Communication method, user equipment, and network node

Abstract

This communication method executed by user equipment in a mobile communication system includes a step for transmitting a notification related to model inference to a network node on the basis of a fact that the user equipment has evaluated a possibility of cell switching from a source cell to a candidate cell and / or an execution timing of the cell switching by using the model inference by means of an artificial intelligence or machine learning (AI / ML) model.

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] 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 equipment in a mobile communication system, the method comprising: based on an evaluation by the user equipment of a possibility of a cell switch from a source cell to a candidate cell and / or a timing of performing the cell switch using model inference based on an artificial intelligence or machine learning (AI / ML) model, transmitting a notification regarding the model inference to a network node.

[0005] A user equipment according to a second aspect is a user equipment for use in a mobile communication system, the user equipment comprising: a transmitter configured to transmit, to a network node, a notification regarding model inference based on an evaluation by the user equipment of a possibility of a cell switch from a source cell to a candidate cell and / or a timing for performing the cell switch using model inference based on an artificial intelligence or machine learning (AI / ML) model.

[0006] A network node according to a third aspect is a network node for use in a mobile communication system, the network node comprising: a receiving unit configured to receive, from a user equipment, a notification regarding model inference based on the user equipment's evaluation of a possibility of and / or timing of a cell switch from a source cell to a candidate cell using model inference based on an artificial intelligence or machine learning (AI / ML) model.

[0007] 1 is a diagram illustrating a configuration of a mobile communication system according to an embodiment. FIG. 1 is a diagram illustrating a configuration of a UE (user equipment) according to an embodiment. FIG. 2 is a diagram illustrating a configuration of a gNB (network node) according to an embodiment. FIG. 3 is a diagram illustrating a protocol stack configuration of a radio interface of a user plane that handles data. FIG. 4 is a diagram illustrating a protocol stack configuration of a radio interface of a control plane that handles signaling (control signals). FIG. 5 is a diagram illustrating a functional block configuration of AI / ML technology in a mobile communication system according to an embodiment. FIG. 6 is a diagram for explaining an example of an operation scenario of a mobile communication system according to an embodiment. FIG. 7 is a diagram illustrating a first basic operation of a UE in a mobile communication system according to an embodiment. FIG. 8 is a diagram illustrating a second basic operation of a UE in a mobile communication system according to an embodiment. FIG. 9 is a diagram illustrating a first operation pattern of a mobile communication system according to an embodiment. FIG. 10 is a diagram illustrating a second operation pattern of a mobile communication system according to an embodiment. FIG. 11 is a diagram illustrating an example of a third operation pattern of a mobile communication system according to an embodiment. FIG. 12 is a diagram illustrating another example of the third operation pattern of a mobile communication system according to an embodiment. FIG. 13 is a diagram illustrating an example of an operation of a UE when handover fails in a fourth operation pattern of a mobile communication system according to an embodiment. FIG. 14 is a diagram illustrating an example of an operation of a UE when handover is successful in the fourth operation pattern of a mobile communication system according to an embodiment. FIG. 15 is a diagram illustrating an example of a log transmission operation of a UE in the fourth operation pattern of a mobile communication system according to an embodiment.

[0008] One possible use case for AI / ML technology is mobility control of user equipment. Specifically, it is conceivable to apply AI / ML technology to control cell switching from a source cell to a target cell. However, a specific mechanism for applying AI / ML technology to mobility control of user equipment has not yet been established, making it difficult to utilize AI / ML technology in mobile communication systems.

[0009] The present disclosure provides an enablement for utilizing 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 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.

[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. The UE 100 performs wireless communication with the network 5.

[0013] 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), 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).

[0014] 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").

[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 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.

[0018] 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.

[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. 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.

[0021] 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.

[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. 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.

[0025] 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.

[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 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.

[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] 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.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] The PDCP layer performs header compression / decompression, encryption / decryption, and the like.

[0034] 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.

[0035] 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).

[0036] 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.

[0037] 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.

[0038] 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).

[0039] (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).

[0040] 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.

[0041] 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.

[0042] 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.

[0043] 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.

[0044] The data processing unit A4 receives the inference result data and performs processing that utilizes the inference result data.

[0045] (3) Operation of the Mobile Communication System Next, an operation of the mobile communication system 1 according to the embodiment will be described. In the embodiment, the AI / ML technology is applied to mobility control of the UE 100. Specifically, in the embodiment, the AI / ML technology is applied to control cell switching from a source cell to a target cell, specifically, switching of the serving cell of the UE 100. As an example, in the embodiment, a handover in which the primary cell (PCell) of the UE 100 is switched under the initiative of the RRC layer when the UE 100 is in an RRC connected state will be mainly described.

[0046] Cell switching includes cell switching when UE 100 is in an RRC connected state and cell switching when UE 100 is in an RRC idle state or an RRC inactive state. When UE 100 is in an RRC connected state, control initiated by network 5 is applied to cell switching. On the other hand, when UE 100 is in an RRC idle state or an RRC inactive state, control initiated by UE 100 is applied to cell switching. Cell switching when UE 100 is in an RRC idle state or an RRC inactive state is called cell reselection. In the embodiment, an example in which AI / ML technology is applied to handover will be mainly described, but AI / ML technology may also be applied to cell reselection. That is, "handover" described below may be read as "cell reselection".

[0047] In addition to handover, cell switching when UE 100 is in the RRC connected state includes PSCell change, which switches the primary / secondary cell (PSCell) of UE 100 at the initiative of the RRC layer, and LTM (L1 / L2 Triggered Mobility), which is cell switching at the initiative of Layer 1 and / or Layer 2 (L1 / L2). In the embodiment, an example of applying AI / ML technology to handover will be mainly described, but AI / ML technology may also be applied to LTM or PSCell change. That is, "handover" described below may be read as "LTM" or "PSCell change." In LTM, for example, gNB200 pre-configures one or more candidate cells in UE100 using an RRC message, UE100 reports the cell measurement results to gNB200 via L1, gNB200 instructs UE100 to switch to the target cell using a MAC CE (Control Element), and UE100 accesses the target cell in accordance with the instruction.

[0048] Handover includes a general handover (also referred to as "HO") and a conditional handover (CHO: Conditional Handover). In a general handover, the UE 100 transmits a measurement report message, which is a type of RRC message, to the gNB 200, the gNB 200 determines a target cell based on the Measurement Report message, the gNB 200 instructs the UE 100 to handover to the target cell by an RRC message, and the UE 100 accesses the target cell in accordance with the instruction. In contrast, in conditional handover, the gNB 200 pre-sets one or more candidate cells together with handover execution conditions to the UE 100 by an RRC message, and the UE 100 evaluates whether the handover execution conditions to any of the candidate cells are met. The UE 100 determines the candidate cell for which the handover execution conditions are met as the target cell and accesses the target cell. Note that the cell that the UE 100 has determined to access is referred to as the target cell, and a cell that is a candidate for the target cell is referred to as a candidate cell. However, in the following, the terms "target cell" and "candidate cell" may be used as synonyms.

[0049] Also, from the viewpoint of the network 5, handovers include intra-gNB (intra-CU) handovers in which the source cell and the target cell belong to the same gNB (CU), and inter-gNB (inter-CU) handovers in which the source cell and the target cell belong to different gNBs (CU). In the embodiment, inter-gNB handovers are mainly assumed, but intra-gNB handovers may also be assumed.

[0050] Furthermore, in the following embodiments, an example will be mainly 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 MAC 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., L1). The downlink AI / ML-related signaling may be UE-dedicated signaling. The downlink AI / ML-related signaling may be broadcast signaling (e.g., SIB (System Information Block)). AI / ML-related signaling may be signaling in a new layer (e.g., an AI / ML layer) specialized for artificial intelligence or machine learning.

[0051] (3.1) Operation Scenario of Mobile Communication System FIG. 7 is a diagram for explaining an example of an operation scenario of the mobile communication system 1 according to the embodiment.

[0052] In the illustrated example, UE100 is in an RRC connected state with cell a managed by gNB200a as the serving cell. That is, UE100 has established an RRC connection with gNB200a and is performing wireless communication with gNB200a. Cell b and cell c are neighboring cells of cell a. Cell b is managed by gNB200b, and cell c is managed by gNB200c. gNB200a is communicably connected to gNB200b and gNB200c via an inter-node interface (Xn interface).

[0053] As the UE 100 moves, it is necessary to perform handover of the UE 100 from the cell a to a neighboring cell. In the illustrated example, the neighboring cells are cell b and cell c, and cell b and cell c are candidate cells for handover.

[0054] In a typical handover, UE100 sends a Measurement Report message, which is a type of RRC message, to gNB200, and gNB200 determines one of cell b and cell c as the target cell based on the Measurement Report message, and gNB200 instructs UE100 to perform a handover to the target cell via an RRC message, and UE100 accesses the target cell in accordance with the instruction.

[0055] In the case of conditional handover, gNB200 pre-configures one or more candidate cells (cell b and cell c) along with handover execution conditions to UE100 via an RRC message, UE100 evaluates whether the handover execution conditions to any of the candidate cells are met, and UE100 determines the candidate cell for which the handover execution conditions are met as the target cell and accesses the target cell.

[0056] Such a handover may cause the following problems, for example.

[0057] Too early handover: HO may be performed too early, causing the UE 100 to fail to access the target cell.

[0058] Too late handover: HO is performed too late, which may result in a radio link failure (RLF) between the UE 100 and the source cell.

[0059] Handover to wrong cell: A ping-pong phenomenon may occur in which HO of the UE 100 is performed to a cell different from the cell to which HO should originally be performed, and HO must be immediately performed again.

[0060] In an embodiment, the AI / ML technology is applied to the handover of the UE 100, thereby making it possible to solve such problems. Specifically, an AI / ML model for handover is deployed in the UE 100, and the UE 100 determines a candidate cell (target cell) and / or a timing for executing handover to the target cell by model inference using the AI / ML model (trained model). This makes it possible to optimize the determination of the target cell and / or the timing for executing handover, thereby solving the handover problems described above.

[0061] In the embodiment, the UE 100 uses at least one of the following as inference data to be input to the AI / ML model: wireless quality (measurement value) of each cell, UE position (positioning position), UE movement speed, frequency of each cell, UE traffic situation, and application information currently being executed by the UE. The inference data may include a cell ID of each cell.

[0062] Here, the radio quality may be at least one of a reference signal received power (RSRP), a reference signal radio quality (RSRQ), a signal-to-interference-and-noise ratio (SINR), a bit error rate (BER), a block error rate (BLER), and an analog-to-digital converter output waveform. The radio quality may be time-series data including a plurality of measurement values ​​over a certain period of time. The UE location is geographical location information obtained by the UE 100 using a Global Navigation Satellite System (GNSS) receiver and / or a positioning reference signal, and may be a combination of latitude and longitude. The UE location may be a combination of latitude, longitude, and altitude. The UE movement speed may be UE acceleration. The UE movement speed may be a UE movement state (stationary state, low-speed movement state, high-speed movement state, etc.). The frequency of each cell may be a band to which the cell belongs. The frequency may be a frequency range (FR). The UE traffic situation may be the amount or pattern of traffic occurring in the UE 100. The information about an application running on the UE may be information about a required quality of service (QoS).

[0063] The inference data input to the AI / ML model may include at least one of the bandwidth of each cell, the cell size (or transmit power) of each cell, and radio parameters of each cell. These inference data may be obtained from system information (broadcast signaling) of each cell. The radio parameters may be, for example, random access channel (RACH) parameters, cell reselection parameters (e.g., frequency priority and / or cell minimum quality (S-criterion)), or other radio parameters.

[0064] Here, by using the bandwidth as inference data, it is possible to estimate the expected throughput (service quality). Therefore, mobility control, such as preferentially selecting a candidate cell having a system bandwidth equivalent to that of the current serving cell, becomes easier. By using the cell size (cell transmission power) as inference data, it is possible to prioritize large cells over small cells to increase the HO success rate, or to prioritize small cells (when moving at low speeds) or large cells (when moving at high speeds) depending on the UE movement speed. The cell size may be estimated, for example, from the uplink maximum transmission power setting. By using the RACH parameters as inference data, particularly when performing CBRA (Contention-based Random Access), the larger (wider) the RACH resource, the fewer PRACH (Physical Random Access Channel) collisions there are, and therefore the HO success rate can be increased. By using cell reselection parameters as inference data, it is possible to deliberately select a cell that is likely to have less traffic (i.e., a cell with low priority) based on frequency priority, or to estimate the cell size from the S-criterion.

[0065] In an embodiment, the inference result data output by the AI / ML model is information indicating the possibility of cell switching to each candidate cell and / or information indicating the timing of cell switching. The information indicating the possibility of cell switching may be a probability value of cell switching to each candidate cell. The information indicating the timing of cell switching may be a relative value indicating how many ms after a handover (access to the target cell) should be performed from the current time point. The information may also be an absolute value indicating the timing at which handover (access to the target cell) should be performed.

[0066] Such an AI / ML model may be held in advance by the UE 100 before model inference. Such an AI / ML model may be provided to the UE 100 by the gNB 200 before model inference.

[0067] (3.2) Overview of Operation of Mobile Communication System Next, an overview of operation of the mobile communication system 1 according to the embodiment will be described.

[0068] (3.2.1) First Basic Operation FIG. 8 is a diagram showing a first basic operation of the UE 100 in the mobile communication system 1 according to the embodiment.

[0069] In step S11, UE100 receives a predetermined message from the source cell (gNB200) including model setting information that sets (specifies) the AI / ML model to be used for cell switching (in an embodiment, handover) from the source cell to the target cell.

[0070] In step S12, the UE 100 infers the possibility of handover and / or the timing of handover execution using the AI / ML model set in step S11. Note that, in the following, the term "infer" may be used as a term meaning "estimate," "evaluate," "determine," or "decide," but these terms may be interchangeable.

[0071] According to this first basic operation, AI / ML technology is applied to the handover of UE 100, making it possible to solve the above-mentioned handover problems. Specifically, an AI / ML model for handover is set in UE 100, and UE 100 can use the AI / ML model to determine the candidate cell (target cell) and / or the timing of handover to the target cell by model inference. This makes it possible to optimize the target cell determination and / or handover execution timing. In addition, since gNB 200 sets the AI / ML model for handover in UE 100, the principle of handover, which is network 5-led control, can be maintained.

[0072] The UE 100 that performs such an operation has a receiver 110 that receives a predetermined message including model setting information for setting the AI / ML model to be used for handover from the source cell, and a control unit 130 that uses the set AI / ML model to infer the possibility of handover and / or the timing of handover execution. Meanwhile, the gNB 200 has a transmitter 210 that transmits to the UE 100 a predetermined message including model setting information for setting the AI / ML model to be used for handover.

[0073] In the first basic operation, the model setting information may include identification information (also referred to as "model identification information") for identifying an AI / ML model for handover. In this case, the UE 100 may store the AI / ML model for handover in advance. The model identification information may be a function ID indicating a function of the AI / ML model. The model identification information may be a model ID that uniquely identifies the AI / ML model.

[0074] The AI / ML model for inferring the possibility of handover and the AI / ML model for inferring the timing of handover execution may be the same AI / ML model. Alternatively, the AI / ML models may be different from each other. In the former case, the function ID may be defined as a function ID called "inferring the possibility of handover" and a function ID called "inferring the timing of handover execution." In the latter case, the function ID may be defined as "handover control."

[0075] In the first basic operation, the model setting information may include an AI / ML model for handover. That is, the gNB200 may provide the AI / ML model for handover itself to the UE100. In this case, the UE100 does not need to store the AI / ML model for handover in advance. The AI / ML model provided by the gNB200 may be assigned model identification information. Regarding the AI / ML models provided by the gNB200, the AI / ML model for inferring the possibility of handover and the AI / ML model for inferring the timing of handover execution may be the same AI / ML model. The AI / ML models may also be different AI / ML models.

[0076] In the first basic operation, the predetermined message including the model setting information may be an RRC Reconfiguration message. The RRC Reconfiguration message may be any of 1) an RRC Reconfiguration message instructing execution of handover, 2) an RRC Reconfiguration message performing measurement configuration for handover, and 3) an RRC Reconfiguration message configuring conditional handover in the UE 100.

[0077] The RRC Reconfiguration message for setting a conditional handover in the UE 100 includes conditional reconfiguration information for setting the conditional handover. The conditional reconfiguration information may include model setting information.

[0078] In the first basic operation, the UE 100 may receive an instruction message (handover command) from the source cell (gNB 200 that manages the source cell) instructing the execution of handover. The UE 100 may receive a predetermined message including model setting information from the source cell before receiving the instruction message from the source cell. Such a predetermined message may be an RRC Reconfiguration message including measurement setting information for configuring measurements for handover and model setting information.

[0079] (3.2.2) Second Basic Operation Fig. 9 is a diagram showing a second basic operation of the UE 100 in the mobile communication system 1 according to the embodiment. The second basic operation may be performed in combination with the first basic operation.

[0080] In step S21, the UE 100 evaluates the possibility of handover and / or the timing of handover execution using model inference based on the AI / ML model.

[0081] In step S22, UE100 transmits a notification (report) regarding the model inference to gNB200 based on the model inference in step S21.

[0082] According to this second basic operation, AI / ML technology can be applied to the handover of UE100, thereby solving the above-mentioned handover problems. Specifically, by transmitting a notification regarding model inference for evaluating (inferring) the possibility of handover and / or the timing of handover from UE100 to gNB200, gNB200 can grasp the status of model inference in UE100. As a result, gNB200 (network 5) can prepare for handover of UE100 and perform autonomous optimization in network 5.

[0083] The UE 100 that performs such operations has a transmitter 120 that transmits a notification regarding the model inference to the gNB 200 based on the UE 100's evaluation of the possibility of handover and / or the timing of handover execution using model inference by the AI / ML model. On the other hand, the gNB 200 has a receiver 220 that receives a notification regarding the model inference from the UE 100 based on the UE 100's evaluation of the possibility of handover and / or the timing of handover execution using model inference by the AI / ML model.

[0084] In the second basic operation, the notification (report) of step S22 may include information indicating the inference result of the model inference of step S21 and identification information of the candidate cell (e.g., a cell ID). The notification (report) of step S22 may include at least one of model identification information (model ID and / or function ID), information indicating the possibility of cell switching in the model inference result data, and information indicating the switching timing in the model inference result data. The notification (report) of step S22 may include radio quality information and / or UE location information of the serving cell and the candidate cell. In step S22, the UE100 may transmit the notification to the gNB200 that manages the source cell. This allows the gNB200 that manages the source cell to understand the possibility of handover to the candidate cell and / or the timing of execution of handover, and to appropriately prepare for handover of the UE100.

[0085] In the second basic operation, after attempting handover (access to the target cell), the UE 100 may store log information regarding whether the handover was successful. The log information is failure log information indicating that the handover failed, or success log information indicating that the handover was successful. The log information may include model inference information regarding whether model inference was applied to the handover. In step S22, the UE 100 may transmit a notification including the log information to the gNB 200. This allows the gNB 200 (network 5) to perform autonomous optimization in the network 5 (for example, optimization of an AI / ML model to be provided to the UE 100 in the future) using the log information.

[0086] Here, the model inference information may include identification information (function ID or model ID) for identifying the AI / ML model used in the model inference. The model inference information may include information indicating that model inference has been applied to the handover. The model inference information may include information indicating a result of the model inference.

[0087] (3.3) Specific Examples of Operation of Mobile Communication System Next, first to fourth operation patterns will be described as specific examples of operation of the mobile communication system 1 according to the embodiment.

[0088] (3.3.1) First Operation Pattern of Mobile Communication System The first operation pattern is an operation pattern in which AI / ML technology is applied to a general handover that is not a conditional handover. In the first operation pattern, the timing at which the UE 100 that has received the handover command accesses the target cell (the timing at which the handover is executed) is optimized by model inference.

[0089] In the first operation pattern, UE100 receives a predetermined message including model setting information from the source cell (gNB200) before receiving an instruction message (handover command) from the source cell instructing the execution of handover. That is, gNB200 (source cell) sets the AI ​​ / ML model for handover to UE100 before sending the handover command. As a result, UE100 can start model inference for evaluating and determining the execution timing of handover before receiving the handover command. Therefore, UE100 can complete model inference by the time of receiving the handover command and adjust the timing to start accessing the target cell.

[0090] In the first operation pattern, the predetermined message including the model setting information may be an RRC Reconfiguration message that performs measurement setting for handover. The RRC Reconfiguration message may include measurement setting information and model setting information. That is, the AI / ML model for adjusting the execution timing of handover may be configured in the UE 100 simultaneously with the measurement setting in the RRC Reconfiguration message. This allows the AI / ML model for adjusting the execution timing of handover to be efficiently configured in the UE 100 at an appropriate timing.

[0091] In the first operation pattern, the UE 100 may prepare to start an inference process (model inference) using an AI / ML model based on the model setting information in response to receiving a predetermined message including the model setting information. After receiving the predetermined message, the UE 100 may start model inference in response to a first condition related to wireless quality being satisfied. That is, the AI / ML model for adjusting the execution timing of handover may be deployed in the UE 100 at the time of its configuration and activated (executed) when a certain condition (first condition) is satisfied. This makes it possible to suppress an increase in the processing load required for model inference compared to starting model inference immediately upon receiving the predetermined message.

[0092] Here, the first condition may be a condition related to the wireless quality of the neighboring cell (candidate cell) becoming relatively higher than the wireless quality of the serving cell (source cell). For example, the first condition may be any one of the following: the wireless quality of the serving cell is equal to or lower than a threshold, the wireless quality of the neighboring cell is equal to or higher than a threshold, or the difference between the wireless qualities of the serving cell and the neighboring cell (+offset) is equal to or lower than a threshold.

[0093] After starting the model inference, the UE 100 may deactivate (stop) the model inference in response to a second condition related to radio quality being satisfied. The second condition may be a condition related to the radio quality of a neighboring cell (candidate cell) becoming relatively low compared to the radio quality of a serving cell (source cell). For example, the second condition may be any of the following: the radio quality of the serving cell exceeds a threshold, the radio quality of the neighboring cell becomes lower than a threshold, or a difference between the radio qualities of the serving cell and the neighboring cell (+offset) exceeds a threshold.

[0094] The first condition and / or the second condition may be set by the gNB200 to the UE100 as part of the model setting information. For example, the gNB200 may set a threshold value used to determine the first condition and / or the second condition to the UE100 in an RRC Reconfiguration message.

[0095] FIG. 10 is a diagram showing a first operation pattern of the mobile communication system 1 according to the embodiment.

[0096] In step S101, UE100 is in an RRC connected state with cell a managed by gNB200a as the serving cell.

[0097] In step S102, UE100 may transmit to cell a (gNB200a) a model notification including identification information (function ID or model ID) of its AI / ML model. UE100 may transmit to cell a (gNB200a) a UE Capability Information message, which is a type of RRC message and indicates the capabilities of UE100, including the model notification. The model notification may be registered and stored in gNB200 (network 5) as part of the UE context.

[0098] In step S103, the gNB 200a transmits an RRC Reconfiguration message including model setting information for optimizing handover execution timing to the UE 100. The UE 100 receives the RRC Reconfiguration message. After receiving the RRC Reconfiguration message, the UE 100 may transmit an RRC Reconfiguration Complete message to the gNB 200a.

[0099] Here, the model setting information includes at least one of the following information 1) to 4).

[0100] 1) Identification information of the AI / ML model (model ID or function ID): The model ID may be an identifier that uniquely identifies an AI / ML model for adjusting the execution timing of handover. The function ID may be, for example, an identifier that indicates a function of adjusting (inferring) the execution timing of handover. In addition, if the UE100 does not have the AI / ML model specified by the gNB200a, the UE100 may send a model provision request to the gNB200a. The model provision request may include identification information (model ID or function ID) of the AI / ML model requested to be provided. The gNB200a may respond to the request and provide the AI / ML model to the UE100.

[0101] 2) AI / ML model: gNB200 may provide UE100 with the AI / ML model itself for optimizing handover execution timing.

[0102] 3) Condition setting information for setting a condition for activating (first condition) / deactivating (second condition) model inference using an AI / ML model: The condition setting information may be information equivalent to the event trigger setting of a Measurement Report message. For example, the condition setting information may include information indicating the type of event that activates the AI / ML model and a threshold that defines the event. The event type may be, for example, Event A1 (Serving becomes better than a threshold), Event A2 (Serving becomes worse than a threshold), or Event A3 (Neighborhood becomes the amount of offset better than PCell / PSCell).

[0103] 4) TTT (Time-to-trigger) setting information: TTT indicates the time from when a set event is satisfied until when the AI / ML model is activated.

[0104] Furthermore, the RRC Reconfiguration message in step S103 may include measurement configuration (Measurement Configuration). That is, the configuration of the AI / ML model (model inference) and the measurement configuration may be performed simultaneously. The configuration of the AI / ML model (model inference) may be configured as part of the measurement configuration. In this case, in the measurement configuration, an AI / ML model may be specified (e.g., a model ID may be configured) for each report configuration (event trigger setting of the Measurement Report message). Furthermore, the activation of model inference and the transmission of the Measurement Report message may be triggered by the same event trigger setting. In this case, when a trigger condition for transmitting a Measurement Report message is satisfied, the UE 100 triggers transmission of a Measurement Report message and also triggers activation of model inference.

[0105] In step S104, the UE 100 may deploy the AI / ML model according to the model configuration information in step S103. Specifically, the UE 100 may deploy the AI / ML model in its AI processor and prepare for execution of the AI / ML model.

[0106] In step S105, the UE 100 detects that a first condition for activating the configured AI / ML model is satisfied. The UE 100 also detects that a transmission trigger condition (report trigger condition) for a Measurement Report message is satisfied. If the report trigger condition and the first condition are common, the UE 100 may detect that the common condition is satisfied.

[0107] In step S106, the UE 100 transmits a Measurement Report message to the cell a (gNB 200a). The Measurement Report message includes the measurement results of the radio quality of each cell.

[0108] In step S107, UE 100 activates the set AI / ML model and starts evaluating (estimating) the optimal timing to perform handover using model inference by the AI / ML model. Note that step S107 may be performed simultaneously with step S106. UE 100 evaluates the execution timing (optimal timing) of handover for each candidate cell (e.g., cell b and cell c) using the activated AI / ML model. Here, UE 100 may evaluate (estimate) a cell with a possibility of handover using the activated AI / ML model and identify the cell with a possibility of handover as a candidate cell.

[0109] On the other hand, in step S108, the gNB 200a determines a target cell for handover of the UE 100 based on the Measurement Report message of step S106. Here, it is assumed that cell b is determined as the target cell. The gNB 200a transmits an HO Request message requesting handover of the UE 100 to the gNB 200b that manages cell b.

[0110] In step S109, in response to receiving the HO Request message, the gNB 200b transmits an HO Request Acknowledge message to the gNB 200a. The HO Request Acknowledge message includes setting information (RRC setting information) necessary for the UE 100 to access the target cell (cell b).

[0111] In step S110, in response to receiving the HO Request Acknowledge message, the gNB 200a transmits an RRC Reconfiguration message including the RRC setting information in the HO Request Acknowledge message to the UE 100 as an HO command. The UE 100 receives the HO command. Note that since the gNB 200 sets handover timing optimization by model inference to the UE 100, it is desirable that the HO command transmission timing be slightly earlier than the conventional handover command transmission timing. This makes it easier to prevent too late handover by model inference.

[0112] In step S111, the UE 100 starts access (connection processing) to cell b, which is the target cell, at the optimal timing derived by HO timing inference using the AI / ML model. The UE 100 may start a random access procedure for cell b at the optimal timing and transmit a random access preamble to cell b. Alternatively, if the random access procedure is omitted, the UE 100 may transmit an RRC Reconfiguration Complete message to cell b at the optimal timing. When such connection processing is completed, the UE 100 continues communication with cell b as a new serving cell.

[0113] (3.3.2) Second Operation Pattern of Mobile Communication System The second operation pattern is an operation pattern in which the AI / ML technique is applied to conditional handover.

[0114] In the second operation pattern, the UE 100 uses model inference using the AI / ML model to evaluate whether the handover execution conditions to the candidate cell are met (trigger evaluation). The gNB 200 configures (specifies) the AI / ML as part of the conditional handover configuration. Specifically, the gNB 200 transmits to the UE 100 model configuration information for configuring (specifying) the AI / ML model in an RRC Reconfiguration message that configures the UE 100 for conditional handover.

[0115] FIG. 11 is a diagram showing a second operation pattern of the mobile communication system 1 according to the embodiment.

[0116] In step S201, UE100 is in an RRC connected state with cell a managed by gNB200a as the serving cell.

[0117] In step S202, UE100 may transmit to cell a (gNB200a) a model notification including identification information (function ID or model ID) of its AI / ML model. UE100 may transmit to cell a (gNB200a) a UE Capability Information message, which is a type of RRC message and indicates the capabilities of UE100, including the model notification. The model notification may be registered and stored in gNB200 (network 5) as part of the UE context.

[0118] In step S203, the gNB 200a may transmit an RRC Reconfiguration message including measurement configuration information to the UE 100. The UE 100 receives the RRC Reconfiguration message. After receiving the RRC Reconfiguration message, the UE 100 may transmit an RRC Reconfiguration Complete message to the gNB 200a.

[0119] In step S204, the UE 100 may transmit a Measurement Report message to the gNB 200a in accordance with the measurement configuration in step S203. The gNB 200 receives the Measurement Report message.

[0120] In step S205, gNB200a determines cell b and cell c as candidate cells and sends a HO Request message requesting conditional handover of UE100 to gNB200b, which manages cell b.

[0121] In step S206, gNB200a sends a HO Request message requesting a conditional handover of UE100 to gNB200c, which manages cell c.

[0122] In step S207, in response to receiving the HO Request message, the gNB 200b transmits an HO Request Acknowledge message to the gNB 200a. The HO Request Acknowledge message includes setting information (RRC setting information) necessary for the UE 100 to access the cell b.

[0123] In step S208, in response to receiving the HO Request message, the gNB 200c transmits an HO Request Acknowledge message to the gNB 200a. The HO Request Acknowledge message includes setting information (RRC setting information) necessary for the UE 100 to access the cell c.

[0124] In step S209, the gNB 200a configures a model inference-based conditional handover (CHO) for the UE 100. Specifically, in response to receiving the HO Request Acknowledge messages of steps S207 and S208, the gNB 200a transmits an RRC Reconfiguration message to the UE 100, the RRC Reconfiguration message including the RRC configuration information in these HO Request Acknowledge messages as conditional reconfiguration information. The UE 100 receives the RRC Reconfiguration message. After receiving the RRC Reconfiguration message, UE100 may send an RRC Reconfiguration Complete message to gNB200a.

[0125] Here, the conditional reconfiguration information may include a cell ID and RRC configuration information for each candidate cell (cell b and cell c).

[0126] In the second operation pattern, the conditional reconfiguration information includes model setting information for setting (specifying) an AI / ML model used to evaluate a handover execution trigger. The model setting information includes at least one of the following information 1) to 5). The model setting information may include such information as independent information for each candidate cell. Alternatively, the model setting information may be included as information common to all candidate cells.

[0127] 1) Identification information (model ID or function ID) of the AI / ML model used to evaluate the handover execution trigger: The model ID may be an identifier that uniquely identifies the AI / ML model used to evaluate the conditional handover trigger. The function ID may be, for example, an identifier that indicates a function called conditional handover trigger evaluation. In addition, if the UE100 does not have the AI / ML model specified by the gNB200a, the UE100 may transmit a model provision request to the gNB200a. The model provision request may include identification information (model ID or function ID) of the AI / ML model requested to be provided. The gNB200a may provide the AI / ML model to the UE100 in response to the request.

[0128] 2) AI / ML model: gNB200 may provide UE100 with the AI / ML model itself used to evaluate the handover execution trigger.

[0129] 3) Information indicating "model inference" as event type information in handover execution conditions (trigger conditions): Information indicating "model inference" (which may be a model ID) may be included as the "CHO ​​execution condition" that sets the handover execution conditions.

[0130] 4) Restriction information for trigger evaluation: The restriction information may include information (e.g., a threshold) indicating a radio quality range within which a conditional handover is permitted to be triggered based on model inference. The restriction information may also include a radio quality threshold that forces a conditional handover to be triggered.

[0131] 5) Model activation information: The model activation information is setting information indicating whether to activate the AI / ML model (model inference) at the time of setting the AI / ML model. After the AI / ML model is set, the gNB 200 may activate the AI / ML model (model inference) by sending a model activation command to the UE 100.

[0132] In step S210, the UE 100 may deploy the AI / ML model according to the model configuration information in step S209. Specifically, the UE 100 may deploy the AI / ML model in its AI processor and prepare for execution of the AI / ML model.

[0133] In step S211, the gNB 200 may transmit a model activation command to the UE 100. The model activation command may include identification information (model ID or function ID) of the AI / ML model to be activated. The model activation command may be, for example, an RRC message. The model activation command may be a MAC CE.

[0134] In step S212, UE 100 activates the AI / ML model and starts evaluating the optimal HO execution timing (CHO trigger) for each candidate cell. Note that, if the model activation information indicates that the AI / ML model (model inference) is to be activated at the time of setting the AI / ML model, UE 100 may activate the AI / ML model (model inference) at the time of setting the AI / ML model (step S209) or at the time of deploying the AI / ML model (step S210).

[0135] In step S213, the UE 100 inputs at least the measurement results of the radio quality of each cell into the AI / ML model, and determines the conditional handover execution timing (trigger) using model inference by the AI / ML model. The AI / ML model may output the optimal HO execution timing (access timing) for each candidate cell. When there are multiple candidate cells, the UE 100 may determine the candidate cell with the earliest optimal HO execution timing as the target cell and access the target cell. The AI / ML model may output information for each candidate cell indicating that the optimal HO execution timing has arrived (indicating that HO execution should be triggered). Here, it is assumed that cell b of the candidate cells (cell b and cell c) is determined as the target cell.

[0136] In step S214, the UE 100 executes handover to the target cell (cell b) at the timing determined in step S213, and starts accessing the target cell. The UE 100 may start a random access procedure for cell b at this timing, and transmit a random access preamble to cell b. Alternatively, if the random access procedure is omitted, the UE 100 may transmit an RRC Reconfiguration Complete message to cell b at the optimal timing. When such connection processing is completed, the UE 100 continues communication with cell b as a new serving cell.

[0137] In step S215, gNB200b, which is the target gNB, sends a HO Success message to gNB200a, which is the source gNB, indicating that UE100 has successfully accessed the target cell (cell b).

[0138] In step S216, gNB200a sends a HO Cancel message to gNB200c indicating cancellation of the conditional handover of UE100.

[0139] (3.3.3) Third Operational Pattern of Mobile Communication System The third operational pattern is an operational pattern that applies AI / ML technology to improved conditional handover. In the third operational pattern, the UE 100 uses model inference with the AI / ML model to perform the following two evaluations: 1) evaluation of the possibility of handover; 2) evaluation of the timing of handover execution.

[0140] The third operation pattern is common to the second operation pattern in that the timing of handover execution is evaluated using model inference. However, in the second operation pattern, in step S204, the UE 100 may need to transmit a Measurement Report message to the gNB 200a. In this case, the gNB 200a may determine a large number of cells as candidate cells based on the Measurement Report message. Since only one cell is determined as the target cell among the candidate cells, resource efficiency may be reduced by designating a large number of cells as candidate cells. Furthermore, if a long time has passed since the UE 100 transmitted the Measurement Report message until the CHO condition is satisfied and the target cell is accessed, it is necessary to prepare (reserve) resources for the UE 100 in each candidate cell for a long period of time, which may reduce resource efficiency. Furthermore, the size of the Measurement Report message may become large because it includes measurement results of all cells measured by the UE 100. The third operation pattern is an operation pattern that enables the UE 100 to solve the problem of the conventional conditional handover by evaluating the possibility of handover by model inference.

[0141] In the third operation pattern, in response to detecting an increase in the likelihood of handover, a first notification indicating an increase in the likelihood of handover is transmitted to the gNB200 (source cell). This allows, for example, the gNB200 (source cell) to prepare for handover based on the first notification. Here, the increase in the likelihood of handover may mean that the probability of handover has changed from 0% to a value of 1% or more (i.e., the possibility of handover has occurred). The increase may mean that the probability of handover has exceeded a threshold (which may be a threshold set by the gNB200). The increase may mean that the increase in the probability of handover is equal to or greater than a predetermined amount.

[0142] In the third operation pattern, the UE 100 may transmit a second notification indicating a decrease in the possibility of handover to the gNB 200 (source cell) in response to detecting a decrease in the possibility of handover. As a result, for example, the gNB 200 (source cell) can cancel handover preparation based on the second notification. Here, the decrease in the possibility of handover may mean that the probability of handover has changed from a value of 1% or more to 0% (i.e., the possibility of handover has disappeared). The decrease may mean that the probability of handover has fallen below a threshold (which may be a threshold set by the gNB 200). The decrease may mean that the amount of decrease in the probability of handover is equal to or greater than a predetermined amount.

[0143] FIG. 12 is a diagram showing an example of a third operation pattern of the mobile communication system 1 according to the embodiment.

[0144] In step S301, UE100 is in an RRC connected state with cell a managed by gNB200a as the serving cell.

[0145] In step S302, UE100 may transmit to cell a (gNB200a) a model notification including identification information (function ID or model ID) of its AI / ML model. UE100 may transmit to cell a (gNB200a) a UE Capability Information message, which is a type of RRC message and indicates the capabilities of UE100, including the model notification. The model notification may be registered and stored in gNB200 (network 5) as part of the UE context.

[0146] In step S303, the gNB200a configures the UE100 for model inference-based conditional handover. Specifically, the gNB200a transmits an RRC Reconfiguration message including model configuration information to the UE100. The UE100 receives the RRC Reconfiguration message. After receiving the RRC Reconfiguration message, the UE100 may transmit an RRC Reconfiguration Complete message to the gNB200a.

[0147] In the third operation pattern, the model setting information includes model setting information for setting (specifying) an AI / ML model to be used for evaluating a handover execution trigger. The model setting information includes at least one of the following information 1) to 6):

[0148] 1) Identification information (model ID or function ID) of the AI / ML model used to evaluate the handover possibility and the handover execution trigger: The model ID may be an identifier that uniquely identifies the AI / ML model used to evaluate the handover possibility and the handover execution trigger. The function ID may be, for example, an identifier indicating a function of evaluating the handover possibility and the handover execution trigger (or a function such as "model inference-based handover"). The evaluation of the handover possibility and the evaluation of the handover execution trigger may be performed using one AI / ML model, or may be performed using two different AI / ML models, respectively. In this case, when two different AI / ML models are used, the model setting information may include two pieces of AI / ML model identification information. If the UE 100 does not have an AI / ML model specified by the gNB 200a, the UE 100 may transmit a model provision request to the gNB 200a. The model provision request may include identification information (model ID or function ID) of the AI / ML model requested to be provided. In response to the request, gNB200a may provide the AI / ML model to UE100.

[0149] 2) AI / ML Model: The gNB 200 may provide the UE 100 with the AI / ML model itself used for evaluating handover possibility and evaluating handover execution triggers. When the evaluation of handover possibility and the evaluation of handover execution triggers are performed using two different AI / ML models, respectively, the model setting information may include the two different AI / ML models.

[0150] 3) Information indicating "model inference" as event type information in handover execution conditions (trigger conditions): Information indicating "model inference" (which may be a model ID) may be included as the "CHO ​​execution condition" that sets the handover execution conditions.

[0151] 4) Restriction information for trigger evaluation: The restriction information may include information (e.g., one or more thresholds) indicating a radio quality range that is permitted to trigger a conditional handover based on model inference. The restriction information may include a radio quality threshold that forces a conditional handover to be triggered.

[0152] 5) Model activation information: The model activation information is setting information indicating whether to activate the AI / ML model (model inference) at the time of setting the AI / ML model. After the AI / ML model is set, the gNB 200 may activate the AI / ML model (model inference) by sending a model activation command to the UE 100.

[0153] 6) Information on measurement target frequencies (handover destination candidate frequencies): The model configuration information may include information for setting the frequency at which the UE 100 should perform measurements. Alternatively, the UE 100 may receive SIB4 including information for inter-frequency cell reselection from the gNB 200a, and may determine the frequency at which the UE 100 should perform measurements based on the frequency information included in the SIB4.

[0154] In the third operation pattern, the gNB 200a may not perform measurement configuration for measurement reporting on the UE 100. For example, the gNB 200a may perform the configuration of step S303 on the UE 100 without performing measurement configuration on the UE 100 when the UE 100 connects to the gNB 200a.

[0155] In step S304, the UE 100 may deploy the AI / ML model according to the model configuration information in step S303. Specifically, the UE 100 may deploy the AI / ML model in its AI processor and prepare for execution of the AI / ML model.

[0156] In step S305, the gNB 200 may transmit a model activation command to the UE 100. The model activation command may include identification information (model ID or function ID) of the AI / ML model to be activated. The model activation command may be, for example, an RRC message. The model activation command may be a MAC CE.

[0157] In step S306, UE 100 activates the AI / ML model and starts evaluating the HO possibility (HO probability) for each candidate cell. Note that, if the model activation information indicates that the AI / ML model (model inference) is to be activated at the time of setting the AI / ML model, UE 100 may activate the AI / ML model (model inference) at the time of setting the AI / ML model (step S303) or at the time of deploying the AI / ML model (step S304).

[0158] In step S307, UE100 estimates (determines) the candidate cell and its handover possibility using model inference using the AI / ML model. Here, UE100 determines cell b as a candidate cell and determines that the possibility (probability) of handover to cell b has increased. For example, UE100 may detect that the probability of handover to cell b has changed from 0% to a value of 1% or more (i.e., that the possibility of handover has occurred), that the probability of handover to cell b has exceeded a threshold (which may be a threshold set by gNB200), or that the increase in the probability of handover to cell b is greater than or equal to a predetermined amount.

[0159] In step S308, the UE 100 transmits to the cell a (gNB 200a) a first notification (HO possibility notification) indicating that the possibility (probability) of handover to the cell b has increased. The gNB 200a receives the first notification (HO possibility notification). The UE 100 may transmit the first notification (HO possibility notification) by including it in a UE Assistance Information message, which is a type of RRC message. The UE 100 may transmit the first notification (HO possibility notification) by including it in a new message for AI / ML. The first notification (HO possibility notification) includes at least one piece of information selected from the following 1) to 3).

[0160] 1) Cell ID of Candidate Cell (Target Cell): In the illustrated example, the UE 100 may include the cell ID of the cell b in the first notification (HO possibility notification).

[0161] 2) Estimated Handover Probability: In the illustrated example, the UE 100 may include the probability of performing a handover to the cell b in the first notification (HO possibility notification).

[0162] 3) Estimated Handover Execution Timing: In the illustrated example, the UE 100 may include information indicating the estimated timing of handover to cell b in the first notification (HO possibility notification). In this case, the gNB 200a may withhold the request for resource preparation for cell b (step S309) until the timing approaches.

[0163] In step S309, gNB200a transmits to gNB200b managing cell b an HO Request message requesting a conditional handover of UE100. Here, gNB200a may transmit the information included in the notification of step S308 in the HO Request message.

[0164] In step S310, in response to receiving the HO Request message, the gNB 200b transmits an HO Request Acknowledge message to the gNB 200a. The HO Request Acknowledge message includes setting information (RRC setting information) necessary for the UE 100 to access cell b. The gNB 200b may transmit the HO Request Acknowledge message by including information indicating the time (deadline) for reserving resources for the UE 100. The time (deadline) specifies the time during which the UE 100 can access cell b.

[0165] In step S311, in response to receiving the HO Request Acknowledge message, the gNB200b transmits to the UE100 an HO preparation complete message including the RRC setting information in the HO Request Acknowledge message and indicating that handover preparation (Ack of the target gNB200) has been completed. The UE100 receives the HO preparation complete message. The HO preparation complete message may be an RRC Reconfiguration message. In this case, after receiving the RRC Reconfiguration message, the UE100 may transmit an RRC Reconfiguration Complete message to the gNB200a.

[0166] The HO preparation complete message may include information indicating the time (deadline) for which the target gNB gNB 200b (cell b) reserves resources. When the UE 100 receives the HO preparation complete message, the UE 100 may start a timer (a timer associated with cell b) to which the time is set. The UE 100 may stop the timer when accessing the target cell, cell b. When the timer expires, the UE 100 may determine that access to cell b is no longer possible.

[0167] In step S312, the UE 100 starts evaluating the optimal HO execution timing (CHO trigger) for cell b, which is the target cell. For example, the UE 100 inputs at least the measurement results of the radio quality of each cell into the AI / ML model and determines the handover execution timing (trigger) using model inference by the AI / ML model. The AI / ML model may output the optimal HO execution timing (access timing) for the target cell (cell b). Note that the UE 100 may continue the evaluation of the handover possibility in step S306. The UE 100 may also stop the evaluation.

[0168] In step S313, the UE 100 executes handover to the target cell (cell b) at the timing determined in step S312, and starts accessing the target cell. The UE 100 may start a random access procedure for cell b at this timing, and transmit a random access preamble to cell b. Alternatively, if the random access procedure is omitted, the UE 100 may transmit an RRC Reconfiguration Complete message to cell b at the optimal timing. When such connection processing is completed, the UE 100 continues communication with cell b as a new serving cell.

[0169] In step S314, gNB200b, which is the target gNB, sends a HO Success message to gNB200a, which is the source gNB, indicating that UE100 has successfully accessed the target cell (cell b).

[0170] Fig. 13 is a diagram showing another example of the third operation pattern of the mobile communication system 1 according to the embodiment. The operation example in Fig. 13 will be described mainly focusing on differences from the operation example in Fig. 12 .

[0171] The operations in steps S331 to S337 are the same as those in the operation example of FIG.

[0172] In step S338, the UE 100 estimates (determines) the candidate cells and the handover possibility thereof by using model inference using the AI / ML model. Here, the UE 100 determines the cell b and the cell c as candidate cells, and determines that the possibility (probability) of handover to the cell b and the cell c has increased.

[0173] In step S339, UE100 transmits a first notification (HO possibility notification 1) to cell a (gNB200a) indicating that the possibility (probability) of handover to cell b and cell c has increased. gNB200a receives the first notification (HO possibility notification 1). The first notification (HO possibility notification 1) includes at least one of the following information 1) to 3).

[0174] 1) Cell IDs of Candidate Cells (Target Cells): In the illustrated example, the UE 100 may include the cell ID of the cell b and the cell ID of the cell c in the first notification (HO Possibility Notification 1).

[0175] 2) Estimated Handover Probability: In the illustrated example, the UE 100 may include the probability of performing a handover to the cell b and the probability of performing a handover to the cell c in the first notification (HO Possibility Notification 1).

[0176] 3) Estimated Handover Execution Timing: In the illustrated example, the UE 100 may include information indicating an estimated timing for performing handover to cell b and information indicating an estimated timing for performing handover to cell c in the first notification (HO Possibility Notification 1).

[0177] In step S340, gNB200a transmits to gNB200b managing cell b an HO Request message requesting a conditional handover of UE100. gNB200a may transmit the information included in the notification of step S339 in the HO Request message.

[0178] In step S341, gNB200a transmits to gNB200c, which manages cell c, an HO Request message requesting a conditional handover of UE100. gNB200a may transmit the information included in the notification of step S339 in the HO Request message.

[0179] In step S342, in response to receiving the HO Request message, the gNB 200b transmits an HO Request Acknowledge message to the gNB 200a. The HO Request Acknowledge message includes setting information (RRC setting information) necessary for the UE 100 to access cell b. The gNB 200b may transmit the HO Request Acknowledge message by including information indicating the time (deadline) for reserving resources for the UE 100. The time (deadline) specifies the time during which the UE 100 can access cell b.

[0180] In step S343, in response to receiving the HO Request message, the gNB 200c transmits an HO Request Acknowledge message to the gNB 200a. The HO Request Acknowledge message includes setting information (RRC setting information) necessary for the UE 100 to access the cell c. The gNB 200b may transmit the HO Request Acknowledge message by including information indicating the time (deadline) for reserving resources for the UE 100. The time (deadline) specifies the time during which the UE 100 can access the cell c.

[0181] In step S344, in response to receiving the HO Request Acknowledge messages of steps S342 and S343, gNB200b includes the RRC setting information in these HO Request Acknowledge messages and transmits an HO preparation complete message to UE100 indicating that handover preparation (Ack of target gNB200) has been completed. UE100 receives the HO preparation complete message. The HO preparation complete message may be an RRC Reconfiguration message.

[0182] In step S345, UE100 estimates (determines) the target cell and its handover possibility using model inference using the AI / ML model. Here, UE100 determines that the possibility (probability) of handover to cell c has decreased. For example, UE100 may detect that the probability of handover to cell c has changed from a value of 1% or more to 0% (i.e., the possibility of handover has disappeared), that the probability of handover to cell c has fallen below a threshold (which may be a threshold set by gNB200), or that the decrease in the probability of handover to cell c is greater than or equal to a predetermined amount.

[0183] In step S346, the UE 100 transmits to the cell a (gNB 200a) a second notification (HO possibility notification 2) indicating that the possibility (probability) of handover to the cell c has decreased. The gNB 200a receives the second notification (HO possibility notification 2). The UE 100 may transmit the second notification (HO possibility notification 2) by including it in a UE Assistance Information message, which is a type of RRC message. The UE 100 may transmit the second notification (HO possibility notification 2) by including it in a new message for AI / ML. The second notification (HO possibility notification 2) includes at least one of the following information 1) and 2).

[0184] 1) Cell ID of a candidate cell (target cell) for which the handover probability has decreased: In the illustrated example, the UE 100 may include the cell ID of the cell c in the second notification (HO possibility notification 2).

[0185] 2) Estimated Handover Probability: In the illustrated example, the UE 100 may include the probability of performing handover to the cell c in the second notification (HO Possibility Notification 2).

[0186] In step S347, gNB200a transmits an HO Cancel message to gNB200c, which manages cell c, indicating the cancellation of the conditional handover of UE100. This allows gNB200c to release the resources prepared (reserved) for UE100.

[0187] In step S348, the UE 100 evaluates the optimal HO execution timing (CHO trigger) for the cell b that is the target cell.

[0188] In step S349, the UE 100 executes handover to the target cell (cell b) at the timing determined in step S348, and starts access to the target cell. When such connection processing is completed, the UE 100 continues communication with the cell b as a new serving cell.

[0189] In step S350, gNB200b, which is the target gNB, sends a HO Success message to gNB200a, which is the source gNB, indicating that UE100 has successfully accessed the target cell (cell b).

[0190] (3.3.4) Fourth Operation Pattern of Mobile Communication System The fourth operation pattern is an operation pattern that can be implemented in combination with the first to third operation patterns.

[0191] In the fourth operation pattern, after attempting a handover (access to a target cell), the UE 100 stores log information regarding whether the handover was successful. The log information is failure log information (handover failure report) indicating that the handover failed, or success log information (successful handover report) indicating that the handover was successful. The log information includes model inference information regarding whether model inference was applied to the handover. The model inference information may include identification information (function ID or model ID) of the AI / ML model used in the model inference. The UE 100 transmits a notification including the log information to the gNB 200.

[0192] This allows the gNB 200 (network 5) to determine whether the handover in the UE 100 was successful or not based on the log information, and to determine whether model inference was applied to the handover (and / or which AI / ML model was applied). Therefore, the network 5 can appropriately optimize the network 5 (and / or optimize the AI / ML model) to increase the handover success rate.

[0193] 14 is a diagram showing an example of the operation of the UE 100 when handover fails in the fourth operation pattern of the mobile communication system 1 according to the embodiment. The UE 100 is assumed to have an AI / ML model (model inference) of any one of the first to third operation patterns set thereto.

[0194] In step S401, the UE 100 identifies a target cell and attempts to access the target cell.

[0195] In step S402, the UE 100 fails to access the target cell. For example, if the random access procedure to the target cell fails, the UE 100 determines that the UE 100 has failed to access the target cell.

[0196] In step S403, the UE 100 stores failure log information. The failure log information is also referred to as handover failure information. The failure log information may form part of a radio link failure (RLF) report. The failure log information may include information indicating a handover failure, a cell ID of the source cell, a cell ID of the target cell (i.e., the handover failed cell), and information indicating a type of failed handover. In a fourth operation pattern, the failure log information includes at least one of the following information 1) to 4).

[0197] 1) Identification information of the AI / ML model used in model inference (model ID or function ID): The UE 100 may store identification information of the AI / ML model used in model inference by including it in the failure log information.

[0198] 2) Information indicating "model inference-based handover" as the type of failed handover: UE 100 may store information indicating "model inference-based handover" as the type of failed handover (lastHO-Type) in the failure log information.

[0199] 3) Information on Cell ID and Frequency of Target Cell: The UE 100 may store information on the cell ID and frequency of the target cell determined by model inference in the failure log information.

[0200] 4) Information regarding model inference results: UE100 may store at least one of information indicating the time from HO possibility estimation (model inference) to failure to access the target cell, information indicating the handover execution timing determined by model inference, and information indicating the handover possibility determined by model inference in the failure log information.

[0201] 15 is a diagram showing an example of the operation of the UE 100 when handover is successful in the fourth operation pattern of the mobile communication system 1 according to the embodiment. The UE 100 is assumed to have an AI / ML model (model inference) of any one of the first to third operation patterns set thereto.

[0202] In step S411, the UE 100 identifies a target cell and attempts to access the target cell.

[0203] In step S412, the UE 100 successfully accesses the target cell. For example, if the random access procedure to the target cell is successful, the UE 100 determines that the UE 100 has successfully accessed the target cell.

[0204] In step S413, the UE 100 stores success log information. The success log information is also referred to as a success handover report (SuccessHO-Report). The success log information may include a cell ID of the source cell and a cell ID of the target cell. In a fourth operation pattern, the success log information includes at least one piece of information among the following 1) to 4).

[0205] 1) Identification information of the AI / ML model used in model inference (model ID or function ID): The UE 100 may store identification information of the AI / ML model used in model inference by including it in the success log information.

[0206] 2) Information indicating "model inference-based handover" as the type of successful handover: The UE 100 may store information indicating "model inference-based handover" as the type of successful handover, by including it in the success log information.

[0207] 3) Information on Cell ID and Frequency of Target Cell: The UE 100 may store information on the cell ID and frequency of the target cell determined by model inference in the success log information.

[0208] 4) Information regarding model inference results: UE100 may store at least one of information indicating the time from HO possibility estimation (model inference) to successful access to the target cell, information indicating the handover execution timing determined by model inference, and information indicating the handover possibility determined by model inference in the success log information.

[0209] FIG. 16 is a diagram illustrating an example of a log transmission operation of the UE 100 in the fourth operation pattern of the mobile communication system 1 according to the embodiment.

[0210] In step S421, UE100 transmits log retention information (Availability Indication) indicating that log information is retained to gNB200. When UE100 retains failure log information, UE100 may transmit first log retention information indicating that failure log information is retained to gNB200. When UE100 retains success log information, UE100 may transmit second log retention information indicating that success log information is retained to gNB200. Note that UE100 may transmit log retention information to gNB200 at the time of RRC connection setup, RRC connection resume, etc.

[0211] In step S422, the UE 100 receives a request message (UE Information Request message) requesting the transmission of log information from the gNB 200. The request message may include first request information requesting the transmission of failure log information and / or second request information requesting the transmission of success log information.

[0212] In step S423, in response to receiving the request message, UE100 transmits a response message (UE Information Response message) including log information to gNB200.

[0213] (4) Other Embodiments 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.

[0214] 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.

[0215] 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.

[0216] 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.

[0217] 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).

[0218] 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.

[0219] 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.

[0220] 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.

[0221] This application claims priority from Japanese Patent Application No. 2023-132048 (filed August 14, 2023), the entire contents of which are incorporated herein by reference.

[0222] (5) Supplementary Notes The following are additional notes regarding the features of the above-described embodiment.

[0223] (Supplementary Note 1) A communication method executed by a user equipment in a mobile communication system, comprising: a step of transmitting a notification regarding model inference based on an artificial intelligence or machine learning (AI / ML) model, based on the user equipment's evaluation of the possibility of a cell switch from a source cell to a candidate cell and / or the timing of performing the cell switch, to a network node.

[0224] (Supplementary Note 2) The communication method according to Supplementary Note 1, wherein the notification includes information indicating an inference result of the model inference and identification information of the candidate cell, and the network node is a network node that manages the source cell.

[0225] (Supplementary Note 3) The communication method according to Supplementary Note 2, further comprising the step of the user equipment evaluating the likelihood using the model inference, and the transmitting step includes the step of transmitting a first notification indicating the increase in the likelihood to the network node in response to detecting the increase in the likelihood.

[0226] (Supplementary Note 4) The communication method according to Supplementary Note 2 or 3, wherein the transmitting step transmits a second notification indicating the decrease in the likelihood to the network node in response to detecting the decrease in the likelihood.

[0227] (Supplementary Note 5) The communication method according to any one of Supplementary Notes 1 to 4, further comprising: a step of attempting the cell switch; and a step of storing log information regarding whether the cell switch was successful or not, wherein the log information includes model inference information regarding whether the model inference was applied to the cell switch; and wherein the transmitting step includes a step of transmitting the notification including the log information to the network node.

[0228] (Supplementary Note 6) The communication method according to Supplementary Note 5, wherein the model inference information includes identification information for identifying the AI / ML model used in the model inference.

[0229] (Supplementary Note 7) The communication method according to Supplementary Note 5 or 6, wherein the model inference information includes information indicating that the model inference has been applied to the cell switching.

[0230] (Supplementary Note 8) The communication method according to any one of Supplementary Notes 5 to 7, wherein the model inference information includes information indicating a result of the model inference.

[0231] (Supplementary Note 9) The communication method according to any one of Supplementary Notes 5 to 8, wherein the log information is failure log information indicating that the cell switching has failed.

[0232] (Supplementary Note 10) The communication method according to any one of Supplementary Notes 5 to 8, wherein the log information is success log information indicating that the cell switching has been successful.

[0233] (Supplementary Note 11) A user equipment for use in a mobile communication system, comprising: a transmitter configured to transmit a notification regarding model inference based on an artificial intelligence or machine learning (AI / ML) model, based on the user equipment's evaluation of a possibility of a cell switch from a source cell to a candidate cell and / or a timing of performing the cell switch, to a network node.

[0234] (Supplementary Note 12) A network node used in a mobile communication system, comprising: a receiving unit configured to receive, from a user equipment, a notification regarding model inference based on an artificial intelligence or machine learning (AI / ML) model, based on the user equipment's evaluation of a possibility of a cell switch from a source cell to a candidate cell and / or a timing of executing the cell switch using the model inference.

[0235] 1: Mobile communication system 5: Network 10: RAN (NG-RAN) 20: CN (5GC) 100: UE 110: Receiving unit 120: Transmitting unit 130: Control 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, The system includes sending a notification to a network node regarding the model inference, based on the user device's evaluation of the possibility of cell switching from a source cell to a candidate cell and / or the timing of such cell switching using an artificial intelligence or machine learning (AI / ML) model. Communication method.

2. The notification includes information indicating the inference result of the model inference and identification information of the candidate cell. The aforementioned network node is a network node that manages the aforementioned source cell. The communication method according to claim 1.

3. The user device further includes evaluating the possibility using the model inference, The aforementioned transmission includes, in response to detecting an increase in the aforementioned probability, transmitting a first notification indicating the increase in the aforementioned probability to the network node. The communication method according to claim 2.

4. The aforementioned transmission includes, in response to detecting a decrease in the aforementioned probability, transmitting a second notification indicating the decrease in the aforementioned probability to the network node. The communication method according to claim 2 or 3.

5. Attempting the aforementioned cell switching, The system further includes storing log information regarding whether or not the cell switching was successful. The log information includes model inference information regarding whether or not the model inference was applied to the cell switching, The aforementioned transmission includes transmitting the notification containing the log information to the network node. The communication method according to claim 1.

6. The model inference information includes identification information that identifies the AI / ML model used in the model inference. The communication method according to claim 5.

7. The model inference information includes information indicating that the model inference was applied to the cell switching. The communication method according to claim 5.

8. The model inference information includes information indicating the results of the model inference. The communication method according to claim 5.

9. The log information mentioned above is failure log information indicating that the cell switching failed. The communication method according to any one of claims 5 to 8.

10. The log information mentioned above is success log information indicating that the cell switching was successful. The communication method according to any one of claims 5 to 8.

11. A user device used in a mobile communication system, The system includes a transmission unit that, based on the user device's evaluation of the possibility of cell switching from a source cell to a candidate cell and / or the timing of such cell switching using model inference by an artificial intelligence or machine learning (AI / ML) model, transmits a notification regarding the model inference to a network node. User device.

12. A network node used in a mobile communication system, The system includes a receiving unit that receives notifications from the user device regarding model inference, based on the user device's evaluation of the possibility of cell switching from a source cell to a candidate cell and / or the timing of such cell switching using model inference by an artificial intelligence or machine learning (AI / ML) model. Network node.