Communication method, user equipment, and network node

Abstract

This communication method is executed by a user equipment in a mobile communication system and comprises: performing connection failure prediction for predicting whether a radio connection failure will occur in the future, using an artificial intelligence or machine learning (AI / ML) model in a radio resource control (RRC) connected state in which the user equipment is connected to a network node; and transmitting a message related to a result of the connection failure prediction to the network node.

Description

COMMUNICATION METHOD, USER EQUIPMENT, AND NETWORK NODE

[0001] The present disclosure relates to a communication method, a user equipment, and a network node for use in a mobile communication system.

[0002] 3GPP (Third Generation Partnership Project) (registered trademark; the same applies hereinafter), a standardization project for mobile communication systems, is considering applying artificial intelligence or machine learning (also referred to as "AI / ML") technology to wireless communication (i.e., air interface) of mobile communication systems.

[0003] 3GPP contribution: RP-234055, “Study on Artificial Intelligence (AI) / Machine Learning (ML) for mobility in NR”

[0004] A communication method according to a first aspect is a communication method executed by a user equipment in a mobile communication system, the method comprising: in a Radio Resource Control (RRC) Connected state in which the user equipment is connected to a network node, performing connection failure prediction using an artificial intelligence or machine learning (AI / ML) model to predict whether a radio connection failure will occur in the future; and transmitting a message relating to the result of the connection failure prediction to the network node.

[0005] A user equipment according to a second aspect is a user equipment used in a mobile communication system, and includes: a control unit that performs connection failure prediction using an artificial intelligence or machine learning (AI / ML) model to predict whether a wireless connection failure will occur in the future when the user equipment is in a radio resource control (RRC) connected state in which the user equipment is connected to a network node; and a transmission unit that transmits a message regarding the result of the connection failure prediction to the network node.

[0006] A network node according to a third aspect is a network node for use in a mobile communication system, the network node including: a receiving unit configured to receive, from a user equipment (UE) in a radio resource control (RRC) connected state connected to the network node, a message regarding a result of a connection failure prediction using an artificial intelligence or machine learning (AI / ML) model; and a control unit configured to perform mobility control of the user equipment (UE) based on the message. The connection failure prediction is a process of predicting whether a wireless connection failure will occur in the future.

[0007] 1 is a diagram showing an example of the configuration of a mobile communication system according to an embodiment. FIG. 2 is a diagram showing an example of the configuration of a UE (user equipment) according to an embodiment. FIG. 3 is a diagram showing an example of the configuration of a gNB (network node) according to an embodiment. FIG. 4 is a diagram showing a protocol stack configuration of a radio interface of a user plane that handles data. FIG. 5 is a diagram showing a protocol stack configuration of a radio interface of a control plane that handles signaling (control signals). FIG. 6 is a diagram showing a configuration related to measurements by a UE according to an embodiment. FIG. 7 is a diagram showing a functional block configuration of AI / ML technology in a mobile communication system according to an embodiment. FIG. 8 is a diagram showing an example of an operation scenario of a mobile communication system according to an embodiment. FIG. 9 is a diagram showing an operation sequence according to an embodiment.

[0008] The technology described in the background art above is considered to be a use case of the AI / ML technology for mobility control of user equipment. For example, it is considered to apply the AI / ML technology to predict wireless connection failures such as handover failures or radio link failures (also referred to as "HOF / RLF"). However, a specific mechanism for applying the AI / ML technology to mobility control of user equipment has not yet been established, making it difficult to utilize the AI / ML technology in mobile communication systems.

[0009] The present disclosure aims to utilize AI / ML technology in mobile communication systems.

[0010] 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.

[0011] (1) Configuration of a Mobile Communication System FIG. 1 is a diagram showing an example of the configuration of a mobile communication system 1 according to an embodiment. The mobile communication system 1 conforms to the 3GPP standard 5th Generation System (5GS). While the following description uses 5GS as an example, the mobile communication system may also be at least partially based on an LTE (Long Term Evolution) system. The mobile communication system may also be at least partially based on a 6th Generation (6G) system.

[0012] 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.

[0013] The UE 100 is a mobile wireless communication device. The UE 100 may be any device 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 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). A link in the transmission direction from the UE 100 to the network 5 is referred to as an uplink (UL), and a link in the transmission direction from the network 5 to the UE 100 is referred to as a downlink (DL).

[0014] The NG-RAN 10 includes a base station (referred to as "gNB" in the 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 the 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, etc. 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 that performs wireless communication with the UE 100. One cell belongs to one carrier frequency (hereinafter simply referred to as "frequency").

[0015] 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.

[0016] 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.

[0017] 2 is a diagram illustrating an example configuration of a UE 100 (user equipment) according to an embodiment. The UE 100 includes a receiving unit 110, a transmitting unit 120, and a control unit 130. The receiving unit 110 and the transmitting unit 120 configure a wireless communication unit 140 that performs wireless communication with the gNB 200.

[0018] The receiving unit 110 performs various reception operations 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.

[0019] 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.

[0020] The control unit 130 performs various controls and processes in the UE 100. Such processes include processes of each layer described below. The operations of the UE 100 described above and below may be operations controlled by the control unit 230. 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.

[0021] 3 is a diagram showing an example 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 network communication unit 240. The transmitter 210 and the receiver 220 constitute a wireless communication unit 250 that performs wireless communication with the UE 100. The network communication unit 240 has a transmitter 241 that transmits and a receiver 242 that receives.

[0022] 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.

[0023] 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.

[0024] The control unit 230 performs various controls and processes in the gNB 200. Such processes include processes for each layer described below. The operations of the gNB 200 described above and below may be operations under the control of the control unit 230. 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 the 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.

[0025] The network communication unit 240 is connected to adjacent base stations via an Xn interface, which is an interface between base stations. The network 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 is composed of a CU (Central Unit) and a DU (Distributed Unit) (i.e., functionally divided), and the two units may be connected by an F1 interface, which is a fronthaul interface.

[0026] FIG. 4 is a diagram showing the configuration of a protocol stack of a radio interface of a user plane that handles data.

[0027] The user plane radio 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] The PDCP layer performs header compression / decompression, encryption / decryption, and the like.

[0032] 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.

[0033] 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).

[0034] The protocol stack of the radio interface of the control plane has an RRC (Radio Resource Control) layer and an NAS (Non-Access Stratum) layer instead of the SDAP layer shown in FIG.

[0035] 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.

[0036] The NAS layer (also simply referred to as "NAS") located above the RRC layer performs session management, mobility management, etc. NAS signaling is transmitted between the NAS layer of the UE 100 and the NAS layer 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 layer is referred to as the AS layer (also simply referred to as "AS").

[0037] (2) Measurement by UE The UE 100 in the RRC connected state performs measurements used for mobility control. Measurements include intra-frequency measurements within the same frequency as the current serving cell and inter-frequency measurements within a frequency different from that of the current serving cell. Measurements also include inter-RAT measurements for a RAT (Radio Access Technology) different from that of the current serving cell. The gNB 200 transmits a measurement configuration (measurement command) to the UE 100 via RRC to instruct the UE 100 to start, change, or stop the measurement.

[0038] For each measurement type, one or more measurement targets (also called "measurement objects") can be defined. A measurement object is, for example, a monitored frequency (carrier frequency), but can also be a cell. For each measurement object, one or more reporting configurations can be defined, which define the reporting criteria. There are three reporting criteria (types of measurement reports): event-triggered reporting, periodic reporting, and event-triggered periodic reporting.

[0039] The association between a measurement object (measurement object ID) and a reporting configuration (measurement configuration ID) is made by a measurement identity (measurement ID). The measurement ID links one measurement object and one reporting configuration of the same RAT. Using multiple measurement IDs (one per measurement object-reporting configuration pair) allows associating multiple reporting configurations with one measurement object or one reporting configuration with multiple measurement objects. The measurement ID is also used when reporting measurement results.

[0040] The UE 100 in the RRC connected state measures at least one beam of a cell and averages the measurement results (power values) to derive the radio quality (also referred to as "reception quality") for the cell. In this case, the UE 100 is configured to consider a subset of the detected beams. Here, filtering, which is measurement averaging, is performed at two different levels. The UE 100 first derives beam quality by L1 filtering, which is filtering at the physical layer (PHY, Layer 1 (L1)), and then derives cell quality from multiple beams by L3 filtering, which is filtering at the RRC layer (Layer 3 (L3)) level. Note that the cell quality from beam measurements is derived in the same way for serving and non-serving cells. Depending on the configuration by the gNB 200, the UE 100 may include measurement results of the X best beams in the L3 measurement report.

[0041] 6 is a diagram showing a configuration related to measurements by the UE 100 according to the embodiment. The control unit 130 of the UE 100 includes an L1 filter 11, a beam combining / selecting unit 12, an L3 filter 13, an evaluation unit 14, an L3 beam filter 15, and a beam selecting unit 16. The control unit 130 receives input of the radio quality of a beam measured by any of the receivers 111 in the receiving unit 110. In the illustrated example, there are two receivers 111 (receiver 111a and receiver 111b), but there may be one receiver 111, or three or more receivers 111. Hereinafter, the receiver 111 is also referred to as an "RF (Radio Frequency) chain." The multiple receivers 111 may support different frequencies.

[0042] The L1 filter 11 includes K L1 filters 11 corresponding to the K beams. K measurement results A obtained by the UE 100 (receiving unit 110) measuring the radio quality for each of the K beams are input to the L1 filter 11. The K measurement results A for the K beams are measurement results (beam-specific samples) within the physical layer, and are measurement results of SSB (SS / PBCH block) or CSI (Channel State Information) reference signal resources detected by the UE 100 (receiving unit 110) in L1. The L1 filter 11 performs L1 filtering on the K measurement results A for the K beams in L1, and outputs the beam-specific measurement results A after the L1 filtering. １ are output to the beam combining / selecting unit 12 and the L3 beam filter 15.

[0043] The beam integration / selection unit 12 outputs the beam-specific measurement result A １ to derive the cell radio quality (Cell quality) B, and output the cell quality B to the L3 filter 13. The operation setting of the beam combining / selecting unit 12 is provided by RRC signaling from the gNB 200.

[0044] The L3 filter 13 filters the measurement result (cell quality B) output by the beam combining / selecting unit 12 at L3 and outputs the measurement result C after L3 filtering to the evaluation unit 14. The configuration of the operation of the L3 filter 13 is provided by RRC signaling from the gNB 200. The measurement result C after L3 filtering is used as input for one or more evaluations of an L3 measurement report from the UE 100 to the gNB 200.

[0045] The L3 filter 13 filters the measurement results for each cell measurement and each beam measurement by the following equation (1) before using them for evaluation of reporting criteria or for L3 measurement reporting: F ｎ = (1 - a) x F ｎ－１ + a × M ｎ ...(1) where M ｎ is the latest measurement result from the physical layer (L1). ｎF is the updated filtered measurement result, which is used for evaluation of reporting criteria or L3 measurement reporting. ｎ－１ is the old filtered measurement, F is the measurement result when the first measurement is received from the physical layer (L1). ０ M １ is set to

[0046] When MeasObjectNR is set in RRC, a = 1 / 2 （ｋｉ／４） Here, k ｉ is the filter coefficient of the corresponding measurement of the ith QuantityConfigNR in the quantityConfigNR-List, where i is indicated by the quantityConfigIndex in the MeasObjectNR. For other measurements, a=½ （ｋ／４） where k is the filter coefficient of the corresponding measurement received by quantityConfig.

[0047] The L3 filter 13 adapts the filter so that its time characteristics are preserved at different input rates, while the filter coefficient k assumes a sample rate equal to X ms, where the value of X corresponds to one intra-frequency L1 measurement period assuming non-DRX operation and is frequency range dependent.

[0048] Note that if the filter coefficient k is set to 0 (zero), no L3 filtering is applied.

[0049] The evaluation unit 14 evaluates whether an L3 measurement report D to the gNB 200 is necessary. This evaluation can be performed based on a comparison of multiple measurement flows at the reference point C, for example, different measurement results. This is done by comparing input C and input C １ The evaluation unit 14 determines whether at least the new measurement results are at points C, C １Each time a measurement report is made, a measurement reporting event evaluation corresponding to the reporting criteria is performed. The reporting criteria setting is provided by RRC signaling from the gNB 200. The L3 measurement report D represents measurement report information (RRC message) transmitted from the UE 100 to the gNB 200. The L3 measurement report D includes the measurement ID of the associated measurement setting that triggered the report.

[0050] The L3 beam filter 15 receives k measurement results A １ (i.e., beam-specific measurement results) are filtered on a per-beam basis, and k measurement results E (i.e., beam-specific measurement results) are output to the beam selector 16. The measurement results E are used as input to select the X measurement results to be reported.

[0051] The beam selection unit 16 selects X measurement results F from the k measurement results E and outputs the X measurement results F. The X measurement results F are beam measurement information included in the measurement report information (RRC message) transmitted from E100 to gNB200.

[0052] (3) Detection of Radio Connection Failure Types of radio connection failure include RLF and HOF, which are detected based on radio link monitoring (RLM). The UE 100 in the RRC connected state performs radio link monitoring (RLM) in an active BWP (Bandwidth Part) based on a reference signal (RS) and a signal quality threshold set by the network 5. The reference signal may be an SSB (Synchronization Signal and PBCH block) or a CSI (Channel state information)-RS.

[0053] The UE 100 basically declares (detects) RLF in response to expiration of a radio problem timer that is started after notification of a radio problem from the physical layer (if the radio problem is recovered before the timer expires, the UE 100 stops the timer). When the UE 100 detects RLF in a serving cell, the UE 100 remains in an RRC connected state, selects an appropriate cell, and starts RRC re-establishment. Then, if the UE 100 does not find an appropriate cell within a certain time after the RLF is detected, the UE 100 transitions to an RRC idle state.

[0054] In order to analyze the radio connection failure on the network 5 side, the UE 100 makes the RLF report available to the network 5. The UE 100 stores the latest RLF report until the RLF report is obtained by the network 5 or for a certain period of time after the radio connection failure is detected. The UE 100 indicates the availability of the RLF report to the network 5 and provides the RLF report upon request from the network 5.

[0055] The occurrence of RLF in connection with handover is called handover failure (HOF), which can be caused by handover too late, too early, or handover to the wrong cell.

[0056] In a too late handover, RLF occurs after the UE 100 has been in the source cell for a long period of time, and the UE 100 attempts to re-establish the radio link connection in another cell.

[0057] In a premature handover, the RLF occurs immediately after a successful handover from the source cell to the target cell or if the handover fails during the handover procedure, and the UE 100 attempts to re-establish the radio link connection with the source cell.

[0058] In a handover to a wrong cell, RLF occurs immediately after a successful handover from a source cell to a target cell or if the handover fails during the handover procedure, and the UE 100 attempts to re-establish a radio link connection with a cell other than the source and target cells.

[0059] Another type of radio connection failure is beam failure. In the case of beam failure detection, the gNB 200 configures the UE 100 to use a reference signal (SSB or CSI-RS) for beam failure detection. The UE 100 declares (detects) beam failure if the number of beam failure instance indicators from the physical layer reaches a configured threshold before the configured timer expires. In the case of beam failure detection in multi-transmission / reception point (TRP) operation, the gNB 200 configures the UE 100 to use two sets of reference signals for beam failure detection.

[0060] (4) Overview of AI / ML Technology 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).

[0061] 7 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 includes a data collection unit A1, a model learning unit A2, a model inference unit A3, and a data processing unit A4.

[0062] 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.

[0063] 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.

[0064] 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.

[0065] The data processing unit A4 receives the inference result data and performs processing that utilizes the inference result data.

[0066] A case in which model learning and / or model inference is performed on the network 5 side, i.e., a case in which the network 5 has an AI / ML model, is referred to as a network-sided model. A case in which model learning and / or model inference is performed on the UE 100 side, i.e., a case in which the UE 100 has an AI / ML model, is referred to as a UE-sided model.

[0067] (5) Operation According to the Embodiment In the embodiment, the AI / ML technology is applied to mobility control of the UE 100. Specifically, the AI / ML technology is applied to predict the occurrence of a wireless connection failure. The UE 100 has an AI / ML model for predicting (specifically, predicting using model inference) whether a wireless connection failure will occur in the future. That is, in the embodiment, a UE-side model is used.

[0068] A "radio connection failure" is a failure in a radio connection, and is detected by monitoring a monitoring target (e.g., RLM). A "monitoring target" is a cell, a beam, or a reference signal. Radio connection failures detected for a cell include RLF and HOF. A radio connection failure detected for a beam is a beam failure. In the embodiment, RLF and HOF are mainly assumed as radio connection failures, but a beam failure may also be included in the radio connection failure. "A radio connection failure will occur in the future" may mean that a radio connection failure will not occur in the current radio environment, but a radio connection failure will occur in the near future.

[0069] First, an overview of the operation according to the embodiment will be described. Fig. 8 is a diagram showing an example of an operation scenario of the mobile communication system 1 according to the embodiment.

[0070] In the illustrated example, the UE 100 is in an RRC connected state with cell a of the gNB 200 as the serving cell. There are multiple neighboring cells (cell b, cell c, cell d) that partially overlap with this serving cell. The neighboring cells may be managed by the same gNB 200 as the serving cell. The neighboring cells may be managed by a gNB 200 different from the serving cell. The frequencies of each cell may be the same. The frequencies may be different.

[0071] In step S1, the gNB 200 transmits configuration information for configuring connection failure prediction (hereinafter also referred to as "failure prediction configuration") to the UE 100. The gNB 200 may also transmit measurement configuration information to the UE 100. The UE 100 receives the configuration information. Note that the measurement configuration may include a measurement object (and its ID), a reporting configuration (and its ID), and a measurement ID.

[0072] In step S2, the UE 100 performs measurement of a measurement target and monitoring of a monitoring target based on the configuration information of step S1. The measurement target is one of a cell, a frequency, a beam, a reference signal, and a measurement object. The measurement target may be determined according to the measurement object in the measurement configuration. The monitoring target is a cell, a beam, or a reference signal. The UE 100 may perform monitoring based on the failure prediction configuration of step S1.

[0073] In step S3, based on the failure prediction setting in step S1, the UE 100 performs connection failure prediction to predict whether a wireless connection failure will occur in the future using the AI / ML model 101. Here, the AI / ML model 101 outputs a prediction result regarding when a wireless connection failure will occur based on the connection failure prediction as a connection failure prediction result. The prediction result may include a value indicating the probability (likelihood) of a future occurrence of HOF / RLF, i.e., a value indicating prediction accuracy.

[0074] For example, the UE 100 predicts whether HOF / RLF will occur in the future using the AI / ML model 101, using parameters such as time-series measurement results for each cell, location data (measurements) of the UE 100, the movement speed (measurements) of the UE 100, and the frequency (set value) of the cell as inference data. The measurement results may be a set of an ID of a measurement target and its measurement value. The "measurements" may be reference signal received power (RSRP), reference signal radio quality (RSRQ), and / or signal-to-interference-and-noise ratio (SINR), etc.

[0075] The AI / ML model 101 possessed by the UE 100 is assumed to have learned the correlation between these parameters through model learning. For example, the AI / ML model 101 may have learned the causal relationship between data such as time-series wireless quality fluctuations (actual measured values) for each cell, location data of the UE 100 (actual measured values), the moving speed of the UE 100 (actual measured values), and the cell frequency (set value), and the HOF / RLF occurrence history for each cell (and the actual measured values ​​of the wireless quality at that time) through model learning. Note that at least a partially trained AI / ML model 101 may be set to the UE 100 by the gNB 200. For example, the AI / ML model 101 may be transferred from the gNB 200 to the UE 100 when communication between the gNB 200 and the UE 100 starts. Alternatively, the UE 100 may generate the trained AI / ML model 101 by performing model learning in various environments.

[0076] In step S4, the UE 100 transmits a message regarding the result of the connection failure prediction to the gNB 200. The gNB 200 receives the message.

[0077] Thus, according to the embodiment, UE100 transmits to gNB200 a message regarding the result of connection failure prediction using AI / ML model 101. This allows gNB200 to understand the possibility of a wireless connection failure occurring in UE100. Therefore, it becomes possible to perform mobility control (e.g., RRC reconfiguration, etc.) on UE100 that prevents the occurrence of a wireless connection failure.

[0078] The UE 100 that performs such operations includes a control unit 130 that performs connection failure prediction using the AI / ML model 101 to predict whether a wireless connection failure will occur in the future when the UE 100 is in an RRC connected state connected to the gNB 200, and a transmission unit 120 that transmits a message regarding the result of the connection failure prediction to the gNB 200 in response to the prediction that a wireless connection failure will occur in the future (see FIG. 2). Meanwhile, the gNB 200 includes a reception unit 220 that receives a message regarding the result of the connection failure prediction using the AI / ML model 101 from the UE 100 in an RRC connected state connected to the gNB 200, and a control unit 230 that performs mobility control of the UE 100 based on the message. The connection failure prediction is a process of predicting whether a wireless connection failure will occur in the future. The message indicates that a wireless connection failure is predicted to occur in the future. The gNB 200 may further include a transmission unit 210 that transmits a failure prediction setting to the UE 100.

[0079] The failure prediction setting in step S1 may include a setting that specifies a future time range for predicting the occurrence of a wireless connection failure in the connection failure prediction. That is, the gNB 200 may set in the UE 100 how far in advance the future connection failure prediction will be performed.

[0080] The UE 100 (AI / ML model 101) may acquire a value indicating the probability that a wireless connection failure will occur in the future using the AI / ML model 101. The failure prediction setting in step S1 may include a setting specifying a threshold value of the probability that a wireless connection failure must be satisfied in order for the connection failure prediction to consider that a wireless connection failure will occur in the future. That is, the setting may include a threshold value of the HOF / RLF occurrence probability (likelihood).

[0081] The failure prediction setting in step S1 may include a setting for specifying any one of 1) HOF only, 2) RLF only, or 3) both HOF and RLF as the type of failure predicted by the connection failure prediction. Alternatively, the failure prediction setting in step S1 may include a setting for individually specifying any one of 1) HOF, 2) RLF, and 3) beam failure as the type of failure predicted by the connection failure prediction. The failure prediction setting in step S1 may include a setting for specifying a combination of two or more types of 1) HOF, 2) RLF, and 3) beam failure as the type of failure predicted by the connection failure prediction.

[0082] The failure prediction setting in step S1 may include a setting for specifying a target cell for which a wireless connection failure is predicted by the connection failure prediction, i.e., the setting may include information for specifying which cell a HOF / RLF is predicted for.

[0083] The failure prediction setting in step S1 includes a setting for specifying the AI / ML model 101 to be used for connection failure prediction. For example, the setting may include a model ID of the AI / ML model 101 to be used for connection failure prediction.

[0084] The message of step S4 may include information indicating a predicted occurrence timing at which a wireless connection failure is predicted to occur in the future. For example, the UE 100 reports to the gNB 200 information on how far in the future the HOF / RLF will occur.

[0085] The message of step S4 may include information indicating the probability of a wireless connection failure occurring at each of a plurality of future timings, and the information may be the probability of a HOF / RLF occurring at each of the plurality of timings.

[0086] The message of step S4 may include proposal information indicating mobility control for avoiding the occurrence of a radio connection failure. For example, the UE 100 may notify the gNB 200 of proposal information regarding a HOF / RLF avoidance measure.

[0087] The proposal information may include information indicating a cell that is recommended as a serving cell of the UE 100. The information may be information regarding in which cell the UE 100 should be located (or in which handover should be performed).

[0088] In step S2, the UE 100 may measure the reception quality of the serving cell and / or neighboring cell. The message in step S4 may include information indicating the result of the measurement. For example, the UE 100 may report the current quality measurement value (latest measurement value) to the gNB 200 together with the report of the connection failure prediction result.

[0089] The message in step S4 may include the model ID of the AI / ML model 101 used to predict the connection failure.

[0090] Next, an operation sequence according to the embodiment will be described with reference to Fig. 9.

[0091] In step S101, UE100 is in an RRC connected state with gNB200.

[0092] In step S102, the gNB 200 transmits a message including a failure prediction setting to the UE 100. The message may be an RRC reconfiguration message. The UE 100 receives the message (failure prediction setting).

[0093] The failure prediction setting may be time information for predicting a connection failure, for example, information on how far in advance a HOF / RLF is to be predicted (50 ms before, 1 s before, etc.) The failure prediction setting may also be information on how far in the future a HOF / RLF will occur (50 ms after, 1 s after, etc.).

[0094] The failure prediction setting may include at least one of information specifying which (or both) of HOF and RLF to predict, information (such as a cell ID) of a cell that is a target of connection failure prediction, a threshold value for the likelihood (probability) of inference of connection failure prediction, information specifying a model ID of the AI / ML model 101 used for model inference (connection failure prediction), and information on whether to report the model ID of the AI / ML model 101 used for model inference. The failure prediction setting may include information specifying a beam and / or a reference signal that is a target of connection failure prediction.

[0095] In step S103, the UE 100 monitors (including measures) a monitoring target that is a target for predicting a wireless connection failure.

[0096] In step S103, the UE 100 performs a connection failure prediction using model inference in accordance with the failure prediction setting. For example, the UE 100 performs a model inference (connection failure prediction) of the occurrence of HOF / RLF for each cell using data such as time-series wireless quality fluctuations (actual measured values) for each cell, location data of the UE 100 (actual measured values), a moving speed of the UE 100 (actual measured values), and a frequency (set value) of the cell as inference data.

[0097] If the reporting condition for reporting the result of the connection failure prediction to the gNB 200 is not met, the UE 100 returns the process to step S103. On the other hand, if the reporting condition is met, the UE 100 proceeds to step S106. The report may be a periodic report.

[0098] The period may be set by a failure prediction setting from the gNB 200 to the UE 100. The reporting condition may be that a timing determined according to the period has arrived.

[0099] The reporting condition may be that any of the following events has occurred. The type of the event may be set by the gNB 200 to the UE 100 through a failure prediction setting. The UE 100 may trigger the transmission of a single report in response to the occurrence of the event. The UE 100 may trigger the transmission of periodic reports in response to the occurrence of the event.

[0100] An event that connection failure prediction (inference processing) is completed This may be when the AI / ML model 101 outputs the inference result.

[0101] - An event in which the timing obtained by subtracting a set amount of time in advance (or in the future) from the predicted time of HOF / RLF occurrence has arrived: For example, if it is predicted that HOF / RLF will occur in 5 seconds, and the setting is set to predict it 3 seconds in advance, UE100 will report it 3 seconds before this (or 2 seconds after the present).

[0102] - An event in which the likelihood (probability) of a connection failure prediction (model inference) exceeds a set threshold.

[0103] In step S106, the UE 100 transmits a message (report) regarding the result of the connection failure prediction. The gNB 200 receives the message (report). The message may be a MAC CE or an RRC message. The RRC message may be a UE Assistance Information message. The message may include at least one of the following information:

[0104] HOF / RLF type (information on which one occurs): This may be HOF only, RLF only, or both.

[0105] Information on HOF / RLF occurrence timing: This may be information on the timing at which HOF / RLF is predicted to occur (50 ms later, 1 second later, etc.).

[0106] HOF / RLF occurrence probability for each of a plurality of timings: For example, the information may be 50% after 1 second, 80% after 2 seconds, and so on.

[0107] Proposal information regarding HOF / RLF avoidance measures: This may be information such as which cell to handover to (or change of primary secondary cell (PS cell)) and / or information such as which cell the user should be in.

[0108] Radio quality measurement values ​​(actual measurements) of the current serving cell and / or neighboring cells: RSRP, RSRQ, SINR, RSSI, etc.

[0109] Model ID of the model used for inference: For example, the gNB200 may determine the likelihood (accuracy) of the connection failure prediction (model inference) by obtaining model performance information from a model database based on the model ID. When the UE100 simultaneously uses multiple AI / ML models 101 for the target function in the UE-side model, the gNB200 may identify the model by the model ID.

[0110] In step S107, gNB200 performs mobility control of UE100 based on the message (report) of step S106. For example, gNB200 may determine and execute an effective workaround. For example, gNB200 recognizes an HOF / RLF occurrence in the near future, and determines and executes a handover of the primary cell or a change of PS cell while checking the reported current radio quality of each cell before the timing when the HOF / RLF is predicted to occur.

[0111] (6) Other Embodiments In the above-described embodiments, handover has been described as an example of mobility control, but the present invention is not limited to handover and can be applied to any mobility control. For example, the operation according to the above-described embodiment may be applied to setting a handover execution condition in a conditional handover. Alternatively, the operation according to the above-described embodiment may be applied to LTM (L1 / L2 Triggered Mobility), which is cell switching initiated by Layer 1 and / or Layer 2 (L1 / L2). In this case, the above-described measurement report may be read as an L1 measurement report. Alternatively, the present invention may be applied to PSCell change, which switches the primary / secondary cell (PSCell) of the UE 100 initiated by the RRC layer.

[0112] In the above-described embodiment, an example in which signaling related to the AI / ML technology is an RRC message, which is signaling of the RRC layer (i.e., Layer 3), has been mainly described. However, the AI / ML-related signaling may be MAC CE, which is signaling of the MAC layer (i.e., Layer 2), or downlink control information (DCI) and / or uplink control information (UCI), which are signaling of the PHY layer (i.e., L1). The downlink AI / ML-related signaling may be UE-dedicated signaling or broadcast signaling (e.g., SIB (System Information Block)). The AI / ML-related signaling may be signaling in a new layer (e.g., the AI / ML layer) dedicated to artificial intelligence or machine learning.

[0113] The above-described operational flows are not limited to being implemented independently, but can 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. Furthermore, the order of steps in each flow may be changed as appropriate.

[0114] In the above-described embodiments and examples, an example in which the base station is an NR base station (gNB) has been described, but the base station may be an LTE base station (eNB) or a 6G base station. 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 of the IAB node. The UE 100 may also be an MT (Mobile Termination) of the IAB node. That is, the UE 100 may be a terminal function unit (a type of communication module) for the base station to control a relay that relays signals. Such a terminal function unit is referred to as an MT. Examples of MT include, in addition to IAB-MT, NCR (Network Controlled Repeater)-MT and RIS (Reconfigurable Intelligent Surface)-MT.

[0115] 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.

[0116] A program that causes a computer to execute each process performed by the UE 100 or the gNB 200 may be provided. 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 and / or a DVD-ROM. Furthermore, circuits that execute each process performed by the UE 100 or the gNB 200 may be integrated, and at least a portion of the UE 100 or the gNB 200 may be configured as a semiconductor integrated circuit (chip set, SoC: System on a chip).

[0117] The functions performed by UE100 or gNB200 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 / or 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 the hardware and software used to configure the hardware and / or processor.

[0118] As used in this disclosure, the terms "based on" and "depending on / in response to" 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 "depending only on" and "depending at least in part on." The terms "include," "comprise," and variations thereof do not mean including only the listed items, but may mean including only the listed items or may include additional items in addition to the listed items. Additionally, the term "or," as used in this disclosure, is not intended to mean an exclusive or. Furthermore, any reference to elements using designations 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, a 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, where articles are added by translation, such as a, an, and the in English, these articles shall include the plural unless the context clearly indicates otherwise.

[0119] 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.

[0120] This application claims priority from Japanese Patent Application No. 2024-060852 (filed April 4, 2024), the entire contents of which are incorporated herein by reference.

[0121] (7) Supplementary Notes The following are additional notes regarding the features of the above-described embodiment.

[0122] Supplementary Note 1: A communication method executed by a user equipment in a mobile communication system, the communication method comprising: performing connection failure prediction using an artificial intelligence or machine learning (AI / ML) model to predict whether a radio connection failure will occur in the future, in a radio resource control (RRC) connected state in which the user equipment is connected to a network node; and transmitting a message regarding the result of the connection failure prediction to the network node.

[0123] Supplementary Note 2: The communication method according to Supplementary Note 1, wherein the radio connection failure is a handover failure (HOF) or a radio link failure (RLF).

[0124] Supplementary Note 3: The communication method according to Supplementary Note 1 or 2, further comprising receiving configuration information for configuring the connection failure prediction from the network node, wherein the user equipment performs the connection failure prediction based on the configuration information.

[0125] Supplementary Note 4: The communication method according to Supplementary Note 3, wherein the setting information includes a setting that specifies a future time range for which the connection failure prediction is to predict the occurrence of the wireless connection failure.

[0126] Supplementary Note 5: The communication method according to Supplementary Note 3 or 4, wherein the user device obtains a value indicating the probability of the wireless connection failure occurring in the future using the AI / ML model, and the setting information includes a setting specifying a threshold value of the probability that must be met in order for the connection failure prediction to consider the wireless connection failure to occur in the future.

[0127] Supplementary Note 6: The communication method according to any one of Supplementary Notes 3 to 5, wherein the setting information includes a setting that specifies, as a type of failure predicted by the connection failure prediction, one of HOF only, RLF only, or both HOF and RLF.

[0128] Supplementary Note 7: The communication method according to any one of Supplementary Notes 3 to 6, wherein the setting information includes a setting for specifying a cell for which the occurrence of the wireless connection failure is predicted by the connection failure prediction.

[0129] Supplementary Note 8: The communication method according to any one of Supplementary Notes 3 to 7, wherein the setting information includes a setting that specifies the AI / ML model to be used for the connection failure prediction.

[0130] Supplementary Note 9: The communication method according to any one of Supplementary Notes 1 to 8, wherein the message includes information indicating a predicted timing at which the wireless connection failure is predicted to occur in the future.

[0131] Supplementary Note 10: The communication method according to any one of Supplementary Notes 1 to 9, wherein the message includes information indicating the probability of occurrence of the wireless connection failure at each of a plurality of future timings.

[0132] Supplementary Note 11: The communication method according to any one of Supplementary Notes 1 to 10, wherein the message includes proposal information indicating mobility control for avoiding the occurrence of the wireless connection failure.

[0133] Supplementary Note 12: The communication method according to Supplementary Note 11, wherein the proposal information includes information indicating a cell that is recommended as a serving cell for the user equipment.

[0134] Supplementary Note 13: The communication method according to any one of Supplementary Notes 1 to 12, further comprising the user equipment measuring reception qualities of a serving cell and / or a neighboring cell, and the message includes information indicating a result of the measurement.

[0135] Supplementary Note 14: The communication method according to any one of Supplementary Notes 1 to 13, wherein the message includes a model ID of the AI / ML model used for the connection failure prediction.

[0136] Supplementary Note 15: A user equipment for use in a mobile communication system, comprising: a control unit that performs connection failure prediction using an artificial intelligence or machine learning (AI / ML) model to predict whether a wireless connection failure will occur in the future, in a Radio Resource Control (RRC) Connected state in which the user equipment is connected to a network node; and a transmission unit that transmits a message regarding a result of the connection failure prediction to the network node.

[0137] Supplementary Note 16: A network node used in a mobile communication system, comprising: a receiving unit that receives, from a user equipment in a radio resource control (RRC) connected state connected to the network node, a message regarding a result of a connection failure prediction using an artificial intelligence or machine learning (AI / ML) model; and a control unit that performs mobility control of the user equipment based on said message, wherein said connection failure prediction is a process of predicting whether a wireless connection failure will occur in the future.

[0138] 1: Mobile communication system 5: Network 10: RAN (NG-RAN) 11: L1 filter 12: Beam integration / selection unit 13: L3 filter 14: Evaluation unit 15: L3 beam filter 16: Beam selection unit 20: CN (5GC) 100: UE 101: AI / ML model 110: Receiving unit 111: Receiver (RF chain) 120: Transmitting unit 130: Control unit 140: Wireless communication unit 200: gNB 210: Transmitting unit 220: Receiving unit 230: Control unit 240: Network communication unit 241: Transmitting unit 242: Receiving unit 250: Wireless communication unit A1: Data collection unit A2: Model learning unit A3: Model inference unit A4 : Data processing section

Claims

1. A communication method executed by a user equipment in a mobile communication system, the communication method comprising: performing connection failure prediction using an artificial intelligence or machine learning (AI / ML) model to predict whether a radio connection failure will occur in the future, in a Radio Resource Control (RRC) Connected state in which the user equipment is connected to a network node; and transmitting a message regarding the result of the connection failure prediction to the network node.

2. The communication method according to claim 1, wherein the radio connection failure is a handover failure (HOF) or a radio link failure (RLF).

3. The communication method according to claim 1 or 2, further comprising receiving configuration information for configuring the connection failure prediction from the network node, wherein the user equipment performs the connection failure prediction based on the configuration information.

4. The communication method according to claim 3, wherein the setting information includes a setting that specifies a future time range for which the connection failure prediction is to predict the occurrence of the wireless connection failure.

5. The communication method according to claim 3, wherein the user device obtains a value indicating the probability that the wireless connection failure will occur in the future using the AI / ML model, and the setting information includes a setting that specifies a threshold value of the probability that must be met in order for the connection failure prediction to consider the wireless connection failure to occur in the future.

6. The communication method according to claim 3, wherein the setting information includes a setting that specifies either HOF only, RLF only, or both HOF and RLF as the type of failure predicted by the connection failure prediction.

7. The communication method according to claim 3, wherein the setting information includes a setting for specifying a cell for which the occurrence of the wireless connection failure is predicted by the connection failure prediction.

8. The communication method according to claim 3, wherein the setting information includes a setting that specifies the AI / ML model to be used for the connection failure prediction.

9. The communication method according to claim 1 or 2, wherein the message includes information indicating a predicted timing at which the wireless connection failure is predicted to occur in the future.

10. The communication method according to claim 1 or 2, wherein the message includes information indicating the probability of occurrence of the wireless connection failure at each of a plurality of future timings.

11. The communication method according to claim 1 or 2, wherein the message includes proposal information indicating mobility control for avoiding the occurrence of the wireless connection failure.

12. The communication method according to claim 11, wherein the proposal information includes information indicating a cell that is recommended as a serving cell for the user equipment.

13. The communication method according to claim 1 or 2, further comprising the user equipment measuring reception quality of a serving cell and / or a neighboring cell, and the message includes information indicating a result of the measurement.

14. The communication method according to claim 1 or 2, wherein the message includes a model ID of the AI / ML model used for the connection failure prediction.

15. A user equipment for use in a mobile communication system, comprising: a control unit that performs connection failure prediction using an artificial intelligence or machine learning (AI / ML) model to predict whether a wireless connection failure will occur in the future when the user equipment is in a radio resource control (RRC) connected state in which the user equipment is connected to a network node; and a transmission unit that transmits a message regarding the result of the connection failure prediction to the network node.

16. A network node used in a mobile communication system, comprising: a receiving unit that receives a message regarding the result of a connection failure prediction using an artificial intelligence or machine learning (AI / ML) model from a user equipment in a radio resource control (RRC) connected state connected to the network node; and a control unit that performs mobility control for the user equipment based on the message, wherein the connection failure prediction is a process of predicting whether a wireless connection failure will occur in the future.

Images