Method and apparatus for handling UE memory for data collection in a wireless communication system

Abstract

The disclosure relates to a 5G or 6G communication system for supporting a higher data transmission rate. Disclosed is a method of operating a UE communicatively coupled to a telecommunication network. The method comprises steps of the UE controlling one or more of data collection, logging or reporting based on one or more UE resource status, wherein the UE is configured to transmit, to a network entity, information for reporting a cause of a failure in case that the data collection fails, and wherein the UE is further configured to transmit, to the network entity, capability information associated with a UE condition comprising a UE memory status or a UE power status.

Description

METHOD AND APPARATUS FOR HANDLING UE MEMORY FOR DATA COLLECTION IN A WIRELESS COMMUNICATION SYSTEM

[0001] The present invention relates to techniques associated with managing and handling User Equipment, UE, memory in connection with data collection tasks, especially tasks associated with Artificial Intelligence / Machine Learning, AI / ML, data.

[0002] 5G mobile communication technologies define broad frequency bands such that high transmission rates and new services are possible, and can be implemented not only in "Sub 6GHz" bands such as 3.5GHz, but also in "Above 6GHz" bands referred to as mmWave including 28GHz and 39GHz. In addition, it has been considered to implement 6G mobile communication technologies (referred to as Beyond 5G systems) in terahertz (THz) bands (for example, 95GHz to 3THz bands) in order to accomplish transmission rates fifty times faster than 5G mobile communication technologies and ultra-low latencies one-tenth of 5G mobile communication technologies.

[0003] At the beginning of the development of 5G mobile communication technologies, in order to support services and to satisfy performance requirements in connection with enhanced Mobile BroadBand (eMBB), Ultra Reliable Low Latency Communications (URLLC), and massive Machine-Type Communications (mMTC), there has been ongoing standardization regarding beamforming and massive MIMO for mitigating radio-wave path loss and increasing radio-wave transmission distances in mmWave, supporting numerologies (for example, operating multiple subcarrier spacings) for efficiently utilizing mmWave resources and dynamic operation of slot formats, initial access technologies for supporting multi-beam transmission and broadbands, definition and operation of BWP (BandWidth Part), new channel coding methods such as a LDPC (Low Density Parity Check) code for large amount of data transmission and a polar code for highly reliable transmission of control information, L2 pre-processing, and network slicing for providing a dedicated network specialized to a specific service.

[0004] Currently, there are ongoing discussions regarding improvement and performance enhancement of initial 5G mobile communication technologies in view of services to be supported by 5G mobile communication technologies, and there has been physical layer standardization regarding technologies such as V2X (Vehicle-to-everything) for aiding driving determination by autonomous vehicles based on information regarding positions and states of vehicles transmitted by the vehicles and for enhancing user convenience, NR-U (New Radio Unlicensed) aimed at system operations conforming to various regulation-related requirements in unlicensed bands, NR UE Power Saving, Non-Terrestrial Network (NTN) which is UE-satellite direct communication for providing coverage in an area in which communication with terrestrial networks is unavailable, and positioning.

[0005] Moreover, there has been ongoing standardization in air interface architecture / protocol regarding technologies such as Industrial Internet of Things (IIoT) for supporting new services through interworking and convergence with other industries, IAB (Integrated Access and Backhaul) for providing a node for network service area expansion by supporting a wireless backhaul link and an access link in an integrated manner, mobility enhancement including conditional handover and DAPS (Dual Active Protocol Stack) handover, and two-step random access for simplifying random access procedures (2-step RACH for NR). There also has been ongoing standardization in system architecture / service regarding a 5G baseline architecture (for example, service based architecture or service based interface) for combining Network Functions Virtualization (NFV) and Software-Defined Networking (SDN) technologies, and Mobile Edge Computing (MEC) for receiving services based on UE positions.

[0006] As 5G mobile communication systems are commercialized, connected devices that have been exponentially increasing will be connected to communication networks, and it is accordingly expected that enhanced functions and performances of 5G mobile communication systems and integrated operations of connected devices will be necessary. To this end, new research is scheduled in connection with eXtended Reality (XR) for efficiently supporting AR (Augmented Reality), VR (Virtual Reality), MR (Mixed Reality) and the like, 5G performance improvement and complexity reduction by utilizing Artificial Intelligence (AI) and Machine Learning (ML), AI service support, metaverse service support, and drone communication.

[0007] Furthermore, such development of 5G mobile communication systems will serve as a basis for developing not only new waveforms for providing coverage in terahertz bands of 6G mobile communication technologies, multi-antenna transmission technologies such as Full Dimensional MIMO (FD-MIMO), array antennas and large-scale antennas, metamaterial-based lenses and antennas for improving coverage of terahertz band signals, high-dimensional space multiplexing technology using OAM (Orbital Angular Momentum), and RIS (Reconfigurable Intelligent Surface), but also full-duplex technology for increasing frequency efficiency of 6G mobile communication technologies and improving system networks, AI-based communication technology for implementing system optimization by utilizing satellites and AI (Artificial Intelligence) from the design stage and internalizing end-to-end AI support functions, and next-generation distributed computing technology for implementing services at levels of complexity exceeding the limit of UE operation capability by utilizing ultra-high-performance communication and computing resources.

[0008] The present disclosure relates to handling UE memory for data collection.

[0009] Aspects of the present disclosure provide efficient communication methods in a wireless communication system.

[0010] FIGURE 1 illustrates an example of the UE sending a resource report to the network in relation to a data collection procedure;

[0011] FIGURE 2 illustrates an example call flow according to an embodiment of the invention;

[0012] FIGURE 3 illustrates a flowchart illustrating an embodiment of the invention;

[0013] FIGURE 4 illustrates a block diagram illustrating a structure of a UE according to various embodiments of the present disclosure; and

[0014] FIGURE 5 illustrates a block diagram illustrating a structure of a network entity of a base station according to various embodiments of the present disclosure, as disclosed herein.

[0015] The present invention relates to techniques associated with managing and handling User Equipment, UE, memory in connection with data collection tasks, especially tasks associated with Artificial Intelligence / Machine Learning, AI / ML, data.

[0016] It is a topic of much debate exactly how to manage the potentially large amounts of AI / ML data generated and / or required in a telecommunication system, which seeks to make use of such data to optimise or improve the performance of the system.

[0017] In 3GPP meeting RAN2#123bis meeting, RAN2 agreed the following proposals on data collection [RAN2#123bis]:

[0018] "Proposal 4Related to gNB-centric data collection for NW-side model training, the following principles can be considered for the L3 signalling reporting framework, if used:

[0019] a.loggingis supported

[0020] c.periodic, event based reporting, on demand report

[0021] d.The UE memory, processing power, energy consumption, signalling overhead should be taken into account.

[0022] Note: The above principles, can be revised depending on RAN1 progress / requirements

[0023] Proposal 9Related to OAM-centric data collection for NW-side model training, the following principles can be considered for the immediate MDT framework, if used:

[0024] a.The Immediate MDT framework for NW-side model training should allow the UE to store sets of measurements and then report them in multiple RRC messages (e.g. similar to the logged MDT).

[0025] b.The Immediate MDT framework for NW-side model training should allow the UE to store multiple measurements taken at different points in time and report them in a single RRC report.

[0026] c.The Immediate MDT framework for NW-side model training should allow the network to configure the UE to report measurements periodically or upon fulfilling certain events.

[0027] d.The UE memory / processing power / energy consumption / signalling overhead should be taken into account.

[0028] Note: The above principles, for the immediate MDT framework, can be revised depending on RAN1 progress / requirements

[0029] Agreements on NW-side data collection

[0030] For CSI and beam management

[0031] 1For training of NW-side models, both gNB- and OAM-centric data collection are considered in the study.

[0032] 2For training of NW-side models, the gNB-centric data collection implies that the gNB configures the UE to initiate / terminate the data collection procedure. To further study the details of the data collection configuration

[0033] 3For training of NW-side models, an OAM-centric data collection implies that the OAM provides the configuration (via the gNB) needed for the UE to initiate / terminate the data collection procedure. MDT framework can be considered.

[0034] 4Related to gNB-centric data collection for NW-side model training, RAN2 studies the potential impact on L3 signalling for the reporting of collected data, taking into account RAN1 further inputs / progress.

[0035] 5Related to OAM-centric data collection for NW-side model training, RAN2 studies the potential impact at on the MDT for connected mode, taking into account RAN1 further inputs / progress

[0036] Positioning

[0037] For LMF sided inference (case 2b, case 3b), RAN2 assumes LPP protocol should be applied to the data collected by UE and terminated at LMF, while the NRPPa protocol should be applied to the data collected by gNB and terminated at LMF.

[0038] 8For LMF sided performance monitoring, RAN2 assumes LPP protocol should be applied to the data collected by UE and terminated at LMF, while the NRPPa protocol should be applied to the data collected by gNB and terminated at LMF.

[0039] General

[0040] 6Principles in proposal 4 and 9 will be captured as one combined set of principles for NW-side data collection:

[0041] logging is supported

[0042] periodic, event based reporting, on demand report

[0043] The UE memory, processing power, energy consumption, signalling overhead should be taken into account.

[0044] Note: The above principles, can be revised depending on RAN1 progress / requirements"

[0045] Additionally, in RAN plenary #102 (RAN#102), 3GPP RAN working groups will be looking in to the following objective as part of Rel-19 work item on AI / ML for NR Air Interface:

[0046] "4.1Objective of SI or Core part WI or Testing part WI

[0047] Provide specification support for the following aspects:

[0048] -AI / ML general framework for one-sided AI / ML models within the realm of what has been studied in the FS_NR_AIML_Air project [RAN2]:

[0049] -

[0050] oSignalling and protocol aspects of Life Cycle Management (LCM) enabling functionality and model (if justified) selection, activation, deactivation, switching, fallback

[0051] ■Identification related signalling is part of the above objective

[0052] oNecessary signalling / mechanism(s) for LCM to facilitate model training, inference, performance monitoring, data collection (except for the purpose of CN / OAM / OTT collection of UE-sided model training data) for both UE-sided and NW-sided models

[0053] oSignalling mechanism of applicable functionalities / models

[0054] -Beam management - DL Tx beam prediction for both UE-sided model and NW-sided model, encompassing [RAN1 / RAN2]:

[0055] oSpatial-domain DL Tx beam prediction for Set A of beams based on measurement results of Set B of beams ("BM-Case1")

[0056] oTemporal DL Tx beam prediction for Set A of beams based on the historic measurement results of Set B of beams ("BM-Case2")

[0057] oSpecify necessary signalling / mechanism(s) to facilitate LCM operations specific to the Beam Management use cases, if any

[0058] oEnabling method(s) to ensure consistency between training and inference regarding NW-side additional conditions (if identified) for inference at UE

[0059] NOTE: Strive for common framework design to support both BM-Case1 and BM-Case2

[0060] -Positioning accuracy enhancements, encompassing [RAN1 / RAN2 / RAN3]:

[0061] oDirect AI / ML positioning:

[0062] ■(1stpriority) Case 1: UE-based positioning with UE-side model, direct AI / ML positioning

[0063] ■(2ndpriority) Case 2b: UE-assisted / LMF-based positioning with LMF-side model, direct AI / ML positioning

[0064] ■(1stpriority) Case 3b: NG-RAN node assisted positioning with LMF-side model, direct AI / ML positioning

[0065] oAI / ML assisted positioning

[0066] ■(2ndpriority) Case 2a: UE-assisted / LMF-based positioning with UE-side model, AI / ML assisted positioning

[0067] ■(1stpriority) Case 3a: NG-RAN node assisted positioning with gNB-side model, AI / ML assisted positioning

[0068] oSpecify necessary measurements, signalling / mechanism(s) to facilitate LCM operations specific to the Positioning accuracy enhancements use cases, if any

[0069] oInvestigate and specify the necessary signalling of necessary measurement enhancements (if any)

[0070] oEnabling method(s) to ensure consistency between training and inference regarding NW-side additional conditions (if identified) for inference at UE for relevant positioning sub use cases

[0071] -Core requirements for the above two use cases for AI / ML LCM procedures and UE features [RAN4]:

[0072] oSpecify necessary RAN4 core requirements for the above two use cases.

[0073] oSpecify necessary RAN4 core requirements for LCM procedures including performance monitoring.

[0074] Study objectives with corresponding checkpoints in RAN#105 (Sept '24):

[0075] -CSI feedback enhancement [RAN1]:

[0076] oFor CSI compression (two-sided model), further study ways to:

[0077] ■Improve trade-off between performance and complexity / overhead

[0078] ·e.g., considering extending the spatial / frequency compression to spatial / temporal / frequency compression, cell / site specific models, CSI compression plus prediction (compared to Rel-18 non-AI / ML based approach), etc.

[0079] ■Alleviate / resolve issues related to inter-vendor training collaboration.

[0080] while addressing other aspects requiring further study / conclusion as captured in the conclusions section of the TR 38.843.

[0081] oFor CSI prediction (one-sided model), further study performance gain over Rel-18 non-AI / ML based approach and associated complexity, while addressing other aspects requiring further study / conclusion as captured in the conclusions section of the TR 38.843 (e.g., cell / site specific model could be considered to improve performance gain).

[0082] -Necessity and details of model Identification concept and procedure in the context of LCM [RAN2 / RAN1]

[0083] -CN / OAM / OTT collection of UE-sided model training data [RAN2 / RAN1]:

[0084] oFor the FS_NR_AIML_Air study use cases, identify the corresponding contents of UE data collection

[0085] oAnalyse the UE data collection mechanisms identified during the FS_NR_AIML_Air (TR 38.843 section 7.2.1.3.2) study along with the implications and limitations of each of the methods

[0086] -Model transfer / delivery [RAN2 / RAN1]:

[0087] oDetermine whether there is a need to consider standardised solutions for transferring / delivering AI / ML model(s) considering at least the solutions identified during the FS_NR_AIML_Air study

[0088] -Testability and interoperability [RAN4]:

[0089] oFinalize the testing framework and procedure for one-sided models and further analyse the various testing options for two-sided models, in collaboration with RAN1, and including at least:

[0090] ■Relation to legacy requirements

[0091] ■Performance monitoring and LCM aspects considering use-case specifics

[0092] ■Generalization aspects

[0093] ■Static / non-static scenarios / conditions and propagation conditions for testing (e.g., CDL, field data, etc.)

[0094] ■UE processing capability and limitations

[0095] ■Post-deployment validation due to model change / drift

[0096] oRAN5 aspects related to testability and interoperability to be addressed on a request basis"

[0097] The logging and reporting of UE measurements of AI / ML data will significantly increase the usage of UE memory, processing power and energy consumption. One issue associated with this is that the UE (or UEs) may fail to collect, store, and / or report the requested data if the UE(s) run(s) out of memory, processing power and / or energy. This problem has been identified by 3GPP RAN working group as set out above. However, there is currently no solution available for how the UE behaves when its resources become depleted with respect to AI / ML data collection, storing & reporting.

[0098] It is an aim of embodiments of the present invention to regulate or control the behaviour of the network and / or the UE in order to handle the UE logging and reporting of AI / ML data in the event of UE limitations of memory, processing power, and / or energy.

[0099] According to the present invention there is provided an apparatus and method as set forth in the appended claims. Other features of the invention will be apparent from the dependent claims, and the description which follows.

[0100] According to a first aspect of the present invention, there is provided a method of operating a User Equipment, UE, communicatively coupled to a telecommunication network, comprising the step of the UE controlling one or more of data collection, logging or reporting, based on one or more UE resource status.

[0101] In an embodiment, the data collection, logging or reporting is connected with AI / ML data used in UE or network optimisation.

[0102] In an embodiment, the UE is configured by the telecommunication network taking into account at least one property of the UE.

[0103] In an embodiment, the at least one property comprises UE capabilities, UE type, UE subscription information, or UE local resources.

[0104] In an embodiment, the UE reports its resource status to the telecommunication network periodically or on demand.

[0105] In an embodiment, the UE reports its resource status either separately or together with the collected data.

[0106] In an embodiment, the UE indicates a failure to perform a configuration for data collection, data logging, and / or data reporting, due to local resources status.

[0107] In an embodiment, the UE pauses or stops data collecting, logging or reporting in the event of a resource threshold being reached.

[0108] In an embodiment, the UE resumes data collecting, logging or reporting in the event of resources becoming available again.

[0109] In an embodiment, the resource threshold relates to one or more of memory or buffer status, processing power, battery life or power consumption.

[0110] According to a second aspect of the present invention, there is provided apparatus arranged to perform the method of the first aspect.

[0111] Aspects of the invention can be considered as follows.

[0112] · The network determines and / or configures the behaviour of the desired UE (or multiple UEs) for data collection considering, for example, the UE(s) capabilities, UE(s) type, UE subscription information, and / or UE local resources. In one example, the UE memory, processing power, energy consumption level, etc.

[0113] · All interactions (or actions) between the UE and the network (e.g. actions such as: requests, responses, feedback, recommendations, commands, indications, reporting, etc.) may occur using new and / or existing RRC signalling, procedure, messages, and / or IEs.

[0114] · All interactions (or actions) between the UE and the network (e.g. actions such as: requests, responses, feedback, recommendations, commands, indications, reporting, etc.) may occur using new and / or existing NAS signalling, procedure, messages, and / or IEs.

[0115] · All proposals in this invention can apply to any type of resource e.g. UE memory, processing power, local resources, and / or power consumption, battery charge, etc.

[0116] · All (or part of) proposals are made using memory as an example, but all proposals (or part of) are not necessarily restricted to memory only and can be therefore applied to other resources in the UE such e.g. processing power, power consumption, battery charge, and / or any other UE local resources, etc.

[0117] · All (or part of ) proposals can be applied in any order and combination. As such there may be solutions that are based on network and UE proposals in an individual or combined manner

[0118] · All (or part of) proposals are not limited to 5G system only.

[0119] · All (or part of) proposals herein apply in any order and / or combination and can apply to 5GS or any other system, e.g. 4G, 6G, IoT, NTN, IoT NTN, dual connectivity, etc.

[0120] · All proposal herein apply to any RAN entity (and / or function) maybe a RAN node (e.g. NG-RAN, gNB, eNB, etc.).

[0121] · All proposal herein apply to the any core network entity (and / or function) e.g. AMF, SMF, MME, UPF, UDM, NWDAF, etc.

[0122] · In all proposals the use of "data collection, logging, and / or reporting" can refer to all traffic types or AI / ML traffic type or a combination of such traffic types.

[0123] · In all proposals the term "data collection task", may refer to data collection, data logging, and / or data reporting steps / tasks / procedures.

[0124] Although a few preferred embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes and modifications might be made without departing from the scope of the invention, as defined in the appended claims.

[0125] For a better understanding of the invention, and to show how embodiments of the same may be carried into effect, reference will now be made, by way of example only, to the accompanying diagrammatic drawings in which:

[0126] FIGURE 1 illustrates an example of the UE sending a resource report to the network in relation to a data collection procedure;

[0127] FIGURE 2 illustrates an example call flow according to an embodiment of the invention; and

[0128] FIGURE 3 illustrates a flowchart illustrating an embodiment of the invention.

[0129] In the following embodiments are described which are provided for handling data collection, logging and reporting of collected AI / ML data according to the UE memory status / requirements.

[0130] Herein, the mention of UE memory status, UE memory, UE storage, may refer to (or mean), for example, memory storage status, current storage, remaining storage, storage level, storage level, storage upper and / or lower threshold or bound, maximum storage, minimum storage, storage below a given level, storage above a given level, storage between two levels, absolute storage level, used storage, corrupted storage, functioning storage, deleted (or released or erased) storage and / or time (and / or location) of deleting this memory, and / or other storage description etc. The storage may refer to overall storage in the UE which is used by more than one local entity, or it may refer to storage that is dedicated for AI / ML data collection and / or processing. Moreover, resource status, may refer to (or mean), for example, remaining resource, consumed resource, reserved resource, allocated (or assigned) resource, required resource, resource level (or threshold or upper or lower bound), maximum (and / or minimum) resource, damaged or unavailable resource, etc.

[0131] Similar to the memory status referred to above, the mention of UE resource status, may refer (or mean), for example, resources such as (but not limited to): memory, power (or battery charge, or power consumption), processing power, and / or other UE resources.

[0132] The following relates to UE capability exchange with the network. It is known in the prior art that the UE and the associated network may exchange certain details of capabilities. The following are new capabilities that the UE and the network can exchange with each other, according to one or more embodiments of the present invention:

[0133] · The UE indicates (or reports) its capability (optionally) to the network about its support for reporting of UE memory and / or other local resources;

[0134] · The UE indicates (or reports) its capability (optionally) to the network about its support for resource management (e.g. resource allocation, re-allocation, release, modify allocation, etc.), during (or for) the data collection, data logging (or storing) and / or data reporting tasks (or procedures). In one example, the UE manages the memory (e.g. store, delete, etc.) for logging data;

[0135] · The UE sends (or reports) any of the proposed capability (optionally) to the network periodically, upon request from the network (e.g. AMF, or RAN, etc.), and / or provides it to the network as part of (or during) the UE connection (re-)establishment with the network;

[0136] · The network indicates (or reports) it capability, (optionally) to the UE, to support configuration and handling of data collection, data logging, and / or data reporting tasks (or procedures), according to UE's local resources (e.g. UE memory). For example, capability to request reports of UE resources, capability to configure a data collection task (e.g. data size, latency, etc.) according to the UE's local resource (e.g. UE memory and / or battery, etc.);

[0137] · The UE and the network capabilities can be exchanged (or reported) using existing UE and network capabilities exchange signaling (e.g. RRC and / or NAS signaling / messages / IEs), any other suitable signaling, and / or any newly defined signaling (e.g. RRC and / or NAS signaling / messages / IEs);

[0138] o In another example, the UE reports its capabilities using (or as part of) UEAssistanceInformation;

[0139] · In one example, on the UE capability exchange with the network, the UE capability can be exchanged with the network using (or as part of) UE capability transfer procedure.

[0140] The following relates to Network configuration for UE logging and / or reporting based on UE resource.

[0141] The following applies for data collection, logging and / or reporting, in any combination or order, unless explicitly stated otherwise. Note that any reference to "memory" is not to be considered as restrictive to memory only and may apply to any UE resource such as power, etc.

[0142] 1) The network controls (or decides or determines) the UE behavior for data collection, logging, reporting via direct signaling (e.g. SIBs, NAS, RRC, MAC CE, etc.) and / or configurations. Optionally, the network may decide the configuration according to the UE reported capability (e.g. capability related to data collection, logging, and / or reporting, or another existing or newly defined UE capability), UE category, UE location, time, and / or subscription, etc. In one example, a selected set (one or more) of UEs can be capable to support data logging according to network configuration (and / or control). In another example, the configuration may be related to memory usage for data collection reporting amongst other resources in the UE (e.g. power consumption).

[0143] 2) The network provides configurations to the UE and it is up to the UE how to handle the different steps (or processes) of data collection, logging, and / or reporting according to its local resources (e.g. UE memory status). For example, the network indicates that the UE can decide what to do when the UE determines that the memory is full (or at a given percentage or proportion of usage / allocation of resources). In another example, the UE assesses the remaining or free memory that is still available, or the memory which has been used, where this memory may be overall UE memory or dedicated memory for AI / ML data collection and / or processing. Based on this, the UE may determine what to do in terms of data collection and / processing for AI / ML e.g. to stop data collection, report the logged data (e.g. full or in part), delete all data (or part of the data), report memory status, etc.

[0144] 3) The network may configure the UE data collection task, e.g. data collection size, use case, latency, data logging amount, time, etc., according to the UE reported UE memory status. For example, if the network had previously configured the UE to report data of size, say, X Bytes, then the network may now configure the UE to report data of size P Bytes where P is less than X. This may happen when for example the UE reports that it has less memory that is available. Alternatively, if the UE reports an increase in its available memory, the network may reconfigure the UE to report data size Y Bytes where Y is larger than X (which may be the previous size configured by the network).

[0145] 4) The network provides, as part of the (re)-configurations for the UE, information (or parameters) related to the collected data, such as: data size, data latency, data QoS characteristics (or QoS profile), data reporting timing and periodicity, reporting triggers (in case of not periodic reporting), e.g. reporting data in X Megabytes, Y msec, etc., where X and Y are positive real numbers defined by the network, in another example, defined by the UE and / or the Network).

[0146] 5) The network configures the UE to indicate (or report) one (or more or combination) of the following in relation to AI / ML data collection:

[0147] a. The UE’s current memory status and / or expected memory status after a given time instance. Optionally, additionally, using same or separate messaging (and / or IEs) to indicate (or report) other UE’s resource(s) status (e.g. power status).

[0148] b. In another example, the UE report the memory status when reaching a certain storage level or threshold, e.g. at or after 50% has been used, or after the memory is full or close to becoming full. Or the network configures the UE to report when the UE’s memory changes by a certain level or threshold, or crosses a certain level or threshold.

[0149] c. The status of the logged data, e.g. data logged in full, logged partially, or logging is complete, or incomplete, data is released (or erased, deleted) or will be updated or released at a given time period, etc. For example, data logged in full may refer to data that is logged based on a known size. As such, logged data which is not full.

[0150] 6) The network configures the UE to wait (or postpone or delay) reporting for complete log or log a certain amount (or data size) and then start reporting. In another example, for the UE to only trigger the reporting when a complete data logging (or a certain amount of data logging) is reached before starting to report the logged data to the network.

[0151] 7) The network indicates (or configures or informs) the UE that when data logging (or logged data size) exceeds certain threshold (or preconfigured or assigned parameters), report this event, if possible (e.g. the UE is in RRC connected mode).

[0152] 8) The network configures the UE to record the number of times (frequency, or how frequent) the UE failed to log the data completely (or partially) or not log according to a set of network configurations of the data collection and logging, for example, data logging according up to a specific time or specific measurements and / or specific time logging window.

[0153] 9) The network decides (or controls) and / or configures the UE behavior under (or during) resource shortage (e.g. memory shortage) to complete the data collection in the UE. For example, the network configures one or more of the following UE behaviors:

[0154] a) The UE to trigger the report of resource shortage (e.g. ‘no memory’ upon detection of insufficient memory or unavailable memory resource) required (or needed) to complete the data collection, logging and reporting, according to the originally configured data collection task (e.g. data size, latency, periodicity of data reporting, etc.).

[0155] b) The UE to send the collected data (or stored or logged data) and indicate to the network the case of reporting of incomplete data (or incomplete data collection task) due to resource shortage (or unavailability or not enough of resources) to complete the data collection task as requested by the network or in another example as required by the data collection task.

[0156] c) The time duration for the event (or situation or condition) of lack of (or shortage or unavailability of) resource before the UE should flag (or indicate or report) this issue to the network. For example, the UE should wait T seconds during which lack of resources is still ongoing and after T seconds then the UE should report the lack of memory. In other words, the network may configure the UE to report a lack of a certain resource but only after a duration of time elapses while the resource is deemed to be still lacking.

[0157] d) The UE to wait until resources become available again. In another example, postpone data collection, logging and / or reporting until resources are available (or available again). In another example, resources are available to complete the data collection, logging, and / or reporting task (or procedure). The UE may save all logged data and potentially augment (or combine or amend, etc.) them with more data when the logging is resumed later.

[0158] e) The UE to tag the time from the start to end of the case of resource shortage (or unavailability) ? hence tag pause or resume time of data log. The UE may report this information.

[0159] f) The UE to stop (or pause) data collection (logging and / or reporting) based on a request from the network. In one example, the network may request (or command) the UE to stop (or pause) data collection (logging and / or reporting) considering the UE reports on resource status (e.g. UE memory). In one example, the UE reported that the UE memory is at X% (or above a given threshold and / or upper bound, etc.) of memory storage usage, then the network informs the UE to stop (or pause) data collection (logging and / or reporting) until the time instance when the memory status is less than X% (or another level below initially reported level) before the UE can re-start or resume data collection task. In one example, the network can inform or command the UE using new and / or existing RRC signaling / messages / IEs (e.g. RRC Reconfiguration). Additionally, in the case that the UE re-starts data collection (logging and / or reporting), the UE may or may not delete (or release memory resources) previously logged. In another example, the UE may combine the logged data with the newly collected data after the UE resumes the data collection task. In an alternative example, the network may configure the UE to stop data collection and delete logged data or pause data collection and delete or combine logged data with data to be collected after the UE resume data collection task.

[0160] g) The UE to start or resume data collection tasks after a given period of time (e.g. expiry of preconfigured T-resume; value is integer of ms) of the UE memory becoming available for data collection (e.g. start new data collection or resume an ongoing data collection task).

[0161] h) The UE to stop data collection (logging and / or reporting) after a given time period (e.g. expiry of preconfigured T-stop; value is integer of ms) from the start of the event (or case) of resource shortage (e.g. no memory or memory status) at the UE. In another example, to stop data collection after a given period of time from the UE reporting the event (or case) of resource shortage (e.g. no memory or memory status) to the network. Additionally, the UE may delete the logged data upon the expiry of the given timer (e.g. T-stop, or any other suitable naming).

[0162] i) Configures how the UE should manage resources (e.g. memory storage or usage, etc.) in the case of resource shortage, taking into considerations of: (i) the purpose of the collected data and / or (ii) the use case of the collected data.

[0163] ■ The data collection for life-cycle-management (LCM) purpose of a model (or functionality), such as data collection for the LCM purpose of monitoring, inference or training, etc., of a model (or functionality). In one example, in the case of memory shortage, the UE may continue to log data collected for the LCM purpose of model (or functionality) monitoring, while the UE would release memory resource storing data collected for other LCM purposes (e.g. training, etc.).

[0164] ■ In another example, the UE may release any logged data collected for a given use case and maintain and / or continue logging data collected for a different use case, if logging is possible (or as long as logging data is still possible, assuming that more memory resources are available due to releasing resources previously used for other data), e.g. release data collected for load balancing, CSI prediction, CSI compression, beam management, positioning and / or energy saving, etc., and keep logging data collected for mobility optimization, etc.

[0165] · The network may request a success and / or failure report(s) on completion of the data collection (and / or logging) requested from the UE. In one example, based on those reports the network may reconfigure the data collection (and / or logging) tasks for the UE based on those reports. In one example, the network may adjust / modify (e.g. reduce or increase) the requested data collection size (e.g. measurements parameters collection periods or number of collected parameters, etc.) or adjust other parameters (or information) related to the collected data (e.g. latency, LCM purpose, etc.) for the desired UE.

[0166] · In one example, the Network may reconfigure requirements for data size logging based on this indication, or increase periodicity of data reporting.

[0167] · The network may perform access barring to one (or more or all UEs) from collecting and / or reporting data, and delete or flush or pause all data collection in the network. In one example, access barring introduced as part of exiting or newly defined SIB.

[0168] Note that for all the details herein, any unit of time or memory or any other resources is to be considered as an example only.

[0169] The following relates to UE behavior for data collection, logging and / or reporting based on resource status.

[0170] Note that details set out above in relation to the network behaviour can be implement in whole or in part as a UE based solution without the need for network configuration.

[0171] · The UE monitors resources for AIML data and / or reporting

[0172] o The UE may have local policies, or (pre-)configurations that a certain portion (or all) of its resources may be used for AIML related procedures (e.g. LCM purposes) or data collection, logging and / or reporting for AI / ML.

[0173] o The UE monitors the resource allocation for upcoming (or requested or instructed by the network) data collection tasks. For example, the UE monitors if current available resources are enough to assign for AIML data collection, logging, and / or reporting, based on information received related to this data. In one example, data size, latency, priority, LCM purpose, QoS profile / characteristics, other information related to the collected data.

[0174] ■ (For cases where resources are not enough for logging process - i.e. logging process not started) the UE indicates that it does not have enough resource to complete the requested data logging (or data collection, logging, and / or reporting) task. The UE may also report how much data size has been logged and / or how much memory is missing to complete the task

[0175] ■ This is the case of UE just reporting the problem of not enough (or lack of) resources to perform the data collection, logging and / or reporting task.

[0176] · Basically UE reports lack of resources or

[0177] · Potential memory failure case

[0178] o The UE monitors if resource usage for AI / ML has gone up or down e.g. based on a predefined threshold

[0179] ■ In one example, the threshold may be:

[0180] · preconfigured in the UE or received from the network via any form of existing and / or newly defined signalling (e.g. RRC and / or NAS signaling / messages / IEs or locally) and / or via system broadcast (e.g. periodically and / or on-demand), e.g. using existing and / or newly defined SIBs

[0181] · selected by the UE, e.g. based on UE resource status or other local policies, or preconfigured by and external entity (or application function, etc.) or via OAM.

[0182] · jointly decided (or selected) by the UE and the network.

[0183] ■ When the condition or threshold (on data logging) is met, the UE can behave in one or more (or combination of the following manners:

[0184] · (For cases where resources or logging process is started)

[0185] o the UE indicates it has already collected data and not possible to collect / log more. This is an example of how the UE just reports the problem

[0186] o The UE pauses data collection, and may report pause. Additionally, the UE re-monitors and may report restart when the condition of resource shortage is ended (i.e. resources available again). The UE may resume data collection and / or logging when its resources are available again

[0187] o the UE sends what it has logged already, unless the network configure the UE to log fully (UE may decides to send what it has in the case that UE detects the case of memory shortage).

[0188] o the UE monitors and / or decides that the resources have not been available for a time period T, where T may be preconfigured or provided by the network.

[0189] o The UE may periodically report its memory usage e.g. based on configurations by the network to do so

[0190] ■ The network may use this report to determine if the UE in question should continue to collect and / or report data. For example, a UE which reports critically low memory may be informed by the network to stop reporting until the memory usage is gone down, or until a certain memory is available (using any units to provide such indications). Note that these proposals can also apply to other UE resources such as power. As such, the UE may report low power and the network may indicate to the UE that reporting should be stopped and optionally resumed when the power goes above, for example, 50%, etc.

[0191] o In one example, the UE reporting of memory status happens (or triggered) at the expiry of a timer configured by the network. In another example the UE reporting of the logged data is triggered when the UE memory status (or storage) reaches a preconfigured threshold (or upper bound), or a lower bound of memory storage, etc. Optionally, the UE may indicate the reason why the UE stopped the data collection (and / or logging) before the full data collection due to UE memory storage reason (e.g. NotEnoughMemory, or any other suitable naming or cause value).

[0192] o The UE reports, in addition to (or separate from) the logged data, the memory status, for example, using the same or separate signals (or messages (or IEs).

[0193] o The UE may indicate its current UE memory status, including how much memory or storage is available for another data collection to the network, so that the network may consider this information when configuration the next data collection (and / or logging) tasks at the UE. The indication may be in any form such as: absolute memory that is remaining, absolute memory that has been used, a percentage of remaining memory, a percentage of used memory, where optionally any of this may be for AIML data collection and / or processing or for overall usage of resource in the UE (optionally not necessarily just for AIML data collection and / or processing).

[0194] o The UE may decide autonomously or based on assistance information from the network (e.g. configurations or other information or commands) to stop collection (and / or logging) of data if it determines that the UE memory status will not be enough to perform the full (or part of) the requested data collection task. Additionally, the UE informs the network of its failure to collected (and / or log or perform this task) due to it is current (and / or predicted) memory status. In one example, the UE may keep, or delete any collected (and / or logged data) at this stage, or send the collected data to the network and then delete this data.

[0195] o The UE may indicate that it does not have enough power to process the configured (or requested) data collection (and / or logging) task, and may recommend a different data collection (and / or logging) task according to the UE's memory status (e.g. remaining UE storage or other local resources status).

[0196] · The UE autonomously handles the different steps of data collection, logging, and / or reporting according to its local resources (e.g. UE memory status) or policies that describe the UE behaviour under resource constraints or shortages:

[0197] o The UE may indicate, in addition to the reported (or sent) data (or part of data), the UE memory status at the time of data reporting, where this time may be tagged by the UE as part of the memory reporting. Optionally the network may tag a time for each reported UE memory status in order to see any pattern in UE memory usage.

[0198] o In one example, the UE indicates that it only collected (and / or logged) part of the data requested for collection (and / or logging) by the network. Optionally, the UE may include with this indication the reason of this action as related to the memory status, e.g. not enough memory to store all requested data. For example, the UE may be configured to report data of a certain size, say X megabytes (or any other unit). However, the UE's collected data has a size of less than X megabyte where this is a result of lack of UE memory. The UE may report the collected data and indicate a reason for the lack of the complete data size where the reason may be to lack of resources such as memory, power, etc.

[0199] · For cases when the UE wants to admit a new data collection and / or data log processes (or tasks), e.g. based on network indication, the UE may:

[0200] ■ Reject the network's request and indicate reason (e.g. lack of memory resources to complete the requested task, e.g. reuse existing cause value or a newly defined, NoMemoryResource, MemoryResourceShortage, or any other suitable naming).

[0201] ■ Report log is delayed or postponed. Optionally, indicate the time when the log will be available.

[0202] ■ Report that log is full, or report the percentage of resource which is full (or available) for another more important or higher priority tasks, e.g. related to other exchanged traffic with the network (MO, MT, or other traffic).

[0203] · A UE capable of providing memory status (and / or any other local resources) information in RRC_CONNECTED state may initiate the UE Assistance information procedure, to provide the indication of memory status to the network, if it was configured to do so, upon detecting memory status problem if the UE is not able to collect or log more data, since it was configured to provide memory status indications, or upon change of memory status or memory status problem information.

[0204] All (or part of) above details are applicable to the case of power resource shortage (e.g. battery charge shortage, etc.). In one example, the UE may indicate that it does not have enough power to process the configured (or requested) data collection (and / or logging) task.

[0205] FIGURE 1 illustrates an example of the UE sending a resource report to the network in relation to data collection procedure. This is illustrative of a change which may be made to 3GPP TS 38.331.

[0206] The purpose of this procedure is to transfer from the UE to the Network (e.g. NG-RAN) information on the status of UE's resources in relation to data collection procedure at the UE.

[0207] The specific information transferred in this message may include one (or more) of the following:

[0208] - The data collection process:

[0209] · Includes information on the status of the collected data (e.g. complete, incomplete, partial, etc.),

[0210] · e.g. DataCollectionReport (or any other suitable naming)

[0211] - The data logging process;

[0212] · Including status of data logging process (e.g. partial, complete, success, failure, postponed, stopped, resumed, started, or stopped, etc.)

[0213] - The UE's memory:

[0214] · Including status of UE memory (e.g. full, available, not storage, storage, % of storage available or used, etc.

[0215] · UEMemoryStaus IE;

[0216] Note that the UEResourceReport message or ResourceReport message (or any other suitable naming) message may also include the collected data (or UE measurements). In one example, AI / ML data (or AI / ML measurements or measurement results).

[0217] In an alternative example, the UE may report the collected data (or UE measurement results) in a separate procedure. In one example, the report is sent based on the network request or triggered by a change in the UE's resource status.

[0218] Note that the above example, also applies to providing information on the reporting the UE's resource status in general, e.g. processing power, power or battery charge, other.

[0219] FIGURE 2 illustrates an example call flow, illustrating at least one embodiment described herein.

[0220] It should be noted that the call flow of FIG. 2 is based on the proposals above and hence should be considered as an example of how the proposed solutions can be used. As such other actions for the UE or the network may also be used in any order or combination in addition to the call flow shown above. The UE behavior may be based on network configuration or may be based on local decision in the UE (e.g. autonomous UE behavior) and therefore the actions taken by the UE may not necessarily be based on a previous message from the network or based on specific indications from the network. All other proposals herein may also be used and the steps shown above may be used in different order and combination.

[0221] FIGURE 3 illustrates a flowchart illustrating an embodiment of the invention. FIG. 3 illustrates an embodiment of the invention where at step S101, the UE is communicatively coupled to a telecommunication network and at step S102 the UE controls one or more of data collection, logging or reporting, based on one or more UE resource status.

[0222] FIGURE 4 illustrates a block diagram illustrating a structure of a UE according to various embodiments of the present disclosure.

[0223] As shown in FIG. 4, the UE according to an embodiment may include a transceiver 410, a memory 420, and a processor (e.g. controller) 430. The transceiver 410, the memory 420, and the processor 430 of the UE may operate according to a communication method of the UE described above. However, the components of the UE are not limited thereto. For example, the UE may include more or fewer components than those described above. In addition, the processor 430, the transceiver 410, and the memory 420 may be implemented as a single chip. Also, the processor 430 may include at least one processor.

[0224] The transceiver 410 collectively refers to a UE receiver and a UE transmitter, and may transmit / receive a signal to / from a network entity or a base station. The signal transmitted or received to or from the network entity or the base station may include control information and data. The transceiver 410 may include a RF transmitter for up-converting and amplifying a frequency of a transmitted signal, and a RF receiver for amplifying low-noise and down-converting a frequency of a received signal. However, this is only an example of the transceiver 410 and components of the transceiver 410 are not limited to the RF transmitter and the RF receiver.

[0225] Also, the transceiver 410 may receive and output, to the processor 430, a signal through a wireless channel, and transmit a signal output from the processor 430 through the wireless channel.

[0226] The memory 420 may store a program and data required for operations of the UE. Also, the memory 420 may store control information or data included in a signal obtained by the UE. The memory 420 may be a storage medium, such as read-only memory (ROM), random access memory (RAM), a hard disk, a CD-ROM, and a DVD, or a combination of storage media.

[0227] The processor 430 may control a series of processes such that the UE operates as described above. For example, the transceiver 410 may receive a data signal including a control signal transmitted by the network entity or the base station, and the processor 430 may determine a result of receiving the control signal and the data signal transmitted by the network entity or the base station.

[0228] FIGURE 5 illustrates a block diagram illustrating a structure of a network entity or a base station according to various embodiments of the present disclosure.

[0229] As shown in FIG. 5, the network entity or the base station according to an embodiment may include a transceiver 510, a memory 520, and a processor (e.g. controller) 530. The transceiver 510, the memory 520, and the processor 530 of the network entity or the base station may operate according to a communication method of the base station described above. However, the components of the network entity or the base station are not limited thereto. For example, the network entity or the base station may include more or fewer components than those described above. In addition, the processor 530, the transceiver 510, and the memory 520 may be implemented as a single chip. Also, the processor 530 may include at least one processor.

[0230] The transceiver 510 collectively refers to a receiver and a transmitter, and may transmit / receive a signal to / from a UE. The signal transmitted or received to or from the UE may include control information and data. The transceiver 510 may include a RF transmitter for up-converting and amplifying a frequency of a transmitted signal, and a RF receiver for amplifying low-noise and down-converting a frequency of a received signal. However, this is only an example of the transceiver 510 and components of the transceiver 510 are not limited to the RF transmitter and the RF receiver.

[0231] Also, the transceiver 510 may receive and output, to the processor 530, a signal through a wireless channel, and transmit a signal output from the processor 530 through the wireless channel.

[0232] The memory 520 may store a program and data required for operations of the network entity or the base station. Also, the memory 520 may store control information or data included in a signal obtained by the network entity or the base station. The memory 520 may be a storage medium, such as read-only memory (ROM), random access memory (RAM), a hard disk, a CD-ROM, and a DVD, or a combination of storage media.

[0233] The processor 530 may control a series of processes such that the network entity or the base station operates as described above. For example, the transceiver 510 may receive a data signal including a control signal transmitted by the UE, and the processor 530 may determine a result of receiving the control signal and the data signal transmitted by the UE.

[0234] At least some of the example embodiments described herein may be constructed, partially or wholly, using dedicated special-purpose hardware. Terms such as 'component', 'module' or 'unit' used herein may include, but are not limited to, a hardware device, such as circuitry in the form of discrete or integrated components, a Field Programmable Gate Array (FPGA) or Application Specific Integrated Circuit (ASIC), which performs certain tasks or provides the associated functionality. In some embodiments, the described elements may be configured to reside on a tangible, persistent, addressable storage medium and may be configured to execute on one or more processors. These functional elements may in some embodiments include, by way of example, components, such as software components, object-oriented software components, class components and task components, processes, functions, attributes, procedures, subroutines, segments of program code, drivers, firmware, microcode, circuitry, data, databases, data structures, tables, arrays, and variables. Although the example embodiments have been described with reference to the components, modules and units discussed herein, such functional elements may be combined into fewer elements or separated into additional elements. Various combinations of optional features have been described herein, and it will be appreciated that described features may be combined in any suitable combination. In particular, the features of any one example embodiment may be combined with features of any other embodiment, as appropriate, except where such combinations are mutually exclusive. Throughout this specification, the term "comprising" or "comprises" means including the component(s) specified but not to the exclusion of the presence of others.

[0235] Attention is directed to all papers and documents which are filed concurrently with or previous to this specification in connection with this application and which are open to public inspection with this specification, and the contents of all such papers and documents are incorporated herein by reference.

[0236] All of the features disclosed in this specification (including any accompanying claims, abstract and drawings), and / or all of the steps of any method or process so disclosed, may be combined in any combination, except combinations where at least some of such features and / or steps are mutually exclusive.

[0237] Each feature disclosed in this specification (including any accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise. Thus, unless expressly stated otherwise, each feature disclosed is one example only of a generic series of equivalent or similar features.

[0238] The invention is not restricted to the details of the foregoing embodiment(s). The invention extends to any novel one, or any novel combination, of the features disclosed in this specification (including any accompanying claims, abstract and drawings), or to any novel one, or any novel combination, of the steps of any method or process so disclosed.

Claims

1.A user equipment (UE) in a wireless communication system, the UE comprising:a transceiver; anda controller coupled with the transceiver, and configured to:receive, from a network entity, first information configuring a data collection for an artificial intelligence (AI) model, andtransmit, to the network entity, second information for reporting logged data, based on the first information.2.The UE of Claim 1, wherein the controller is further configured to:in case that the data collection fails, transmit, to the network entity, third information for reporting a cause of a failure.3.The UE of Claim 1, wherein the controller is further configured to:transmit, to a network entity, capability information associated with a UE condition comprising a UE memory status or a UE power status.4.The UE of Claim 3, wherein the first information is based on the capability information.5.A network entity in a wireless communication system, the network entity comprising:a transceiver; anda controller coupled with the transceiver, and configured to:transmit, to a user equipment (UE), first information configuring a data collection for an artificial intelligence (AI) model, andreceive, from the UE, second information for reporting logged data, based on the first information.6.The network entity of Claim 5, wherein the controller is further configured to:in case that the data collection fails, receive, from the UE, third information for reporting a cause of a failure.7.The network entity of Claim 5, wherein the controller is further configured to:receive, from the UE, capability information associated with a UE condition comprising a UE memory status or a UE power status.8.The network entity of Claim 7, wherein the first information is based on the capability information.9.A method performed by a user equipment (UE) in a wireless communication system, the method comprising:receiving, from a network entity, first information configuring a data collection for an artificial intelligence (AI) model; andtransmitting, to the network entity, second information for reporting logged data, based on the first information.10.The method of Claim 9, further comprising:in case that the data collection fails, transmitting, to the network entity, third information for reporting a cause of a failure.11.The method of Claim 9, further comprising:transmitting, to a network entity, capability information associated with a UE condition comprising a UE memory status or a UE power status.12.The method of Claim 11, wherein the first information is based on the capability information.13.A method performed by a network entity in a wireless communication system, the method comprising:transmitting, to a user equipment (UE), first information configuring a data collection for an artificial intelligence (AI) model; andreceiving, from the UE, second information for reporting logged data, based on the first information.14.The method of Claim 13, further comprising:in case that the data collection fails, receiving, from the UE, third information for reporting a cause of a failure.15.The method of Claim 13, further comprising:receiving, from the UE, capability information associated with a UE condition comprising a UE memory status or a UE power status.

Images