Communication methods, user devices, mobile communication systems, programs, and chipsets
Patent Information
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Filing Date
- 2024-08-07
- Publication Date
- 2026-05-11
Abstract
Description
Communication Method
[0001] The present disclosure relates to a communication method for use in a mobile communication system.
[0002] BACKGROUND ART 3GPP (Third Generation Partnership Project) (registered trademark; the same applies hereinafter), a standardization project for mobile communication systems, is studying the application of artificial intelligence or machine learning (also referred to as "AI (Artificial Intelligence) / ML (Machine Learning)") technology to wireless communication (i.e., air interface) of mobile communication systems.
[0003] 3GPP Technical Report: TR 38.843 V0.1.0 (2023-05), “Study on Artificial Intelligence (AI) / Machine Learning (ML) for NR air interface (Release 18)”
[0004] A communication method according to a first aspect is a method executed by a user device in a mobile communication system. The communication method includes the steps of receiving, from a network node, configuration information for applying an inference process using an artificial intelligence or machine learning (AI / ML) model to wireless communication with the network node, and performing the wireless communication applying the inference process based on the configuration information. The configuration information includes a discontinuous operation setting for discontinuously applying the inference process. The step of performing the wireless communication includes the step of discontinuously applying the inference process.
[0005] A communication method according to a second aspect is a method executed by a user device in a mobile communication system, the method comprising the steps of receiving, from a network node, configuration information for applying an inference process using an artificial intelligence or machine learning (AI / ML) model to wireless communication with the network node, performing the wireless communication to which the inference process is applied based on the configuration information, and transmitting, to the network node, AI / ML preference information indicating preferences for setting changes to reduce a processing load of the inference process.
[0006] 1 is a diagram showing the configuration of a mobile communication system according to an embodiment. FIG. 1 is a diagram showing the configuration of a UE (user equipment) according to an embodiment. FIG. 2 is a diagram showing the configuration of a gNB (network node) according to an embodiment. FIG. 3 is a diagram showing the configuration of a protocol stack of a radio interface of a user plane that handles data. FIG. 4 is a diagram showing the configuration of a protocol stack of a radio interface of a control plane that handles signaling (control signals). FIG. 5 is a diagram showing a functional block configuration of AI / ML technology in a mobile communication system according to an embodiment. FIG. 6 is a diagram showing an example of an application scenario of AI / ML technology. FIG. 7 is a diagram showing a first example of reducing CSI-RS. FIG. 8 is a diagram showing a second example of reducing CSI-RS. FIG. 9 is a diagram showing an overview of UE operation in a first operation pattern according to an embodiment. FIG. 10 is a diagram showing an example of operation when inference processing is periodically applied in CSI prediction according to the first operation pattern according to an embodiment. FIG. 11 is a diagram showing an example of an operation flow of a mobile communication system according to the first operation pattern according to an embodiment. FIG. 12 is a diagram showing an overview of UE operation in a second operation pattern according to an embodiment. FIG. 13 is a diagram showing an example of operation flow of a mobile communication system according to the second operation pattern according to an embodiment.
[0007] When a user equipment (UE) having an AI / ML model constantly performs inference processing (model inference) using the AI / ML model during wireless communication with a network node, the processing load of the inference processing in the UE may become high. This may result in problems such as increased power consumption, increased delay in the inference processing, and / or increased internal temperature in the UE. This makes it difficult to utilize AI / ML technology in a mobile communication system.
[0008] The present disclosure aims to utilize AI / ML technology in mobile communication systems.
[0009] A mobile communication system according to an embodiment will be described with reference to the drawings. In the description of the drawings, the same or similar parts are denoted by the same or similar reference numerals.
[0010] (1) Configuration of a Mobile Communication System First, the configuration of a mobile communication system according to an embodiment will be described. FIG. 1 is a diagram showing the configuration of a mobile communication system 1 according to an embodiment. The mobile communication system 1 conforms to the 5th Generation System (5GS) of the 3GPP standard. In the following description, 5GS will be used as an example, but the LTE (Long Term Evolution) system may also be applied at least in part to the mobile communication system. The 6th Generation (6G) system may also be applied at least in part to the mobile communication system.
[0011] The mobile communication system 1 includes a user equipment (UE) 100, a 5G radio access network (NG-RAN: Next Generation Radio Access Network) 10, and a 5G core network (5GC: 5G Core Network) 20. Hereinafter, the NG-RAN 10 may be simply referred to as the RAN 10. Furthermore, the 5GC 20 may be simply referred to as the core network (CN) 20. The RAN 10 and the CN 20 constitute a network 5 of the mobile communication system 1. The UE 100 performs wireless communication with the network 5.
[0012] The UE 100 is a mobile wireless communication device. The UE 100 may be any device that is used by a user. For example, the UE 100 may be a mobile phone terminal (which may be a smartphone) and / or a tablet terminal, a notebook PC, a communication module (which may be a communication card or a chipset), a sensor or a device provided in a sensor, a vehicle or a device provided in a vehicle (Vehicle UE), or an aircraft or a device provided in an aircraft (Aerial UE).
[0013] The NG-RAN 10 includes a base station (called a "gNB" in a 5G system) 200, which is a type of network node. The gNBs 200 are connected to each other via an Xn interface, which is an interface between base stations. The gNB 200 manages one or more cells. The gNB 200 performs wireless communication with a UE 100 that has established a connection with its own cell. The gNB 200 has a radio resource management (RRM) function, a routing function for user data (hereinafter simply referred to as "data"), a measurement control function for mobility control and scheduling, and the like. The term "cell" is used to indicate the smallest unit of a wireless communication area. The term "cell" is also used to indicate a function or resource for wireless communication with the UE 100. One cell belongs to one carrier frequency (hereinafter simply referred to as "frequency").
[0014] In addition, gNBs can also be connected to the Evolved Packet Core (EPC), which is the core network of LTE. LTE base stations can also be connected to 5GC. LTE base stations and gNBs can also be connected via an inter-base station interface.
[0015] The 5GC20 includes an AMF (Access and Mobility Management Function) and a UPF (User Plane Function) 300. The AMF performs various mobility controls for the UE 100. The AMF manages the mobility of the UE 100 by communicating with the UE 100 using NAS (Non-Access Stratum) signaling. The UPF controls data forwarding. The AMF and the UPF are connected to the gNB 200 via an NG interface, which is an interface between a base station and a core network.
[0016] 2 is a diagram showing the configuration of a UE 100 (user equipment) according to an embodiment. The UE 100 has a receiving unit 110, a transmitting unit 120, and a control unit 130. The receiving unit 110 and the transmitting unit 120 constitute a communication unit that performs wireless communication with the gNB 200. The UE 100 is an example of a communication device.
[0017] The receiving unit 110 performs various types of reception under the control of the control unit 130. The receiving unit 110 includes an antenna and a receiver. The receiver converts a radio signal received by the antenna into a baseband signal (received signal) and outputs the baseband signal to the control unit 130.
[0018] The transmitting unit 120 performs various transmissions under the control of the control unit 130. The transmitting unit 120 includes an antenna and a transmitter. The transmitter converts a baseband signal (transmission signal) output by the control unit 130 into a radio signal and transmits it from the antenna.
[0019] The control unit 130 performs various controls and processes in the UE 100. The operations of the UE 100 described above and below may be operations controlled by the control unit 130. The control unit 130 includes at least one processor and at least one memory. The memory stores programs executed by the processor and information used in the processing by the processor. The processor may include a baseband processor and a CPU (Central Processing Unit). The baseband processor performs modulation / demodulation and encoding / decoding of baseband signals. The CPU executes programs stored in the memory to perform various processes.
[0020] 3 is a diagram showing the configuration of a gNB 200 (network node) according to an embodiment. The gNB 200 has a transmitter 210, a receiver 220, a controller 230, and a backhaul communication unit 240. The transmitter 210 and the receiver 220 constitute a communication unit that performs wireless communication with the UE 100. The backhaul communication unit 240 constitutes a network communication unit that communicates with the CN 20. The gNB 200 is another example of a communication device.
[0021] The transmitting unit 210 performs various transmissions under the control of the control unit 230. The transmitting unit 210 includes an antenna and a transmitter. The transmitter converts a baseband signal (transmission signal) output by the control unit 230 into a radio signal and transmits it from the antenna.
[0022] The receiving unit 220 performs various types of reception under the control of the control unit 230. The receiving unit 220 includes an antenna and a receiver. The receiver converts a radio signal received by the antenna into a baseband signal (received signal) and outputs the baseband signal to the control unit 230.
[0023] The control unit 230 performs various controls and processes in the gNB 200. The operations of the gNB 200 described above and below may be operations under the control of the control unit 130. The control unit 230 includes at least one processor and at least one memory. The memory stores programs executed by the processor and information used in processing by the processor. The processor may include a baseband processor and a CPU. The baseband processor performs modulation / demodulation and encoding / decoding of baseband signals. The CPU executes programs stored in the memory to perform various processes.
[0024] The backhaul communication unit 240 is connected to adjacent base stations via an Xn interface, which is an interface between base stations. The backhaul communication unit 240 is connected to the AMF / UPF 300 via an NG interface, which is an interface between a base station and a core network. The gNB 200 may be configured (i.e., functionally divided) with a central unit (CU) and a distributed unit (DU), and the two units may be connected via an F1 interface, which is a fronthaul interface.
[0025] FIG. 4 is a diagram showing the configuration of a protocol stack of a radio interface of a user plane that handles data.
[0026] The user plane air interface protocol includes a physical (PHY) layer, a medium access control (MAC) layer, a radio link control (RLC) layer, a packet data convergence protocol (PDCP) layer, and a service data adaptation protocol (SDAP) layer.
[0027] The PHY layer performs encoding / decoding, modulation / demodulation, antenna mapping / demapping, and resource mapping / demapping. Data and control information are transmitted between the PHY layer of UE100 and the PHY layer of gNB200 via a physical channel. The PHY layer of UE100 receives downlink control information (DCI) transmitted from gNB200 on a physical downlink control channel (PDCCH). Specifically, UE100 performs blind decoding of the PDCCH using a radio network temporary identifier (RNTI) and acquires successfully decoded DCI as DCI addressed to the UE. The DCI transmitted from gNB200 has a CRC (Cyclic Redundancy Code) parity bit scrambled by the RNTI added.
[0028] In NR, UE100 can use a bandwidth narrower than the system bandwidth (i.e., the cell bandwidth). The gNB200 configures the UE100 with a bandwidth portion (BWP) consisting of contiguous PRBs (Physical Resource Blocks). The UE100 transmits and receives data and control signals in the active BWP. For example, up to four BWPs may be configurable for the UE100. Each BWP may have a different subcarrier spacing. The BWPs may overlap in frequency. When multiple BWPs are configured for the UE100, the gNB200 can specify which BWP to apply by controlling the downlink. This allows the gNB200 to dynamically adjust the UE bandwidth according to the amount of data traffic of the UE100, etc., thereby reducing UE power consumption.
[0029] The gNB 200 can configure, for example, up to three control resource sets (CORESETs) for each of up to four BWPs on the serving cell. The CORESET is a radio resource for control information to be received by the UE 100. Up to 12 or more CORESETs may be configured on the serving cell for the UE 100. Each CORESET may have an index of 0 to 11 or more. The CORESET may consist of six resource blocks (PRBs) and one, two, or three consecutive Orthogonal Frequency Division Multiplex (OFDM) symbols in the time domain.
[0030] The MAC layer performs data priority control, retransmission processing using Hybrid Automatic Repeat reQuest (HARQ), random access procedures, etc. Data and control information are transmitted between the MAC layer of the UE 100 and the MAC layer of the gNB 200 via a transport channel. The MAC layer of the gNB 200 includes a scheduler. The scheduler determines the uplink and downlink transport format (transport block size, modulation and coding scheme (MCS)) and the resource blocks to be allocated to the UE 100.
[0031] The RLC layer transmits data to the receiving RLC layer using the functions of the MAC layer and PHY layer. Data and control information are transmitted between the RLC layer of the UE 100 and the RLC layer of the gNB 200 via a logical channel.
[0032] The PDCP layer performs header compression / decompression, encryption / decryption, and the like.
[0033] The SDAP layer maps IP flows, which are units for Quality of Service (QoS) control by the core network, to radio bearers, which are units for QoS control by the access stratum (AS). Note that if the RAN is connected to the EPC, SDAP may not be required.
[0034] FIG. 5 is a diagram showing the configuration of a protocol stack of a radio interface of a control plane that handles signaling (control signals).
[0035] The protocol stack of the radio interface of the control plane includes a Radio Resource Control (RRC) layer and a Non-Access Stratum (NAS) instead of the SDAP layer shown in FIG.
[0036] RRC signaling for various settings is transmitted between the RRC layer of UE100 and the RRC layer of gNB200. The RRC layer controls logical channels, transport channels, and physical channels according to the establishment, re-establishment, and release of radio bearers. When there is a connection (RRC connection) between the RRC of UE100 and the RRC of gNB200, UE100 is in an RRC connected state. When there is no connection (RRC connection) between the RRC of UE100 and the RRC of gNB200, UE100 is in an RRC idle state. When the connection between the RRC of UE100 and the RRC of gNB200 is suspended, UE100 is in an RRC inactive state.
[0037] The NAS, which is located above the RRC layer, performs session management, mobility management, etc. NAS signaling is transmitted between the NAS of the UE 100 and the NAS of the AMF 300A. Note that the UE 100 has an application layer and the like in addition to the radio interface protocol. Also, a layer lower than the NAS is called an AS (Access Stratum).
[0038] (2) Overview of AI / ML Technology Next, an overview of AI / ML technology will be described. A mobile communication system 1 according to an embodiment applies AI / ML technology to wireless communication (i.e., air interface).
[0039] 6 is a diagram showing a functional block configuration of the AI / ML technology in the mobile communication system 1 according to the embodiment. The functional block configuration shown in FIG. 6 includes a data collection unit A1, a model learning unit A2, a model inference unit A3, and a data processing unit A4.
[0040] The data collection unit A1 collects input data, specifically, learning data and inference data, outputs the learning data to the model learning unit A2, and outputs the inference data to the model inference unit A3. The data collection unit A1 may acquire data in the device on which the data collection unit A1 is provided as input data. The data collection unit A1 may also acquire data in another device as input data.
[0041] The model learning unit A2 performs model learning (also referred to as "learning processing"). Specifically, the model learning unit A2 optimizes parameters of a learning model (hereinafter also referred to as a "model" or an "AI / ML model") through machine learning using learning data, derives (generates and updates) a learned model, and outputs the learned model to the model inference unit A3. The model is a data-driven algorithm that applies AI / ML technology to generate a set of outputs based on a set of inputs. For example, considering y = ax + b, a (slope) and b (intercept) are parameters, and optimizing these corresponds to machine learning. Generally, machine learning is classified into supervised learning, unsupervised learning, and reinforcement learning. Supervised learning is a method that uses correct answer data as learning data. Unsupervised learning is a method that does not use correct data for training data. For example, in unsupervised learning, feature points are memorized from a large amount of training data and the correct answer is determined (range estimation). Reinforcement learning is a method that assigns a score to the output result and learns how to maximize the score.
[0042] The model inference unit A3 performs model inference (also referred to as "inference processing"). Specifically, the model inference unit A3 infers an output from inference data using a trained model and outputs the inference result data to the data processing unit A4. For example, in the case of y = ax + b, x corresponds to the inference data and y corresponds to the inference result data. Note that "y = ax + b" is a model. A model in which the slope and intercept are optimized, for example, "y = 5x + 3", is a trained model. There are various modeling techniques, including linear regression analysis, neural networks, and decision tree analysis. The above "y = ax + b" can be considered a type of linear regression analysis. The model inference unit A3 may provide model performance feedback to the model learning unit A2.
[0043] The data processing unit A4 receives the inference result data and performs processing that utilizes the inference result data.
[0044] (3) Example of an Application Scenario of AI / ML Technology Next, an example of an application scenario of AI / ML technology will be described. Fig. 7 is a diagram showing an example of an application scenario of AI / ML technology.
[0045] In this application scenario example, the data collection unit A1, the model learning unit A2, and the model inference unit A3 are arranged in the UE 100 (e.g., the control unit 130), and the data processing unit A4 is arranged in the gNB 200 (e.g., the control unit 230). That is, model learning and model inference are performed on the UE 100 side.
[0046] In addition, in this application scenario example, AI / ML technology is introduced into channel state information (CSI) feedback from UE100 to gNB200. The CSI (CSI feedback information) transmitted (feedback) from UE100 to gNB200 is information regarding the downlink channel state between UE100 and gNB200. The CSI may include at least one of a channel quality indicator (CQI), a precoding matrix indicator (PMI), and a rank indicator (RI). The gNB200 performs, for example, downlink scheduling based on the CSI feedback from UE100.
[0047] The gNB 200 transmits a reference signal for the UE 100 to estimate the downlink channel state. Such a reference signal may be, for example, a CSI reference signal (CSI-RS). Such a reference signal may be a demodulation reference signal (DMRS). Hereinafter, an example in which the reference signal is CSI-RS will be mainly described.
[0048] First, in model learning, UE100 (receiving unit 110) receives a first reference signal from gNB200 using a first resource. Then, UE100 (model learning unit A2) derives a learned model for inferring CSI using learning data including the first reference signal. Such a first reference signal is sometimes referred to as a full CSI-RS.
[0049] For example, the UE 100 (CSI generation unit 131) performs channel estimation using a received signal (CSI-RS) received by the receiver 110 from the gNB 200, and generates CSI. The UE 100 (transmitter 120) transmits the generated CSI to the gNB 200. The UE 100 (model learning unit A2) may, for example, perform model learning using multiple sets of the received signal (CSI-RS) and CSI as learning data, and derive a learned model for inferring CSI from the received signal (CSI-RS). The UE 100 (model learning unit A2) may perform model learning using reception quality and / or UE movement speed as learning data. Here, the reception quality may be reference signal received power (RSRP), reference signal received quality (RSRQ), signal-to-interference-plus-noise ratio (SINR), bit error rate (BER), block error rate (BLER), analog-to-digital converter output waveform, etc.
[0050] Second, in model inference, UE100 (receiving unit 110) receives a second reference signal from gNB200 using a second resource that is less than the first resource. Then, UE100 (model inference unit A3) uses the learned model to infer CSI from inference data including the second reference signal as inference result data. Such a second reference signal may be referred to as a partial CSI-RS or a punctured CSI-RS.
[0051] For example, UE100 (model inference unit A3) uses the received signal (CSI-RS) received by receiver 110 from gNB200 as inference data, and infers CSI from the received signal (CSI-RS) using a learned model. UE100 (transmitter 120) transmits the inferred CSI to gNB200. UE100 (model inference unit A3) may perform model inference using reception quality and / or UE movement speed as inference data.
[0052] This enables UE 100 to feed back accurate (complete) CSI to gNB 200 from the small amount of CSI-RS (partial CSI-RS) received from gNB 200. For example, gNB 200 can reduce (puncture) CSI-RS when intended to reduce overhead. In addition, UE 100 can respond to situations where the radio conditions deteriorate and some CSI-RS cannot be received normally.
[0053] FIG. 8 is a diagram showing a first example of reducing CSI-RS. In the first example, the gNB 200 reduces the number of antenna ports that transmit the CSI-RS. For example, in a mode in which the UE 100 performs model learning, the gNB 200 transmits the CSI-RS from all antenna ports of the antenna panel. On the other hand, in a mode in which the UE 100 performs model inference, the gNB 200 reduces the number of antenna ports that transmit the CSI-RS and transmits the CSI-RS from half the antenna ports of the antenna panel. Note that the antenna port is an example of a resource. This reduces overhead, improves the utilization efficiency of the antenna ports, and reduces power consumption.
[0054] FIG. 9 is a diagram showing a second example of reducing CSI-RS. In the second example, the gNB 200 reduces the number of radio resources, specifically, time-frequency resources, that transmit the CSI-RS. For example, in a mode in which the UE 100 performs model learning, the gNB 200 transmits the CSI-RS using predetermined time-frequency resources. On the other hand, in a mode in which the UE 100 performs model inference, the gNB 200 transmits the CSI-RS using a smaller amount of time-frequency resources than the predetermined time-frequency resources. This reduces overhead, improves the utilization efficiency of radio resources, and reduces power consumption.
[0055] In the following embodiments, an application scenario in which AI / ML technology is applied to CSI feedback will be described, but other application scenarios may be assumed, such as those described in Non-Patent Document 1. Examples of other application scenarios include beam management (beam estimation, overhead / latency reduction, and beam selection accuracy improvement), UE positioning, modulation / demodulation, coding / decoding (CODEC), and packet compression.
[0056] Note that the beam management may be beam management for SSB-based beamforming. Such beam management includes, for example, SSB selection in an RRC idle state and beam monitoring and recovery in an RRC connected state. The beam management may be beam management for CSI-RS-based beamforming (precoding). Such beam management includes, for example, management of PDSCH beamforming in an RRC connected state. For example, the UE 100 uses AI / ML technology to estimate another beam (e.g., beam #2) by measuring a certain beam (e.g., beam #1), specifically, to estimate the measurement results of the other beam.
[0057] In UE positioning, model learning and model inference may be performed using at least one of the following input data: PRS (Positioning Reference Signal), GNSS (Global Navigation Satellite System) location information (latitude, longitude, and altitude), RF fingerprint (cell ID and its reception quality, etc.), angle of arrival (AoA) of the received signal, reception level, reception phase, and reception time difference (OTDOA) for each antenna, round trip time, and short-range wireless reception information such as a wireless LAN (Local Area Network). For example, the training data may be a full PRS. The UE 100 may derive location information from the full PRS and use the full PRS and the location information as training data to generate a trained model that derives location information from the PRS. The training data may be a general reference signal or PRS. If the UE 100 has a GNSS receiver, a trained model that derives location information from the RF fingerprint may be generated using the reception state of the general reference signal or PRS (so-called RF fingerprint) and the GNSS location information as training data. Here, location information provided by a location server may be used in addition to or instead of the GNSS location information.
[0058] (4) Operation According to the Embodiment Next, the operation of the mobile communication system 1 according to the embodiment will be described.
[0059] When UE100 having one or more AI / ML models (trained models) always performs inference processing (model inference) using the AI / ML models during wireless communication with gNB200, the processing load of the inference processing in UE100 may be high. Therefore, problems such as increased power consumption, increased delay in inference processing, and / or increased internal temperature may occur in UE100.
[0060] The following describes a first operation pattern and a second operation pattern for solving such problems. The first operation pattern and the second operation pattern may be implemented independently, or the two operation patterns may be combined. In each of the following operation patterns, it is assumed that the UE 100 has an AI / ML model (a trained model) stored in advance.
[0061] (4.1) First Operation Pattern The first operation pattern is an operation pattern that enables the UE 100 to apply the inference process discontinuously.
[0062] (4.1.1) Overview of First Operation Pattern FIG. 10 is a diagram illustrating an overview of the operation of the UE 100 in the first operation pattern.
[0063] In step S101, the UE 100 receives, from the gNB 200, configuration information for applying an inference process (model inference) using an AI / ML model to wireless communication with the gNB 200. In a first operation pattern, the configuration information includes a discontinuous operation setting for discontinuously applying the inference process. Discontinuously applying the inference process may mean periodically applying the inference process. Discontinuously applying the inference process may mean applying the inference process one-off. The UE 100 may receive, from the gNB 200, an RRC reconfiguration message including such configuration information. That is, the configuration information may be RRC configuration information.
[0064] In step S102, the UE 100 performs wireless communication to which an inference process is applied based on the configuration information received in step S101. The UE 100 may apply the inference process to predicting downlink CSI. The UE 100 may apply the inference process to beam management. The UE 100 may apply the inference process to UE positioning.
[0065] In the first operation pattern, the UE 100 discontinuously applies the inference process based on the discontinuous operation setting. For example, the UE 100 may identify a timing when the inference process is unnecessary based on the discontinuous operation setting, and stop (sleep) the inference process at the identified timing.
[0066] According to this operation, the UE 100 receives setting information for performing discontinuous operation of the model inference process. This enables the UE 100 to apply the inference process discontinuously, thereby reducing the processing load of the inference process in the UE 100. Therefore, it is possible to suppress power consumption, delay in the inference process, and / or an increase in internal temperature in the UE 100.
[0067] The discontinuous operation setting may include at least one of information indicating a timing when the inference process is necessary and information indicating a timing when the inference process is unnecessary. This allows the UE 100 to identify an application timing when the inference process is applied and a non-application timing when the inference process is not applied.
[0068] The discontinuous operation setting may include information about an inference cycle when the inference process is applied periodically. The information about the inference cycle may include an inference start timing (Offset), an inference cycle (Cycle), and an inference duration (Duration (which may also be referred to as "Periodicity")). The information about the inference cycle may further include information indicating an inference end timing at which the periodic inference process is ended. The information indicating the inference start timing and / or the information indicating the inference end timing may be a frame number, subframe number, slot number, or symbol number indicating the end timing. The information may be a combination of two or more of these numbers.
[0069] The discontinuous operation setting may include information about inference timing when the inference process is applied singly. The information about the inference timing may be a frame number, a subframe number, a slot number, or a symbol number indicating the inference timing. The information may also be a combination of two or more of these numbers.
[0070] The setting information may include identification information for identifying an AI / ML model to be used in the inference process. Specifically, the setting information may include identification information for identifying an AI / ML model to be subjected to discontinuous operation. The identification information may be a function ID indicating a function of the AI / ML model. The identification information may be a model ID that uniquely identifies the AI / ML model.
[0071] The configuration information may be information for configuring the application of inference processing to downlink CSI prediction. For example, the configuration information may include a function ID indicating CSI prediction, or a model ID of an AI / ML model for CSI prediction. In step S102, the UE 100 applies the inference processing to predict CSI only at timing when the inference processing is required (application timing). That is, the UE 100 predicts CSI by applying the AI / ML model for CSI prediction at the application timing. This reduces the processing load of the inference processing for CSI prediction in the UE 100. Note that, at non-application timing, the UE 100 performs CSI measurement similar to conventional methods. In this case, the gNB 200 must transmit the same CSI-RS (full CSI-RS) as conventional methods. On the other hand, in the case of gNB200, at the timing when inference processing is required (application timing), UE200 applies the AI / ML model, so that transmission of CSI-RS to UE100 can be simplified (for example, transmission of punctured CSI-RS) or stopped, thereby saving radio resources. gNB200 may set the timing for stopping transmission of CSI-RS to UE100 as the timing when inference processing is required (application timing).
[0072] The setting information may be information for setting the application of inference processing to beam management. For example, the setting information may include a function ID indicating beam management or a model ID of an AI / ML model for beam management. In step S102, UE100 performs beam management by applying inference processing only at the timing when inference processing is required (application timing). That is, UE100 performs beam management by applying the AI / ML model for beam management at the application timing. This reduces the processing load of the inference processing for beam management in UE100. In beam management, for example, when a gNB200 that forms two beams (beams A and B) transmits beam A intermittently, the timing at which the transmission of beam A is stopped is set in UE100 as the timing when inference processing is required (application timing). UE100 estimates beam A from beam B using the AI / ML model for beam management at the set application timing.
[0073] The setting information may be information for setting the application of inference processing to UE positioning. For example, the setting information may include a function ID indicating UE positioning or a model ID of an AI / ML model for UE positioning. In step S102, the UE 100 performs UE positioning by applying the inference processing only at the timing when the inference processing is required (application timing). That is, the UE 100 performs UE positioning by applying the AI / ML model for UE positioning at the application timing. This reduces the processing load of the inference processing for UE positioning in the UE 100. In UE positioning, for example, when the PRS is transmitted intermittently, the gNB 200 sets the timing at which the PRS transmission is stopped to the UE 100 as the timing when the inference processing is required (application timing). The UE 100 performs positioning using the AI / ML model for UE positioning at the set application timing.
[0074] The setting information may be information for applying the inference process to another use case. For example, the other use case may be a DRX operation using an AI / ML model. The other use case may be a mobility operation using an AI / ML model.
[0075] (4.1.2) Example of First Operation Pattern FIG. 11 is a diagram showing an example of operation when inference processing is applied periodically in CSI prediction according to the first operation pattern.
[0076] In Fig. 11, each rectangle represents a slot, and the number in each rectangle represents the slot number. However, instead of processing in slot units, processing may be performed in frame units, subframe units, or symbol units. The example in Fig. 11 shows an example in which the inference start timing (Offset) is set to "5", the inference cycle (Cycle) is set to "6", and the inference duration (Duration) is set to "3".
[0077] In each of slots "0" to "4", gNB200 transmits CSI-RS and UE100 performs CSI measurement. The result of the CSI measurement may be transmitted from UE100 to gNB200 as CSI feedback. During the period from slots "0" to "4", UE100 may perform a learning process to generate or update an AI / ML model for CSI prediction. During this period, UE100 stops the inference process.
[0078] In each of slots "5" to "7", gNB200 stops or reduces the transmission of CSI-RS, and UE100 applies the AI / ML model to perform CSI prediction (inference processing). The result of the CSI prediction may be transmitted from UE100 to gNB200 as CSI feedback.
[0079] In each of slots "8" to "10", gNB200 transmits CSI-RS and UE100 performs CSI measurement. The result of the CSI measurement may be transmitted from UE100 to gNB200 as CSI feedback. During the period from slots "8" to "10", UE100 may perform a learning process to update the AI / ML model for CSI prediction. During this period, UE100 stops the inference process.
[0080] In each of slots "11" to "13", gNB200 stops transmitting CSI-RS, and UE100 applies the AI / ML model to perform CSI prediction (inference processing). The result of the CSI prediction may be transmitted from UE100 to gNB200 as CSI feedback.
[0081] (4.1.3) Example of operation flow of first operation pattern Figure 12 is a diagram showing an example of the operation flow of the mobile communication system 1 according to the first operation pattern. In the illustrated example, the UE 100 is in an RRC connected state in the cell of the gNB 200.
[0082] In step S111, UE 100 may receive CSI-RS from gNB 200 and measure CSI. In step S112, UE 100 may transmit CSI feedback (feedback information) indicating the CSI measurement result of step S111 to gNB 200. Note that steps S111 and S112 are conventional CSI feedback operations that do not apply inference processing.
[0083] In step S113, the gNB 200 transmits to the UE 100 an RRC Reconfiguration message including configuration information for configuring the UE 100 to perform processing using the inference processing. The UE 100 receives the configuration information from the gNB 200. Note that the gNB 200 may transmit the configuration information to the UE 100 by a MAC Control Element (CE) or downlink control information (DCI) instead of the RRC Reconfiguration message.
[0084] In operation pattern 1, the setting information includes the discontinuous operation setting as described above. The setting information may include identification information of the AI / ML model. The setting information may include information indicating a frequency resource (e.g., a frequency band, a BWP) to which model inference is applied. The setting information may include information indicating a space (e.g., a tracking area, an arbitrary geographical location) to which model inference is applied. The setting information may include settings related to inference data (input data to the model). The setting may be information indicating how many past CSI measurement results should be input to the AI / ML model (e.g., at least 10 times).
[0085] In step S114, UE100 identifies the timing at which the inference process should be performed (application timing) and / or the timing at which it does not need to be performed (non-application timing) based on the setting information (discontinuous operation setting) received in step S113.
[0086] At the non-application timing of steps S115 and S116, the UE 100 may perform a conventional CSI feedback operation without applying the inference process.
[0087] At the application timing of steps S117 and S118, the UE 100 performs a CSI feedback operation to which the inference process is applied.
[0088] (4.2) Second Operation Pattern The second operation pattern will be described, focusing on the differences from the first operation pattern. The second operation pattern is an operation pattern that enables the UE 100 to request the gNB 200 to change settings to reduce the processing load of the inference process.
[0089] (4.2.1) Overview of Second Operation Pattern FIG. 13 is a diagram illustrating an overview of the operation of the UE 100 in the second operation pattern.
[0090] In step S201, the UE 100 receives, from the gNB 200, configuration information for applying inference processing using the AI / ML model to wireless communication with the gNB 200. In the second operation pattern, the configuration information may include the discontinuous operation configuration described above. This configuration information may not be included. The configuration information of the UE 100 may include identification information of the AI / ML model. The UE 100 may receive, from the gNB 200, an RRC Reconfiguration message including such configuration information. That is, the configuration information may be RRC configuration information.
[0091] In step S202, the UE 100 performs wireless communication to which an inference process is applied based on the configuration information received in step S201. The UE 100 may apply the inference process to predicting downlink CSI. The UE 100 may apply the inference process to beam management. The UE 100 may apply the inference process to UE positioning.
[0092] In step S203, the UE 100 determines whether a predetermined condition is satisfied. The predetermined condition may be a condition that an internal overheating state in the UE 100 is detected. The predetermined condition may be a condition that a state in which power consumption of the UE 100 is higher than a threshold is detected. The predetermined condition may be a condition in which the remaining battery charge of the UE 100 is below a threshold. The predetermined condition may further include a condition in which permission to transmit AI / ML preference information is set by the gNB 200. If the predetermined condition is not satisfied (step S203: NO), the process returns to step S202.
[0093] If it is determined that the predetermined condition is satisfied (step S203: YES), in step S204, the UE 100 transmits AI / ML preference information indicating a preference for setting changes to reduce the processing load of the inference process to the gNB 200. The UE 100 may transmit a UE Assistance Information message including the AI / ML preference information to the gNB 200. The UE Assistance Information message is a type of RRC message.
[0094] According to such an operation, the UE 100 can indicate to the gNB 200 a preference for a setting change for reducing the processing load of the inference process, and therefore the gNB 200 can make a setting change for reducing the processing load of the inference process to the UE 100. As a result, the processing load of the inference process in the UE 100 can be reduced, and power consumption in the UE 100, delays in the inference process, and / or increases in internal temperature can be suppressed.
[0095] In the second operation pattern, the AI / ML preference information may include a limit value for the processing load of the inference process. This allows the gNB 200 to change (reconfigure) the setting of the UE 100 so that the processing load of the inference process is within the range of the limit value.
[0096] In the second operation pattern, the AI / ML preference information may include information indicating the stop of the inference process as a preference. This allows the gNB 200 to change (reconfigure) the setting of the UE 100 so as to stop the inference process.
[0097] (4.2.2) Example of operation flow of second operation pattern Figure 14 is a diagram showing an example of the operation flow of the mobile communication system 1 according to the second operation pattern. In the illustrated example, the UE 100 is in an RRC connected state in the cell of the gNB 200.
[0098] In step S211, UE 100 may receive CSI-RS from gNB 200 and measure CSI. In step S212, UE 100 may transmit CSI feedback (feedback information) indicating the CSI measurement result of step S211 to gNB 200. Note that steps S211 and S212 are conventional CSI feedback operations that do not apply inference processing.
[0099] In step S213, the gNB 200 transmits to the UE 100 an RRC Reconfiguration message including configuration information for configuring the UE 100 to perform processing using the inference processing. The UE 100 receives the configuration information from the gNB 200. Note that the gNB 200 may transmit the configuration information to the UE 100 by a MAC Control Element (CE) or downlink control information (DCI) instead of the RRC Reconfiguration message. Alternatively, if a new layer (e.g., an AI / ML layer) is defined, the configuration information may be signaling of the AI / ML layer. The configuration information may be a configuration for applying the inference processing to prediction of downlink CSI. The configuration information may be a configuration for applying the inference processing to beam management. The configuration information may be a configuration for applying the inference processing to UE positioning. In the second operation pattern, the setting information may include a setting indicating that transmission of the AI / ML preference information is permitted for the UE 100. The UE 100 may be able to transmit the AI / ML preference information only when the transmission of the AI / ML preference information is permitted.
[0100] In step S214, the UE 100 performs wireless communication to which the inference process is applied, based on the setting information received in step S213. The UE 100 may apply the inference process to predicting downlink CSI. The UE 100 may apply the inference process to beam management. The UE 100 may apply the inference process to UE positioning. When the inference process is applied to predicting downlink CSI, in step S215, the UE 100 may transmit the CSI predicted by the inference process to the gNB 200 as CSI feedback.
[0101] In step S216, the UE 100 determines whether or not a predetermined condition for transmitting AI / ML preference information is satisfied. If the predetermined condition is not satisfied (step S216: NO), the process returns to step S214.
[0102] On the other hand, if it is determined that the predetermined condition is satisfied (step S216: YES), in step S217, the UE 100 transmits AI / ML preference information to the gNB 200. The gNB 200 receives the AI / ML preference information.
[0103] For example, the UE 100 may determine that the predetermined condition is satisfied in response to detecting an internal overheating state (internal temperature rise) in the UE 100. In this case, the UE 100 may include AI / ML preference information in Overheating Assistance Information, which is an information element in the UE Assistance Information message, and transmit it to the gNB 200.
[0104] The UE 100 may determine that the predetermined condition is satisfied in response to detecting an excessive power consumption state (over-power-consumption), a state in which the remaining battery capacity of the UE 100 is below a certain level, or a state in which the processing load is above a certain level (an over-processing state that affects the processing of the communication itself). In such a case, the UE 100 may include AI / ML preference information as an information element different from the Overheating Assistance Information in the UE Assistance Information message.
[0105] The AI / ML preference information may include a limit value related to the processing load of the inference process. The AI / ML preference information may include identification information of the AI / ML model for which the inference process is to be limited, for example, a model ID or a function ID (which may be the name of the function). Such AI / ML preference information may be referred to as Reduced-Model-Inference-Preference. For example, the AI / ML preference information is information indicating the maximum number (limit value) of AI / ML models for which the UE 100 executes the inference process. The AI / ML preference information may be information indicating at least one of the limit value of the number of simultaneously executing models for model inference (inference process), the limit value of the number of simultaneously executing models for model learning (learning process), and the limit value of the number of simultaneously executing models for inference and learning. The AI / ML preference information may include at least one of a limit value of processing capacity, for example, a limit value of the number of neurons or synapses of a DNN (Deep Neural Network), a limit value of FLOPS, and a limit value of memory or CPU usage (usage rate).
[0106] The AI / ML preference information may include information indicating a preference for stopping (e.g., deactivating) the inference process. Such AI / ML preference information may be referred to as Model-Deactivation-Preference. The AI / ML preference information may include identification information of the AI / ML model whose execution is to be stopped, such as a model ID or a function ID (which may be the name of the function).
[0107] In step S218, the gNB 200 may reconfigure the UE 100 based on the AI / ML preference information, i.e., according to the preferences of the UE 100. For example, the gNB 200 may transmit to the UE 100 an RRC Reconfiguration message (or a MAC CE, etc.) including configuration information for executing the inference process within a limit value related to the processing load of the inference process. The gNB 200 may transmit to the UE 100 an RRC Reconfiguration message (or a MAC CE, etc.) including configuration information for stopping the inference process. Alternatively, if a new layer (e.g., an AI / ML layer) is defined, this may be signaling of the AI / ML layer. The inference process may be stopped by canceling the configuration contents (configuration release) of step S213. The inference process may also be stopped by deactivating the inference process.
[0108] In addition, if a predetermined condition is satisfied and the UE 100 transmits AI / ML preference information to the gNB 200, and then the predetermined condition is no longer satisfied, the UE 100 may notify the gNB 200 that the predetermined condition is no longer satisfied. For example, the notification may be to transmit AI / ML preference information that does not include limit value and inference stop information to the gNB 200. The notification may be to transmit a UE Assistance Information message that does not include AI / ML preference information to the gNB 200.
[0109] (5) Other Embodiments In the above-described embodiment, the operation of the UE 100 discontinuously performing the inference process (model inference) has been mainly described. However, in addition to or instead of such an operation, the UE 100 may be modified to perform the learning process (model learning) discontinuously. In such a modified example, the "inference process" in the first and second operation patterns described above may be read as "learning process" or "learning process and inference process."
[0110] In the above-described embodiment, an example has been described in which AI / ML-related signaling related to the AI / ML technology is an RRC message, which is signaling of the RRC layer (i.e., Layer 3). However, the AI / ML-related signaling may be a MAC Control Element (CE), which is signaling of the MAC layer (i.e., Layer 2). The AI / ML-related signaling may be downlink control information (DCI) and / or uplink control information (UCI), which are signaling of the PHY layer (i.e., Layer 1). The downlink AI / ML-related signaling may be UE-dedicated signaling. The downlink AI / ML-related signaling may be broadcast signaling. AI / ML-related signaling may be signaling in a new layer (e.g., an AI / ML layer) specialized for artificial intelligence or machine learning.
[0111] The above-described operational flows are not limited to being implemented independently, but can also be implemented by combining two or more operational flows. For example, some steps of one operational flow may be added to another operational flow, or some steps of one operational flow may be replaced with some steps of another operational flow. In each flow, it is not necessary to execute all steps, and only some steps may be executed.
[0112] In the above embodiment, an example in which the base station is an NR base station (gNB) has been described, but the base station may also be an LTE base station (eNB). The base station may also be a relay node such as an IAB (Integrated Access and Backhaul) node. The base station may also be a DU (Distributed Unit) of the IAB node. The user equipment (terminal device) may also be a relay node such as an IAB node, or an MT (Mobile Termination) of the IAB node.
[0113] That is, the UE 100 may be a terminal function unit (a type of communication module) for a base station to control a repeater that relays signals. Such a terminal function unit is referred to as an MT. Examples of the MT include, in addition to the IAB-MT, an NCR (Network Controlled Repeater)-MT and a RIS (Reconfigurable Intelligent Surface)-MT.
[0114] The term "network node" primarily refers to a base station, but may also refer to a core network device or a part of a base station (CU, DU, or RU). A network node may also be configured by a combination of at least a part of a core network device and at least a part of a base station.
[0115] A program may be provided that causes a computer to execute each process performed by a communication device (for example, UE 100 or gNB 200). The program may be recorded on a computer-readable medium. Using a computer-readable medium, the program can be installed on a computer. Here, the computer-readable medium on which the program is recorded may be a non-transitory recording medium. The non-transitory recording medium is not particularly limited, and may be, for example, a recording medium such as a CD-ROM or DVD-ROM. Furthermore, circuits that execute each process performed by the communication device may be integrated, and at least a part of the communication device may be configured as a semiconductor integrated circuit (chip set, SoC: System on a chip).
[0116] The functions performed by the UE 100 or the gNB 200 (network node) may be implemented in circuitry or processing circuitry, including general-purpose processors, application-specific processors, integrated circuits, ASICs (Application Specific Integrated Circuits), CPUs (Central Processing Units), conventional circuits, and / or combinations thereof, programmed to perform the described functions. A processor includes transistors and other circuits and is considered to be circuitry or processing circuitry. A processor may also be a programmed processor that executes a program stored in memory. In this specification, circuitry, unit, or means refers to hardware that is programmed to perform the described functions or hardware that executes them. The hardware may be any hardware disclosed herein or any hardware known to be programmed or capable of performing the described functions. If the hardware is a processor, the circuitry, means, or unit is a combination of hardware and software used to configure the hardware and / or processor.
[0117] As used in this disclosure, the terms "based on" and "depending on" do not mean "based only on" or "depending only on," unless expressly stated otherwise. The term "based on" means both "based only on" and "based at least in part on." Similarly, the term "depending on" means both "based only on" and "at least in part on." Furthermore, "obtain" may mean obtaining information from stored information, obtaining information from information received from another node, or obtaining information by generating the information. The terms "include," "comprise," and variations thereof do not mean including only the listed items, but may also mean including only the listed items or including additional items in addition to the listed items. Furthermore, as used in this disclosure, the term "or" is not intended to mean an exclusive or. Furthermore, any reference to an element using a designation such as "first," "second," etc., as used in this disclosure does not generally limit the quantity or order of those elements. These designations may be used herein as a convenient method of distinguishing between two or more elements. Thus, reference to a first and a second element does not imply that only two elements may be employed therein, or that the first element must precede the second element in some way. In this disclosure, when articles are added by translation, such as a, an, and the in English, these articles are intended to include the plural unless the context clearly dictates otherwise.
[0118] The above describes the embodiments in detail with reference to the drawings, but the specific configuration is not limited to that described above, and various design changes can be made within the scope that does not deviate from the gist of the invention.
[0119] This application claims priority from Japanese Patent Application No. 2023-129203 (filed August 8, 2023), the entire contents of which are incorporated herein by reference.
[0120] (6) Supplementary Notes The following are additional notes regarding the features of the above-described embodiment.
[0121] (Supplementary Note 1) A communication method executed by a user device in a mobile communication system, comprising: a step of receiving, from a network node, configuration information for applying an inference process using an artificial intelligence or machine learning (AI / ML) model to wireless communication with the network node; and a step of performing the wireless communication to which the inference process is applied based on the configuration information, wherein the configuration information includes a discontinuous operation setting for discontinuously applying the inference process, and the step of performing the wireless communication includes a step of discontinuously applying the inference process.
[0122] (Supplementary Note 2) The communication method according to Supplementary Note 1, wherein the discontinuous operation setting includes at least one of information indicating a timing when the inference process is necessary and information indicating a timing when the inference process is unnecessary.
[0123] (Supplementary Note 3) The communication method according to Supplementary Note 2, wherein the discontinuous operation setting includes at least one of information regarding an inference period when the inference process is applied periodically and information regarding an inference timing when the inference process is applied singly.
[0124] (Supplementary Note 4) The communication method according to any one of Supplementary Notes 1 to 3, wherein the step of discontinuously applying the inference processing includes the steps of: identifying a timing at which the inference processing is unnecessary based on the discontinuous operation setting; and stopping the inference processing at the identified timing.
[0125] (Supplementary Note 5) The communication method according to any one of Supplementary Notes 1 to 4, wherein the receiving step comprises receiving a Radio Resource Control (RRC) reconfiguration message from the network node, the RRC reconfiguration message including the configuration information.
[0126] (Supplementary Note 6) The communication method according to any one of Supplementary Notes 1 to 5, wherein the setting information includes identification information for identifying the AI / ML model used in the inference process.
[0127] (Supplementary Note 7) The communication method according to any one of Supplementary Notes 1 to 6, wherein the setting information is information for setting application of the inference process to prediction of downlink channel state information (CSI), and the step of performing wireless communication includes a step of applying the inference process to prediction of the CSI at a timing when the inference process is required.
[0128] (Supplementary Note 8) A communication method executed by a user device in a mobile communication system, comprising: a step of receiving, from a network node, configuration information for applying inference processing using an artificial intelligence or machine learning (AI / ML) model to wireless communication with the network node; a step of performing the wireless communication to which the inference processing is applied based on the configuration information; and a step of transmitting, to the network node, AI / ML preference information indicating preferences for setting changes to reduce the processing load of the inference processing.
[0129] (Supplementary Note 9) The communication method according to Supplementary Note 8, wherein the sending step includes sending a UE Assistance Information message including the AI / ML preference information to the network node.
[0130] (Supplementary Note 10) The communication method according to Supplementary Note 8 or 9, wherein the AI / ML preference information includes a limit value related to the processing load.
[0131] (Supplementary Note 11) The communication method according to any one of Supplementary Notes 8 to 10, wherein the AI / ML preference information includes information indicating, as the preference, stopping the inference process.
[0132] (Supplementary Note 12) The communication method according to any one of Supplementary Notes 8 to 11, further comprising the step of detecting an internal overheating condition in the user equipment, wherein the transmitting step includes the step of transmitting the AI / ML preference information to the network node in response to the detection of the internal overheating condition.
[0133] 1: Mobile communication system 5: Network 10: RAN (NG-RAN) 20: CN (5GC) 100: UE 110: Receiving unit 120: Transmitting unit 130: Control unit 131: CSI generating unit 200: gNB 210: Transmitting unit 220: Receiving unit 230: Control unit 240: Backhaul communication unit A1: Data collection unit A2: Model learning unit A3: Model inference unit A4: Data processing unit
Claims
1. A communication method performed by a user device in a mobile communication system, Receiving configuration information from the network node for applying inference processing using an artificial intelligence or machine learning (AI / ML) model to wireless communication with the network node, The process includes performing the inference process based on the aforementioned setting information, The aforementioned configuration information includes frequency resource information predicted by the inference process. Communication method.
2. The setting information includes information regarding the inference period when the inference process is applied periodically, The information relating to the inference period further includes the period during which the prediction is made by the inference process and the number of times the prediction is made by the inference process. The communication method according to claim 1.
3. A user device in a mobile communication system, A receiving unit that receives configuration information from a network node for applying inference processing using artificial intelligence or machine learning (AI / ML) models to wireless communication with the network node, The system includes a control unit that performs the inference processing based on the setting information, The aforementioned configuration information includes frequency resource information predicted by the inference process. User device.
4. A mobile communication system having a user device and a network node, The user device receives configuration information from the network node for applying inference processing using artificial intelligence or machine learning (AI / ML) models to wireless communication with the network node. The user device performs the inference process based on the configuration information. The aforementioned configuration information includes frequency resource information predicted by the inference process. Mobile communication system.
5. A user device in a mobile communication system, A process for receiving configuration information from a network node for applying inference processing using artificial intelligence or machine learning (AI / ML) models to wireless communication with the network node, Based on the aforementioned configuration information, the process of performing the inference process is executed. The aforementioned configuration information includes frequency resource information predicted by the inference process. program.
6. A chipset for a user device in a mobile communication system, Receiving configuration information from the network node for applying inference processing using artificial intelligence or machine learning (AI / ML) models to wireless communication with the network node, The process includes performing the inference process based on the aforementioned setting information, The aforementioned configuration information includes frequency resource information predicted by the inference process. Chipset.