Radio terminal

Abstract

To allow a network to control whether a radio terminal is permitted to report to the network prediction data obtained based on predictions or determinations made using machine learning models.SOLUTION: A radio terminal receives control information from a network. The radio terminal generates prediction data using a machine learning model at the radio terminal. The radio terminal transmits the prediction data to the network only if permission is indicated in the control information.SELECTED DRAWING: Figure 4

Description

[Technical Field]

[0001] The present disclosure relates to wireless communication networks, and more particularly to the application of artificial intelligence (AI) to wireless communication networks. [Background technology]

[0002] The 3rd Generation Partnership Project (3GPP®) is discussing the application or introduction of AI or machine learning (ML) to 5G. AI / ML can be considered for both network internal functions and the air interface (i.e., Uu). In 3GPP Release 17, the Radio Access Network (RAN) Working Group #3 (RAN3) is discussing network-based AI / ML without User Equipment (UE) involvement, where examples of targets include energy saving, load balancing, and mobility optimization (see, for example, Non-Patent Documents 1 and 2). In network-based AI / ML, the network performs AI / ML inference. AI / ML inference refers to prediction or decision based on a trained machine learning model. The AI / ML inference function is expected to be applied to Next Generation Radio Access Networks (NG-RANs) (e.g., The machine learning model may be deployed in the NG-RAN (e.g., gNB). Training of the machine learning model may be performed in the NG-RAN. Alternatively, Operation, Administration and Maintenance (OAM) may train the machine learning model and provide the trained machine learning model (i.e., trained parameters) to the NG-RAN (e.g., gNB).

[0003] Furthermore, for 3GPP Release 18, network-based AI / ML with UE involvement and UE-based AI / ML have been proposed (see, for example, Non-Patent Documents 3-5). In UE-based AI / ML, the UE performs AI / ML inference. Potential use cases of AI / ML for the air interface include Channel State Information (CSI) feedback compression, beam management, positioning, Reference Signal (RS) overhead reduction, and mobility. In UE-based AI / ML, the UE runs an AI model (i.e., a trained machine learning model) and obtains the AI ​​inference results locally. For example, the UE can predict future events or measurements based on past measurements. The UE can feed back the predicted results (e.g., mobility or beam predictions) to the network (e.g., gNB). [Prior art documents] [Non-patent literature]

[0004] [Non-Patent Document 1] CMCC, "Revised SID: Study on enhancement for data collection for NR and ENDC", RP-201620, 3GPP TSG-RAN Meeting #89e, Electronic meeting, September 14-18, 2020 [Non-patent document 2] 3GPP TR 37.817 V0.3.0 (2021-08) "3rd Generation Partnership Project; Technical Specification Group RAN; Evolved Universal Terrestrial Radio Access (E-UTRA) and NR; Study on enhancement for Data Collection for NR and EN-DC (Release 17)", September 23, 2021 [Non-patent document 3] Ericsson, "Views on Rel-18 AI / ML on Air-Interface", RP-212346, 3GPP TSG-RAN Meeting#93e, Electronic meeting, September 13-17, 2021 [Non-patent document 4] ZTE, "Support of Artificial Intelligence Applications for 5G Advanced", RP-212383, 3GPP TSG-RAN Meeting#93e, Electronic meeting, September 13-17, 2021 [Non-patent document 5] Xiaomi, "Mobility enhancement by UE based AI", RP-211787, 3GPP TSG-RAN Meeting#93e, Electronic meeting, September 13-17, 2021 Summary of the Invention [Problem to be solved by the invention]

[0005] The present inventors have studied network-based AI / ML and found various problems. One of these problems relates to training a machine learning model used in a network or inference using a trained machine learning model. Data obtained by a UE can be used as training data for a machine learning model used in a network. Additionally or alternatively, data obtained by a UE can be used as input data for performing inference in a network using a trained machine learning model. However, currently, there is insufficient mechanism for a UE to transmit data suitable for training or inference in network-based AI / ML to a network.

[0006] One of the objectives to be achieved by the embodiments disclosed in this specification is to provide an apparatus, a method, and a program that contribute to solving at least one of the multiple problems related to network-based AI / ML, including the problem described above. It should be noted that this objective is only one of the multiple objectives to be achieved by the multiple embodiments disclosed in this specification. Other objectives or objectives and novel features will become apparent from the description of this specification or the accompanying drawings. [Means for solving the problem]

[0007] In a first aspect, a wireless terminal includes at least one memory and at least one processor coupled to the at least one memory. The at least one processor is configured to transmit assistance information to a network. The assistance information is used for training a first machine learning model related to radio access network optimization or for performing inference on the first trained machine learning model related to radio access network optimization. The assistance information includes one or both of statistical data and predictive data. The statistical data indicates a subset of historical data of a predetermined event extracted by filtering the historical data according to one or more conditions. The predictive data is generated by the wireless terminal making a prediction or decision using a second trained machine learning model.

[0008] In a second aspect, a method performed by a wireless terminal includes transmitting assistance information to a network, the assistance information being used to train a first machine learning model related to radio access network optimization or to perform inference with the first trained machine learning model related to radio access network optimization. The assistance information includes one or both of statistical data and predictive data. The statistical data represents a subset of historical data of a predetermined event extracted by filtering the historical data according to one or more conditions. The predictive data is generated by a prediction or decision made by the wireless terminal using a second trained machine learning model.

[0009] In a third aspect, a radio access network (RAN) node includes at least one memory and at least one processor coupled to the at least one memory. The at least one processor is configured to receive assistance information from a wireless terminal. The assistance information is used to train a first machine learning model related to radio access network optimization or to perform inference on the first trained machine learning model related to radio access network optimization. The assistance information includes one or both of statistical data and predictive data. The statistical data indicates a subset of historical data of a predetermined event extracted by filtering the historical data according to one or more conditions. The predictive data is generated by the wireless terminal making a prediction or decision using a second trained machine learning model.

[0010] In a fourth aspect, a method performed by a RAN node includes receiving assistance information from a wireless terminal, the assistance information being used for training a first machine learning model related to radio access network optimization or for performing inference with the first trained machine learning model related to radio access network optimization. The assistance information includes one or both of statistical data and predictive data. The statistical data represents a subset of historical data of a predetermined event extracted by filtering the historical data by one or more conditions. The predictive data is generated by a prediction or decision made by the wireless terminal using a second trained machine learning model.

[0011] A fifth aspect is directed to a program, which includes a group of instructions (software code) that, when loaded into a computer, causes the computer to perform the method according to the second or fourth aspect. [Effects of the Invention]

[0012] According to the above-described aspects, it is possible to provide an apparatus, a method, and a program that contribute to solving at least one of a plurality of problems related to network-based AI / ML. [Brief explanation of the drawings]

[0013] [Figure 1] 1 is a diagram illustrating an example of the configuration of a wireless communication system according to an embodiment. [Figure 2] FIG. 10 is a sequence diagram illustrating an example of the operation of a radio terminal and a radio access network node according to the embodiment. [Figure 3] FIG. 10 is a diagram illustrating a specific example of a format of UE support information according to an embodiment. [Figure 4] FIG. 10 is a sequence diagram illustrating an example of the operation of a radio terminal and a radio access network node according to the embodiment. [Figure 5] 10 is a flowchart illustrating an example of an operation of the wireless terminal according to the embodiment. [Figure 6]FIG. 2 is a block diagram illustrating a configuration example of a wireless terminal according to the embodiment. [Figure 7] FIG. 2 is a block diagram illustrating a configuration example of a radio access network node according to the embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0014] Hereinafter, specific embodiments will be described in detail with reference to the drawings. In each drawing, the same or corresponding elements are designated by the same reference numerals, and for clarity of explanation, duplicate explanations will be omitted as necessary.

[0015] The multiple embodiments described below can be implemented independently or in appropriate combination. These multiple embodiments have different novel features. Therefore, these multiple embodiments contribute to solving different purposes or problems and to achieving different effects.

[0016] Although the following embodiments will be described mainly with respect to the 3GPP fifth generation mobile communication system (5G system), these embodiments may also be applied to other wireless communication systems.

[0017] As used herein, depending on the context, "if" may be construed to mean "when," "at or around the time," "after," "upon," "in response to determining," "in accordance with a determination," or "in response to detecting." These expressions may be construed to have the same meaning, depending on the context.

[0018] First, the configurations and operations of multiple network elements common to multiple embodiments will be described. Figure 1 illustrates an example configuration of a wireless communication system according to multiple embodiments. In the example of Figure 1, the wireless communication system includes a wireless terminal (i.e., UE) 1 and a radio access network (RAN) node (e.g., gNB) 2. Each element (network function) illustrated in Figure 1 can be implemented, for example, as a network element on dedicated hardware, as a software instance running on dedicated hardware, or as a virtualized function instantiated on an application platform.

[0019] UE1 has at least one radio transceiver and is configured to perform wireless communication with RAN node 2. UE1 is connected to RAN node 2 via an air interface 101. RAN node 2 is configured to manage a cell and perform wireless communication with multiple UEs, including UE1, using a cellular communication technology (e.g., NR Radio Access Technology (RAT)). UE1 may be simultaneously connected to multiple RAN nodes for dual connectivity (DC).

[0020] The RAN node 2 may be a Central Unit (e.g., gNB-CU) in a cloud RAN (C-RAN) deployment, or a combination of a CU and one or more Distributed Units (e.g., gNB-DUs). C-RAN is also referred to as a CU / DU split. Furthermore, a CU may include a Control Plane (CP) Unit (e.g., gNB-CU-CP) and one or more User Plane (UP) Units (e.g., gNB-CU-UP). Thus, the RAN node 2 may be a CU-CP or a combination of a CU-CP and a CU-UP. The CU may be a logical node that hosts the Radio Resource Control (RRC), Service Data Adaptation Protocol (SDAP), and Packet Data Convergence Protocol (PDCP) protocols of the gNB (or the RRC and PDCP protocols of the gNB). The DU may be a logical node that hosts the Radio Link Control (RLC), Medium Access Control (MAC), and Physical (PHY) layers of the gNB.

[0021] The UE1 may locally perform AI / ML inference. The AI / ML inference may relate to radio access network optimization. The UE1 may run AI inference on a trained machine learning model and take one or more actions according to a prediction or decision based on the AI ​​inference. The machine learning model may be any model known in the field of machine learning, including deep learning. The machine learning model may be, for example, but not limited to, a neural network model, a support vector machine model, a decision tree model, a random forest model, or a K-nearest neighbor model.

[0022] By way of example and not limitation, the AI-based prediction or decision by UE1 and the resulting one or more actions may relate to at least one of beam management, mobility, CSI feedback, and positioning (or location estimation). The one or more actions may include, but are not limited to, at least one of cell reselection, transmission of a measurement report, performing conditional mobility, and selecting a downlink beam. The downlink beam may be a Synchronization Signal (SS) / Physical Broadcast Channel (PBCH) block (SSB) beam. For example, the machine learning model may output a prediction result for a candidate cell for cell reselection, a target cell or node for handover, a candidate cell or node for conditional mobility, a candidate beam for beam selection, or a UE trajectory. Additionally or alternatively, the machine learning model may predict or determine the timing of performing an action for mobility or beam management.

[0023] Cell reselection may occur when UE1 is in RRC_IDLE or RRC_INACTIVE.

[0024] Mobility may occur when UE1 is in RRC_CONNECTED. Mobility in RRC_CONNECTED may be handover. The handover may be a Dual Active Protocol Stack (DAPS) handover. Additionally or alternatively, mobility in RRC_CONNECTED may relate to various mobilities in the DC. Specifically, the mobility may be a change of a primary cell of a Master Cell Group (MCG) in the DC, an inter-Master Node (MN) handover in the DC, a secondary node change in the DC, or an addition or change of a primary cell of a secondary cell group in the DC.

[0025] Conditional mobility may be performed when UE1 is RRC_CONNECTED. The conditional mobility may be a conditional handover. Additionally or alternatively, the conditional mobility may relate to various mobility in the DC. Specifically, the conditional mobility may be a change of a primary cell of a Master Cell Group (MCG) in the DC, an inter-Master Node (MN) handover in the DC, a secondary node change in the DC, or an addition or change of a primary cell of a secondary cell group in the DC.

[0026] The selection of the downlink beam may be performed in a Beam Failure Recovery (BFR) procedure.

[0027] The training of the machine learning model for AI / ML inference by the UE 1 may be performed by the UE 1 or by the network (e.g., OAM, RAN node 2). The training method may be offline learning, online learning, or a combination of these.

[0028] Similarly, the RAN node 2 may perform AI / ML inference. This AI / ML inference may relate to radio access network optimization. The RAN node 2 may run AI inference on a trained machine learning model and take one or more actions according to a prediction or decision based on the AI ​​inference. The machine learning model may be any model known in the field of machine learning, including deep learning. The machine learning model may be, for example, but not limited to, a neural network model, a support vector machine model, a decision tree model, a random forest model, or a k-nearest neighbor model.

[0029] By way of example and not limitation, the AI ​​reasoning-based prediction or decision by the RAN node 2 and the one or more actions triggered thereby may relate to at least one of energy saving, load balancing, mobility optimization, enhanced CSI feedback, and enhanced positioning accuracy. For example, the machine learning model's prediction or decision may relate to one or both of an energy saving strategy and a mobility strategy. With respect to a mobility strategy, the machine learning model may output a predicted result of a target cell or node for handover, a candidate cell or node for conditional mobility, or a UE trajectory.

[0030] The training of the machine learning model for AI / ML inference by the RAN node 2 may be performed by the RAN node 2 or by the OAM. The training method may be offline learning, online learning, or a combination of these.

[0031] First Embodiment A configuration example of the wireless communication system according to this embodiment may be the same as the example shown in Fig. 1. Fig. 2 shows an example of the operation of UE1 and RAN node 2 for network-based AI / ML, that is, for a network (e.g., RAN node 2) to perform AI inference on a machine learning model. In step 201, UE1 transmits UE assistance information to RAN node 2. RAN node 2 may request UE1 to transmit the UE assistance information. UE1 may transmit the UE assistance information in response to the request from RAN node 2.

[0032] The UE assistance information is used in the network (e.g., RAN node 2 or OAM) to train a machine learning model for radio access network optimization or to perform inference on the trained machine learning model for radio access network optimization. In one example, as shown in FIG. 2, RAN node 2 may use the UE assistance information received from UE 1 to train a machine learning model or to perform inference on the trained machine learning model. The UE assistance information may be used as part of training data for training a machine learning model used in the network (e.g., RAN node 2). The UE assistance information may be used to generate training data. The UE assistance information may be used as input data for performing inference on a trained machine learning model in the network (e.g., RAN node 2). The UE assistance information may be used to generate input data that is fed to the trained machine learning model. The UE assistance information includes one or both of statistical data and predictive data.

[0033] The term “training a machine learning model” may be alternatively referred to as collecting or updating training data for a machine learning model, learning (machine learning-based) artificial intelligence, improving or enhancing inference accuracy by artificial intelligence, or machine learning or artificial intelligence. The term “performing inference with a trained machine learning model” may be alternatively referred to performing inference by artificial intelligence (using a trained machine learning model), performing inference by (machine learning-based) artificial intelligence, or performing machine learning or artificial intelligence. The term “predicting or making a decision using a trained machine learning model by a wireless terminal” may be alternatively referred to predicting or making a decision based on machine learning by a wireless terminal (e.g., UE), a prediction or result derived by machine learning, or a prediction or decision by (machine learning-based) artificial intelligence. The term “optimizing a radio access network” may refer to, for example, optimizing the functionality or processing of a wireless network (e.g., one or more RAN nodes) or optimizing the values ​​or settings of radio parameters that a wireless network configures for a wireless terminal (e.g., one or more UEs).

[0034] The statistical data indicates a subset of historical data extracted by filtering historical data of a predetermined event by one or more conditions. The historical data may indicate a history of success or failure of UE's mobility or beam selection. The historical data may indicate a history of beam management. The historical data may include one or more of a history of beam failure detection (BFD), a history of beam failure recovery (BFR), and a history of radio link failure (RLF). In other words, the predetermined event may be UE's mobility or beam selection (or beam management). As described above, the mobility may be mobility in RRC_CONNECTED (e.g., handover, conditional handover, MCG primary cell change, and MCG conditional primary cell change). Additionally or alternatively, the mobility may be mobility in RRC_IDLE or RRC_INACTIVE (e.g., cell reselection). The one or more conditions for filtering the historical data may include one or more conditions related to one or more of UE1's location, moving speed, serving beam, serving cell, and serving frequency band.

[0035] More specifically, the one or more conditions for filtering the historical data may include one or more conditions related to a movement pattern of UE1. UE1 may extract a subset of historical data corresponding to a movement pattern identical or similar to the movement pattern indicated by the conditions from the recorded (or archived) historical data. The movement pattern may indicate one or any combination of a source cell and target cell pair, a source cell frequency band and target cell frequency band pair, a UE location, a UE speed, and a downlink beam.

[0036] Additionally or alternatively, the one or more conditions for filtering the historical data may include one or more conditions related to the network slice used by UE 1. UE 1 may extract from the recorded (or archived) historical data a subset of the historical data that corresponds to a network slice that is the same as or similar to the network slice, slice group, or slice type indicated in the condition.

[0037] Additionally or alternatively, the one or more conditions for filtering the historical data may include one or more conditions related to the radio settings of UE1. UE1 may extract a subset of historical data corresponding to the same or similar radio settings as those indicated in the conditions from the recorded (or archived) historical data. The radio settings may be, for example, mobility-related parameters. More specifically, the radio settings may be a specific value of a predetermined offset, a specific frequency priority, or a specific execution condition for conditional mobility.

[0038] Meanwhile, the predicted data is generated by UE1 through prediction or decision using a machine learning model. In other words, the predicted data is generated based on the inference results of UE-based AI / ML in UE1. The predicted data may be real-time data transmitted to a network (e.g., RAN node 2) in response to the generation of the predicted data. The real-time data may be used as input data for the network to perform network-based AI / ML inference. The real-time data may indicate the position or trajectory of UE1 predicted by the machine learning model implemented in UE1. The real-time data may indicate candidate target cells or candidate downlink beams predicted by the machine learning model implemented in UE1.

[0039] Additionally or alternatively, the prediction data generated based on the inference results of the UE-based AI / ML in UE 1 may be recorded (or archived) data. The recorded data may be used as training data for a machine learning model used in the network. Additionally or alternatively, the recorded data may be used as input data for network-based AI / ML inference performed by the network.

[0040] The recorded data may indicate a position or trajectory of UE1 predicted by a machine learning model implemented in UE1. The recorded data may indicate a candidate target cell or a candidate downlink beam predicted by a machine learning model implemented in UE1. The recorded data may indicate a timing of mobility execution predicted by a machine learning model implemented in UE1. The recorded data may indicate a downlink beam determined by beam selection using a machine learning model implemented in UE1.

[0041] Figure 3 shows an example of the format of UE assistance information. The ai-ML-Assistance information element (IE) 302 shown in Figure 3 corresponds to UE assistance information related to AI. The ai-ML-Assistance IE 302 may be included in a UEAssistanceInformation IE 301. The UEAssistanceInformation IE 301 may be transmitted to the RAN node 2 via an RRC message (e.g., RRC Setup Request, RRC Setup Complete, RRC Resume Request, RRC Resume Complete, RRC Re-establishment Request, RRC Re-establishment Complete).

[0042] The ai-ML-Assistance IE 302 may include a statisticInfo IE 303 or 305. The statisticInfo IE 303 indicates that the UE 1 has statistical data or can report statistical data, while the statisticInfo IE 305 indicates specific statistical data sent from the UE 1 to the RAN node 2.

[0043] The ai-ML-Assistance IE 302 may include a predictedInfo IE 304 or 306. The predictedInfo IE 304 indicates that the UE 1 has predicted data or that the UE 1 can report predicted data, while the predictedInfo IE 306 indicates specific predicted data sent from the UE 1 to the RAN node 2.

[0044] The operation of UE1 and RAN node 2 described with reference to Figures 2 and 3 allows UE1 to provide the network with data suitable for network-based AI / ML training or inference.

[0045] <Second embodiment> A configuration example of the wireless communication system according to this embodiment may be the same as the example shown in FIG. 1. FIG. 4 shows an example of the operation of UE1 and RAN node 2 for network-based AI / ML, that is, for a network (e.g., RAN node 2) to perform AI inference using a machine learning model. In step 401, RAN node 2 transmits control information to UE1. The control information may be transmitted via broadcast (e.g., system information). The system information may be any system information block. Alternatively, the control information may be transmitted via dedicated signaling for UE1. The dedicated signaling may be dedicated RRC signaling, such as an RRC Reconfiguration message, an RRC Reestablishment message, an RRC Resume message, or an RRC Setup message. The control information may be an information element included in an SIB or the dedicated RRC signaling. The name of the information element may be, but is not limited to, "AI configuration."

[0046] The control information indicates whether the UE 1 is permitted to transmit UE assistance information to the network (e.g., RAN node 2) indicating prediction data based on predictions or decisions made using a machine learning model in the UE 1. The prediction data in this embodiment is similar to the prediction data described in the first embodiment.

[0047] The control information may indicate a condition under which transmission of UE assistance information indicating prediction data is permitted. In this case, UE1 may transmit the UE assistance information indicating the prediction data to the network only when the indicated condition is satisfied. Alternatively, the control information may indicate a condition under which collection of prediction data is permitted. In this case, UE1 may collect prediction data based on the AI / ML inference result only when the indicated condition is satisfied. In other words, UE1 may include in the UE assistance information only prediction data obtained when the indicated condition is satisfied. The condition may indicate restrictions on at least one of a frequency band, a location, and a time.

[0048] For example, the conditions may indicate a location (e.g., a geographic area, a logical area, a cell, or a set of cells) where UE1 is permitted to collect or report prediction data based on AI / ML inference results. The conditions may indicate a time or period where collection or reporting of prediction data is permitted. The conditions may indicate one or more frequency bands where collection or reporting of prediction data is permitted.

[0049] Additionally or alternatively, the condition may be that a consistent failure is detected. For example, the condition may allow UE1 to collect or report prediction data based on the AI / ML inference results when a predetermined failure is repeatedly detected in the same or similar situation (e.g., location, cell, cell pair, time, frequency band, time). The predetermined failure may be, for example, a handover failure or a beam failure. The situation may be at least one of a location, a cell, a cell pair, time, frequency band, and time.

[0050] Additionally or alternatively, the condition may be that UE 1 receives a signal indicating a predetermined identifier from the network (e.g., RAN node 2). The predetermined identifier may be, for example, but not limited to, a Config Set Number or ID, an AI Set Number or ID, or a Combination Set Number or ID. The predetermined identifier may be set by the network to represent the same or similar conditions (e.g., transmit power, antenna tilt, number of downlink beams, or other physical layer settings of RAN node 2).

[0051] Steps 402 and 403 of Figure 4 are similar to steps 201 and 202 of Figure 2, except that in step 402, UE1 sends UE assistance information indicating the prediction data to RAN node 2 if the control information in step 401 allows it.

[0052] 5 shows an example of the operation of UE1. In step 501, UE1 receives the above-mentioned control information. In step 502, UE1 makes a prediction or decision using the trained machine learning model. In step 503, if the control information allows it, UE1 transmits UE assistance information to RAN node 2, which indicates the prediction data obtained by inference using the machine learning model at UE1. In other words, if the control information allows it, UE1 reports the UE assistance information triggered by the prediction or decision at UE1 based on the machine learning model to the network.

[0053] According to the operation of UE1 and RAN node 2 described with reference to Figures 4 and 5, RAN node 2 can control whether UE1 is allowed to report prediction data obtained based on predictions or decisions made by UE-based AI / ML.

[0054] Next, exemplary configurations of a UE 1 and a RAN node 2 according to the above-described embodiments will be described below. FIG. 6 is a block diagram illustrating an exemplary configuration of a UE 1. A radio frequency (RF) transceiver 601 performs analog RF signal processing for communication with a RAN node. The RF transceiver 601 may include multiple transceivers. The analog RF signal processing performed by the RF transceiver 601 includes frequency up-conversion, frequency down-conversion, and amplification. The RF transceiver 601 is coupled to an antenna array 602 and a baseband processor 603. The RF transceiver 601 receives modulation symbol data (or OFDM symbol data) from the baseband processor 603, generates a transmit RF signal, and provides the transmit RF signal to the antenna array 602. The RF transceiver 601 also generates a baseband receive signal based on the receive RF signal received by the antenna array 602 and provides the baseband receive signal to the baseband processor 603. The RF transceiver 601 may include an analog beamformer circuit for beamforming. The analog beamformer circuitry includes, for example, multiple phase shifters and multiple power amplifiers.

[0055] The baseband processor 603 performs digital baseband signal processing (data plane processing) and control plane processing for wireless communication. Digital baseband signal processing includes (a) data compression / decompression, (b) data segmentation / concatenation, (c) transmission format (transmission frame) generation / decomposition, (d) transmission path coding / decoding, (e) modulation (symbol mapping) / demodulation, and (f) generation of OFDM symbol data (baseband OFDM signal) using Inverse Fast Fourier Transform (IFFT). Meanwhile, control plane processing includes communication management for Layer 1 (e.g., transmit power control), Layer 2 (e.g., radio resource management and hybrid automatic repeat request (HARQ) processing), and Layer 3 (e.g., signaling related to attachment, mobility, and call management).

[0056] For example, the digital baseband signal processing by the baseband processor 603 may include signal processing of a Service Data Adaptation Protocol (SDAP) layer, a Packet Data Convergence Protocol (PDCP) layer, a Radio Link Control (RLC) layer, a Medium Access Control (MAC) layer, and a Physical (PHY) layer. Also, the control plane processing by the baseband processor 603 may include processing of a Non-Access Stratum (NAS) protocol, a Radio Resource Control (RRC) protocol, MAC Control Elements (CEs), and Downlink Control Information (DCIs).

[0057] The baseband processor 603 may perform Multiple Input Multiple Output (MIMO) encoding and precoding for beamforming.

[0058] The baseband processor 603 may include a modem processor (e.g., a Digital Signal Processor (DSP)) that performs digital baseband signal processing and a protocol stack processor (e.g., a Central Processing Unit (CPU) or a Micro Processing Unit (MPU)) that performs control plane processing. In this case, the protocol stack processor that performs control plane processing may be shared with the application processor 604, which will be described later.

[0059] The application processor 604 is also referred to as a CPU, MPU, microprocessor, or processor core. The application processor 604 may include multiple processors (multiple processor cores). The application processor 604 executes a system software program (operating system (OS)) and various application programs (e.g., a calling application, a web browser, a mailer, a camera operation application, and a music playback application) read from the memory 606 or a memory not shown, thereby realizing various functions of the UE1.

[0060] In some implementations, the baseband processor 603 and the application processor 604 may be integrated on a single chip, as indicated by the dashed line (605) in Figure 6. In other words, the baseband processor 603 and the application processor 604 may be implemented as a single System on Chip (SoC) device 605. An SoC device is sometimes called a system Large Scale Integration (LSI) or a chipset.

[0061] The memory 606 is volatile memory, nonvolatile memory, or a combination thereof. The memory 606 may include multiple physically independent memory devices. The volatile memory may be, for example, static random access memory (SRAM), dynamic RAM (DRAM), or a combination thereof. The nonvolatile memory may be mask read only memory (MROM), electrically erasable programmable ROM (EEPROM), flash memory, a hard disk drive, or any combination thereof. For example, the memory 606 may include an external memory device accessible from the baseband processor 603, the application processor 604, and the SoC 605. The memory 606 may also include an internal memory device integrated within the baseband processor 603, the application processor 604, or the SoC 605. Furthermore, the memory 606 may include memory within a universal integrated circuit card (UICC).

[0062] The memory 606 may store one or more software modules (computer programs) 607 including instructions and data for performing the processes by the UE 1 described in the above embodiments. In some implementations, the baseband processor 603 or the application processor 604 may be configured to read and execute the software modules 607 from the memory 606 to perform the processes by the UE 1 described in the above embodiments with reference to the drawings.

[0063] It should be noted that the control plane processing and operations performed by UE1 described in the above embodiment can be realized by elements other than the RF transceiver 601 and the antenna array 602, namely, at least one of the baseband processor 603 and the application processor 604, and the memory 606 storing the software module 607.

[0064] FIG. 7 is a block diagram showing an example configuration of a RAN node 2 according to the above embodiment. Referring to FIG. 7, the RAN node 2 includes a radio frequency transceiver 701, a network interface 703, a processor 704, and a memory 705. The RF transceiver 701 performs analog RF signal processing for communication with UEs, including UE1. The RF transceiver 701 may include multiple transceivers. The RF transceiver 701 is coupled to an antenna array 702 and a processor 704. The RF transceiver 701 receives modulation symbol data from the processor 704, generates a transmit RF signal, and provides the transmit RF signal to the antenna array 702. The RF transceiver 701 also generates a baseband receive signal based on the receive RF signal received by the antenna array 702 and provides the baseband receive signal to the processor 704. The RF transceiver 701 may include an analog beamformer circuit for beamforming. The analog beamformer circuit may include, for example, multiple phase shifters and multiple power amplifiers.

[0065] The network interface 703 is used to communicate with network nodes (e.g., other RAN nodes, and control and forwarding nodes of the core network), and may include, for example, a network interface card (NIC) compliant with the IEEE 802.3 series.

[0066] The processor 704 performs digital baseband signal processing (data plane processing) and control plane processing for wireless communication. The processor 704 may include multiple processors. For example, the processor 704 may include a modem processor (e.g., a Digital Signal Processor (DSP)) that performs digital baseband signal processing and a protocol stack processor (e.g., a Central Processing Unit (CPU) or a Micro Processing Unit (MPU)) that performs control plane processing. The processor 704 may include a digital beamformer module for beamforming. The digital beamformer module may include a Multiple Input Multiple Output (MIMO) encoder and precoder.

[0067] The memory 705 is configured by a combination of volatile memory and non-volatile memory. The volatile memory is, for example, Static Random Access Memory (SRAM), Dynamic RAM (DRAM), or a combination thereof. The non-volatile memory is, for example, Mask Read Only Memory (MROM), Electrically Erasable Programmable ROM (EEPROM), flash memory, or a hard disk drive, or any combination thereof. The memory 705 may include storage located remotely from the processor 704. In this case, the processor 704 may access the memory 705 via the network interface 703 or an I / O interface (not shown).

[0068] The memory 705 may store one or more software modules (computer programs) 706 including instructions and data for performing the processing by the RAN node 2 described in the above embodiments. In some implementations, the processor 704 may be configured to read and execute the software modules 706 from the memory 705 to perform the processing by the RAN node 2 described in the above embodiments.

[0069] Note that if the RAN node 2 is a CU (e.g., gNB-CU) or a CU-CP (e.g., gNB-CU-CP), the RAN node 2 may not include the RF transceiver 701 (and the antenna array 702).

[0070] As described with reference to FIGS. 6 and 7, each of the processors included in the UE 1 and the RAN node 2 according to the above-described embodiments can execute one or more programs including instructions for causing a computer to perform the algorithms described with reference to the drawings. The programs include instructions (or software code) that, when loaded into a computer, cause the computer to perform one or more functions described in the embodiments. The programs may be stored on a non-transitory computer-readable medium or a tangible storage medium. By way of example and not limitation, computer-readable media or tangible storage media include random-access memory (RAM), read-only memory (ROM), flash memory, solid-state drive (SSD) or other memory technology, CD-ROM, digital versatile disk (DVD), Blu-ray® disc or other optical disk storage, magnetic cassette, magnetic tape, magnetic disk storage or other magnetic storage device. The programs may also be transmitted on a transitory computer-readable medium or communication medium. By way of example and not limitation, transitory computer-readable media or communication media include electrical, optical, acoustic, or other forms of propagated signals.

[0071] <Other embodiments> The above-described embodiments may be applied to a Non-Terrestrial Network (NTN), a vehicle-to-everything (V2X), high-speed trains (HSTs), unmanned aerial vehicles (UAVs), uncrewed aerial vehicles (UAVs), urban air mobility (UAM), and various other new applications.

[0072] In the above-described embodiment, UE1 may send an AI interest indication (e.g., ai-ML-InterestIndication) during the RRC connection setup, resume, or re-establishment procedure. RAN node 2 may request UE1 to send the AI ​​interest indication. The AI ​​interest indication may indicate that UE1 supports the capability of sending to RAN node 2 information (UE assistance information) necessary (or useful) for performing AI inference using a machine learning model (AI / ML inference) at RAN node 2. Additionally or alternatively, the AI ​​interest indication may indicate to RAN node 2 that UE1 is interested in sending (or providing) UE assistance information. The AI ​​interest indication may indicate a category of AI / ML inference that UE1 wishes to perform (or contribute to). In other words, the AI ​​interest indication may indicate an action or category of action for which UE1 wishes to be allowed to provide UE assistance information. The AI ​​interest indication may indicate a function or feature (e.g., mobility, power saving) for which UE1 wishes to be allowed to provide UE assistance information. The AI ​​interest indication may indicate a sub-function or sub-feature (e.g., cell selection, handover, beam management) for which UE1 wishes to be allowed to provide UE assistance information. The AI ​​interest indication may also indicate a procedure (e.g., RRC re-establishment, beam failure recovery (BFR)) for which UE1 wishes to be allowed to provide UE assistance information. The AI ​​interest indication may also indicate an RRC configuration (e.g., information element or field level in Abstract Syntax Notation One (ASN.1)) for which UE1 wishes to be allowed to provide UE assistance information.

[0073] The above-described embodiment may be applied to a secondary cell group (SCG) in dual connectivity (e.g., multi-radio dual connectivity (MR-DC)). In this case, the RAN node 2 may be a secondary node (SN). In this case, the SN may transmit and receive RRC messages to and from the UE 1 directly using a signaling radio bearer (SRB3) in the SCG, or may transmit and receive RRC messages via a master node (MN). Additionally or alternatively, the RAN node 2 may be the master node (MN) and may play a role in transferring RRC messages between the SN and the UE 1.

[0074] The RAN node 2 in the above-described embodiment may be implemented in a C-RAN configuration. For example, the RAN node 2 may include a CU (e.g., gNB-CU) and a DU (e.g., gNB-DU). The CU may request UE1 to transmit UE assistance information or may receive the UE assistance information from UE1 (via the DU). The CU may optimize the radio network based on the UE assistance information. Furthermore, the CU may transmit at least a portion of the UE assistance information or control information derived from the UE assistance information (or in response to receiving the UE assistance information) to the DU. The DU may optimize the radio network based on the information transmitted from the CU (i.e., received by the DU). For example, the optimization of the radio network by the CU may be optimization of radio parameters (e.g., Radio Bearer Config) configured by the CU1 for UE1. The optimization of the radio network by the DU may be optimization of radio parameters (e.g., Cell Group Config, Measurement Gap) configured by the DU for UE1. The above-described controls by the CU and DU may be selected or combined depending on the target of optimization of the wireless network or the type and content of the requested UE assistance information.

[0075] The RAN node 2 in the above-described embodiment may transmit at least a portion of the UE assistance information to one or more other network nodes. The other network nodes may include, for example, one or both of an Operation, Administration and Maintenance (OAM) and a RAN Intelligent Controller (RIC). The RIC may be one considered by a standardization organization (e.g., the Open RAN (O-RAN) alliance) or a network node contributing to RAN optimization other than the RIC. The other network nodes may optimize the radio network based on at least a portion of the UE assistance information. Additionally or alternatively, the other network nodes may transmit new radio parameter configurations for radio network optimization to the RAN node 2. In this case, the other network nodes may transmit the new radio parameter configurations directly to either or both of the CU and DU.

[0076] Furthermore, the above-described embodiments are merely examples of application of the technical ideas obtained by the inventors of the present invention. In other words, the technical ideas are not limited to the above-described embodiments, and various modifications are possible.

[0077] For example, some or all of the above embodiments can be described as, but are not limited to, the following supplementary notes.

[0078] (Appendix 1) A wireless terminal, at least one memory; at least one processor coupled to the at least one memory and configured to transmit assistance information to a network; the assistance information is used for training a first machine learning model related to radio access network optimization or for performing inference on the first trained machine learning model related to radio access network optimization; the support information includes one or both of statistical data and predictive data; the statistical data represents a subset of the historical data of a predetermined event extracted by filtering the historical data according to one or more conditions; the predictive data is generated by a prediction or decision made by the wireless terminal using a second trained machine learning model. Wireless terminal. (Appendix 2) the historical data indicating a history of success or failure of mobility or beam selection of the wireless terminal; 1. A wireless terminal as defined in claim 1. (Appendix 3) the one or more conditions include one or more conditions related to one or more of the location, movement speed, serving beam, serving cell, and serving frequency band of the wireless terminal; 3. A wireless terminal according to claim 1 or 2. (Appendix 4) the one or more conditions include one or more conditions related to a movement pattern of the wireless terminal; 4. The wireless terminal according to claim 1. (Appendix 5) The one or more conditions include one or more conditions regarding a network slice used by the wireless terminal. 5. The wireless terminal according to any one of Supplementary notes 1 to 4. (Appendix 6) the one or more conditions include one or more conditions related to radio settings of the wireless terminal; 6. The wireless terminal according to any one of Supplementary notes 1 to 5. (Appendix 7) the prediction data is real-time data transmitted to the network in response to the prediction data being generated, and is used to perform inference with the first trained machine learning model. 7. The wireless terminal according to claim 1. (Appendix 8) the real-time data indicating a predicted position or trajectory of the wireless terminal; 8. The wireless terminal of claim 7. (Appendix 9) the real-time data indicating predicted candidate target cells or candidate downlink beams; 8. The wireless terminal of claim 7. (Appendix 10) the predicted data is recorded data; 7. The wireless terminal according to claim 1. (Appendix 11) the recorded data indicates timing of mobility execution predicted or determined using the second trained machine learning model. 11. The wireless terminal of claim 10. (Appendix 12) the recorded data indicates a downlink beam determined by beam selection using the second trained machine learning model. 11. The wireless terminal of claim 10. (Appendix 13) The at least one processor: receiving control information from the network; If the control information permits it, transmitting the assistance information to the network indicating the prediction data based on the results of a prediction or decision using the second trained machine learning model. It is configured as follows: 13. A wireless terminal according to any one of Supplementary notes 1 to 12. (Appendix 14) the control information indicates a condition under which transmission of the assistance information indicating the prediction data is permitted; the at least one processor is configured to transmit the assistance information indicative of the predicted data to the network only if the condition is met. 14. The wireless terminal of claim 13. (Appendix 15) the control information indicates a condition under which collection of the prediction data is permitted; the at least one processor is configured to include in the assistance information only prediction data obtained when the condition is satisfied. 14. The wireless terminal of claim 13. (Appendix 16) The conditions indicate constraints on at least one of a frequency band, a location, and a time. 16. The wireless terminal of claim 14 or 15. (Appendix 17) 1. A method performed by a wireless terminal, comprising: transmitting the assistance information to a network; the assistance information is used for training a first machine learning model related to radio access network optimization or for performing inference on the first trained machine learning model related to radio access network optimization; the support information includes one or both of statistical data and predictive data; the statistical data represents a subset of the historical data of a predetermined event extracted by filtering the historical data according to one or more conditions; the predictive data is generated by a prediction or decision made by the wireless terminal using a second trained machine learning model. method. (Appendix 18) A program for causing a computer to perform a method for a wireless terminal, comprising: The method comprises transmitting assistance information to a network; the assistance information is used for training a first machine learning model related to radio access network optimization or for performing inference on the first trained machine learning model related to radio access network optimization; the support information includes one or both of statistical data and predictive data; the statistical data represents a subset of the historical data of a predetermined event extracted by filtering the historical data according to one or more conditions; the predictive data is generated by a prediction or decision made by the wireless terminal using a second trained machine learning model. program. (Appendix 19) at least one memory; at least one processor coupled to the at least one memory and configured to receive assistance information from a wireless terminal; the assistance information is used for training a first machine learning model related to radio access network optimization or for performing inference on the first trained machine learning model related to radio access network optimization; the support information includes one or both of statistical data and predictive data; the statistical data represents a subset of the historical data of a predetermined event extracted by filtering the historical data according to one or more conditions; the predictive data is generated by a prediction or decision made by the wireless terminal using a second trained machine learning model. Radio access network node. (Appendix 20) the historical data indicating a history of success or failure of mobility or beam selection of the wireless terminal; 19. A radio access network node according to claim 18. (Appendix 21) the one or more conditions include one or more conditions related to one or more of the location, movement speed, serving beam, serving cell, and serving frequency band of the wireless terminal; 21. A radio access network node according to claim 19 or 20. (Appendix 22) the one or more conditions include one or more conditions related to a movement pattern of the wireless terminal; 22. A radio access network node according to any one of Supplementary Notes 19 to 21. (Appendix 23) The one or more conditions include one or more conditions regarding a network slice used by the wireless terminal. 23. A radio access network node according to any one of Supplementary Notes 19 to 22. (Appendix 24) the one or more conditions include one or more conditions related to radio settings of the wireless terminal; A radio access network node according to any one of Supplementary Notes 19 to 23. (Appendix 25) the prediction data is real-time data transmitted to the radio access network node in response to the prediction data being generated, and used to perform inference with the first trained machine learning model. A radio access network node according to any one of Supplementary notes 19 to 24. (Appendix 26) the real-time data indicating a predicted position or trajectory of the wireless terminal; 26. A radio access network node according to claim 25. (Appendix 27) the real-time data indicating predicted candidate target cells or candidate downlink beams; 26. A radio access network node according to claim 25. (Appendix 28) the prediction data is recorded data and is used to train the first machine learning model; A radio access network node according to any one of Supplementary notes 19 to 24. (Appendix 29) the recorded data indicates timing of mobility execution predicted or determined using the second trained machine learning model. 29. A radio access network node according to claim 28. (Appendix 30) the recorded data indicates a downlink beam determined by beam selection using the second trained machine learning model. 29. A radio access network node according to claim 28. (Appendix 31) the at least one processor is configured to transmit control information to the wireless terminal; the control information causes the wireless terminal to transmit, if the control information allows it, the assistance information indicating the predicted data to the radio access network node. A radio access network node according to any one of Supplementary notes 19 to 30. (Appendix 32) the control information indicates a condition under which transmission of the assistance information indicating the prediction data is permitted; the control information causes the wireless terminal to transmit the assistance information indicating the prediction data to the radio access network node only if the condition is met. 32. The radio access network node of claim 31. (Appendix 33) the control information indicates a condition under which collection of the prediction data is permitted; the control information causes the wireless terminal to include in the assistance information only prediction data obtained when the condition is satisfied. 32. The radio access network node of claim 31. (Appendix 34) The conditions indicate constraints on at least one of a frequency band, a location, and a time. 34. A radio access network node according to claim 32 or 33. (Appendix 35) receiving assistance information from a wireless terminal; the assistance information is used for training a first machine learning model related to radio access network optimization or for performing inference on the first trained machine learning model related to radio access network optimization; the support information includes one or both of statistical data and predictive data; the statistical data represents a subset of the historical data of a predetermined event extracted by filtering the historical data according to one or more conditions; the predictive data is generated by a prediction or decision made by the wireless terminal using a second trained machine learning model. method. (Appendix 36) 1. A program for causing a computer to perform a method for a radio access network node, comprising: The method comprises receiving assistance information from a wireless terminal; the assistance information is used for training a first machine learning model related to radio access network optimization or for performing inference on the first trained machine learning model related to radio access network optimization; the support information includes one or both of statistical data and predictive data; the statistical data represents a subset of the historical data of a predetermined event extracted by filtering the historical data according to one or more conditions; the predictive data is generated by a prediction or decision made by the wireless terminal using a second trained machine learning model. program.

[0079] This application claims priority based on Japanese Patent Application No. 2021-182105, filed on November 8, 2021, the disclosure of which is incorporated herein in its entirety. [Explanation of symbols]

[0080] 1 UE 2. RAN Node 603 Baseband Processor 604 Application Processor 606 memory 607 Modules 704 processor 705 memory 706 modules

Claims

1. A wireless terminal, a receiving unit for receiving control information from a network; a generation unit that generates prediction data using a machine learning model in the wireless terminal; a transmitter configured to transmit the prediction data to a network only if permission is indicated in the control information; Equipped with A wireless terminal, wherein the prediction data is used for performing inference or further training on a network-side machine learning model related to radio access network optimization.

2. the control information indicates conditions regarding at least one of a location, a time, or a frequency band under which transmission of the predicted data is permitted; The wireless terminal according to claim 1 , wherein the transmitter transmits the prediction data only when the condition is satisfied.

3. the control information indicates that transmission of the prediction data is permitted only during a period in which a signal including a predetermined identifier is received; The wireless terminal according to claim 1 , wherein the transmitter transmits the prediction data only while the wireless terminal is receiving a signal including the identifier.

4. The prediction data is a) the future position or trajectory of said wireless terminal; b) a candidate target cell, or c) Candidate Downlink Beams 3. The wireless terminal according to claim 1, wherein the wireless terminal exhibits at least one of the following:

5. The wireless terminal according to claim 1 or 2, wherein the transmission unit encodes the prediction data as an ai-ML-Assistance information element in a UEAssistanceInformation information element included in an RRC message and transmits the encoded data.

Images