or “on-demand” approaches should be used. One could argue that, since there is no latency requirement involved in the transmission of the AIML-related collected data, a periodical reporting would be sufficient. We note however that in some cases the data collection could be stopped by the UE at any point in time. For example, the UE may become memory limited, or the UE may exit certain radio conditions such that the data collection would be stopped by the UE. In this case, it is useful if the UE could transmit the collected data or at least indicate to the network that the data collection is stopped. For example, if the UE stops the data collection due to UE memory becoming full, this is definitely an information that the network should know as soon as possible so that the network can start retrieving the data in order to free up the UE memory, and to avoid that the UE needs to skip the logging of some radio measurements. Hence, both the event-driven reporting of collected data and the on-demand report of collected data may be useful to allow the UE to quickly free up its memory, and continue the data collection. Further, the on-demand report gives to the gNB some further flexibility on when to get the collected data, especially as proposed in b if the collected data do not fit into one RRC message.Event-driven reporting of collected data at the stopping of data collection can be configured.On-demand reporting of collected data is supported.2.4 UE memory capabilitiesDuring the last RAN2 meetings, we have discussed at length the problem of UE memory limitations that may arise when performing the data collection. It was proposed to introduce a minimum memory requirement (as in MDT) for the AIML data collection, or to define in a UE capability the maximum memory that a UE can support for the logging of data related to NW- side data collection. The latter approach gives some more flexibility to the UE implementation. These two alternatives can be considered and discussed by RAN2.RAN2 to discuss the following options for defining UE memory limitations for a UE supporting the data logging: h. Introduce a minimum requirement on the UE memory size for the logging of data related to NW-side data collectioni. Define in a UE capability the maximum memory values that a UE can support for the logging of data related to NW-side data collection3 ConclusionIn the previous sections we made the following observations:Observation 1 UL RRC segmentation is used in legacy when the data to be transmitted are generated outside the RAN (i.e. as in QoE) and hence no control of the maximum supported size of a PDCP SDU can be guaranteed; or when the amount of IES to be transmitted in a single container is so large that the message exceeds the maximum supported side.Observation 2 In the logged MDT. the logged measurements stored by the UE are signalled in a list of logged measurement results (i.e. logMeasInfoLisf). TheUE implementation can determine how many entries to include in this list such that the maximum PDCP SDU size is not exceeded. No standardizedRRC segmentation procedure is specified.Observation 3 The reporting of AIML collected data for NW-side model training resembles the reporting of measurement results for logged MPT, because the collected data are generated at RAN level (unlike QoE). and the information associated to measurements results collcted at a given point in time do not exceed the maximum PDCP SDU supported size (unlike UECapability Information).Based on the discussion in the previous sections we propose the following:Proposal 1 The collected AIML-specific data stored by the UE are signalled in a list whose entries include information associated to radio measurements taken at different points in time (as for the logged MPT),Proposal 2 The UE implementation can determine how many entries to include in the list radio measurements information, such that the maximum PDCP SDU size is not exceeded. No standardized RRC segmentation procedure is specified (as for the logged MPT),Proposal 3 In case all the collected data do not fit into a single RRC message. RAN2 to discuss: a. Whether and how the UE should inform the network about remaining collected data to be transmitted. b. When the UE should transmit remaining collected data, e.g. in following RRC message(s) based on SRB priority, upon gNB request, at the next periodic transmission occasion, etc.Proposal 4 The UE should perform measurements based on a L3 configuration indicating the resources (CSI-RS / SSB) specifically configured for NW-side data collection purposes.Proposal 5 RAN2 to consider the following mechanisms for the starting of the NW- side data collection procedure: a. The UE starts the data collection upon receiving a L3 configuration for NW-side data collection b. The UE starts the data collection upon fulfilling certain events, e.g. the UE starts the data collection when it ends up in poor coverage regions.Proposal 6 RAN2 to consider the following mechanisms for the stopping of the NW- side data collection procedure: a. The UE continues data collection for a certain configurable time (as in logged MPT) b. The UE continues data collection until certain events are fulfilled, e.g. until the UE is in poor radio coverage reasons c. UE-side reasons, e.g. UE becoming memory limitedProposal 7 Event-driven reporting of collected data at the stopping of data collection can be configured.Proposal 8 On-demand reporting of collected data is supported.Proposal 9 RAN2 to discuss the following options for defining UE memory limitations for a UE supporting the data logging:a. Introduce a minimum requirement on the UE memory size for the logging of data related to NW-side data collection b. Define in a UE capability the maximum memory values that a UE can support for the logging of data related to NW-side data collection

Claims

CLAIMS1. A method performed by a user equipment for managing data collection, the method comprising: performing one or more actions to control a data collection session at the user equipment when one or more conditions are fulfilled, wherein the data collection session is a session in which data is collected for an artificial intelligence or machine learning, AI / ML, model.

2. The method of claim 1, wherein: performing the one or more actions to control the data collection session when the one or more conditions are fulfilled comprises: starting a first data collection session for a first time when one or more first conditions are fulfilled.

3. The method of claim 2, wherein: the one or more first conditions comprise any one or more of: a condition that a cell level measurement quantity of one or more cells is above or below a threshold, is within a range, or is different from another one or more cells; a condition that a beam level measurement quantity of one or more beams is above or below a threshold, is within a range, or is different from another one or more beams; a condition that the user equipment is at a predefined location; a condition that the user equipment starts a timer; a condition that a mobility event occurs, such as any one or more of Al, A2, A3, A4, A5, A6, Bl, and B2; a condition that the user equipment detects a mobility event, such as a handover failure or a radio link failure; a condition that the user equipment receives, from a network node, an indication to start the first data collection session; and a condition that the user equipment receives, from a network node, a Layer 3 (L3) configuration for the first data collection session.

4. The method of any of the preceding claims, wherein: performing the one or more actions to control the data collection session when the one or more conditions are fulfilled comprises: starting a first data collection session for a subsequent time when one or more second conditions are fulfilled.

5. The method of claim 4, wherein: the one or more second conditions comprise any one or more of: a condition that one or more third conditions for stopping the first data collection session are no longer fulfilled; and a condition that the user equipment receives a request, from a network node, to start the first data collection session for the subsequent time.

6. The method of any of the preceding claims, wherein: performing the one or more actions to control the data collection session when the one or more conditions are fulfilled comprises: starting a second data collection session when one or more fourth conditions are fulfilled, wherein the second data collection session is started subsequent to starting a first data collection.

7. The method of claim 6, wherein: the one or more fourth conditions comprise any one or more of: a condition that the user equipment stops the first data collection session; a condition that the user equipment transmits some or all of the data collected in the first data collection session; a condition that the user equipment receives, from a network node, a request to transmit the data collected in the first data collection session; and a condition that the user equipment discards the data collected in the first data collection session.

8. The method of any of the preceding claims, wherein: performing the one or more actions to control the data collection session when the one or more conditions are fulfilled comprises: stopping the data collection session when one or more third conditions arefulfilled.

9. The method of claim 8, wherein: stopping the data collection session comprises: stopping the data collection session permanently; or stopping the data collection session temporarily.

10. The method of claim 9, wherein: the one or more third conditions comprise any one or more of: a condition that the user equipment has reached a maximum storage capacity; a condition that a memory of the user equipment is full; a condition that the user equipment executes or completes a handover; a condition that the user equipment receives a release message; a condition that the user equipment exits an area of interest; a condition that the user equipment fulfils one or more radio conditions; a condition that a data collection timer expires; a condition that a mobility event, such as a handover failure or a radio link failure, is detected; a condition that the user equipment changes a mobility state or speed; and a condition that one or more conditions for starting the data collection session are no longer fulfilled.

11. The method of any of claims 8 to 10, the method comprising: transmitting, to a network node, information signalling that the data collection session has stopped.

12. The method of claim 11, wherein: the information signalling that the data collection session has stopped comprises any one or more of: information indicative of the one or more third conditions that are fulfilled; information indicative of a point in time at which the data collection session stopped; information indicative of the data collected in the data collection session before the data collection session stopped;information indicative of whether or not data collected in the data collection session is available for transmission; and information indicative of a memory status of the user equipment.

13. The method of any of the preceding claims, wherein: performing the one or more actions to control the data collection session when the one or more conditions are fulfilled comprises: discarding some or all of the data collected in the data collection session when one or more fifth conditions are fulfilled.

14. The method of claim 13, wherein: the one or more fifth conditions comprise any one or more of: a condition that one or more third conditions for stopping the data collection session are fulfilled; a condition that the user equipment fails to transmit, within a predefined time, the data collected in the data collection session; and a condition that the user equipment receives, from a network node, a request to release a first configuration associated with the data collection session.

15. The method of any of the preceding claims, the method comprising: storing the data in a memory of the user equipment according to a first configuration associated with the data collection session.

16. The method of any of the preceding claims, the method comprising: transmitting, to a network node, some or all of the data collected in the data collection session, wherein the data collected in the data collection session is transmitted according to a second configuration associated with the data collection session, and wherein the second configuration comprises one or both of: a periodicity for the transmission of some or all of the data collected in the data collection session; and at least one event for triggering the transmission of some or all of the data collected in the data collection session.

17. The method of any of the preceding claims, the method comprising: acquiring a first configuration for the data collection session, wherein the first configuration comprises the one or more conditions.

18. The method of claim 17, wherein: acquiring the first configuration comprises: retrieving the first configuration from a standard specification; or receiving the first configuration from a network node.

19. The method of claim 17 or 18, wherein: the first configuration enables the user equipment to store the data collected in the data collection session until the data is transmitted to a network node.

20. The method of any of claims 17 to 19, wherein: for each of the one or more conditions, the first configuration for the data collection session comprises an associated second configuration for the data collection session.

21. The method of claim 20, wherein: for a condition that a cell-level measurement is less than a threshold, the associated second configuration comprises a configuration for the user equipment to start the data collection session on one or more predefined cells; for a condition that the user equipment starts the data collection session at execution of a handover from a first network node to a second network node, the associated second configuration comprises a configuration for the user equipment to collect data on a different set of cells in the data collection session; and for a condition that the user equipment starts the data collection session upon receiving, from a network node, an indication to start the first data collection session, the associated second configuration comprises a configuration for the user equipment to collect data on one or more predefined beams in the data collection session.

22. The method of any of the preceding claims, wherein: the data collected in the data collection session comprises one or more radio measurements.

23. A user equipment, UE, comprising processing circuitry configured to cause the UE to:perform one or more actions to control a data collection session at the user equipment when one or more conditions are fulfilled, wherein the data collection session is a session in which data is collected for an artificial intelligence or machine learning, AI / ML, model.

24. The UE of claim 23, wherein the processing circuitry is configured to cause the UE to perform the method according to any of claims 2 to 22.

25. A computer program comprising instructions which, when executed by processing circuitry of a user equipment, cause the user equipment to perform the method according to any of claims 1 to 22.

26. A computer program product, embodied on a non-transitory machine-readable medium, comprising instructions which are executable by processing circuitry of a user equipment to cause the user equipment to perform the method according to any of claims 1 to 22.

Images