Communication control method and user device

Abstract

A communication control method in a mobile communication system is provided. The communication control method comprises a step of inferring, by user equipment using an AI / ML model, whether a data traffic is generated in a downlink in a next DRX on-duration. The communication control method further comprises a step of performing a wake-up in the next DRX on-duration or skipping a wake-up in the next DRX on-duration by the user equipment on the basis of the result of the inferring of whether the data traffic is generated.

Description

Communication Control Method

[0001] The present disclosure relates to a communication control method.

[0002] In recent years, the Third Generation Partnership Project (3GPP) (registered trademark), a standardization project for mobile communication systems, has been studying the application of artificial intelligence (AI) technology, particularly machine learning (ML) technology, to wireless communication (air interface) in mobile communication systems.

[0003] For example, the following Non-Patent Document 1 discusses that a simulation was performed to predict the next traffic burst by applying an AI algorithm to DRX (Discontinuous Reception), and that it was possible to significantly reduce delay (latency) with the same power consumption as a conventional DRX configuration. Furthermore, the following Non-Patent Document 2 discusses identifying high-layer use cases to which AI / ML is applied, such as dynamic TDD, positioning, mobility management, and service awareness RRM, and studying their performance evaluation.

[0004] 3GPP contribution: RP-223079, “Study on AI / ML for NR air interface higher layer” 3GPP contribution: RP-222954, “Motivation on AI / ML for NR air interface high layer”

[0005] A communication control method according to one aspect is a communication control method in a mobile communication system, the communication control method including a step in which a user equipment uses an AI / ML model to infer whether or not downlink data traffic will occur in a next DRX on-duration, and a step in which the user equipment either wakes up in the next DRX on-duration or skips wake-up in the next DRX on-duration based on the inference result of whether or not data traffic will occur.

[0006] Another aspect of the present invention relates to a communication control method for a mobile communication system. The communication control method includes a step in which a network node uses an AI / ML model to infer whether or not downlink data traffic will occur in a next DRX-on period. The communication control method also includes a step in which the network node transmits a first dynamic DRX instruction to a user equipment, the first dynamic DRX instruction instructing the user equipment to either wake up in the next DRX-on period or sleep in the next DRX-on period, based on the inference result of whether or not data traffic will occur. The communication control method also includes a step in which the user equipment uses the AI / ML model to infer whether or not data traffic will occur in the next DRX-on period. The communication control method also includes a step in which the user equipment wakes up, based on the first dynamic DRX instruction and the inference result of the user equipment, at a timing when both the first dynamic DRX instruction and the inference result of the user equipment indicate wake-up.

[0007] FIG. 1 is a diagram showing an example of the configuration of a mobile communication system according to the first embodiment. FIG. 2 is a diagram showing an example of the configuration of a UE (user equipment) according to the first embodiment. FIG. 3 is a diagram showing an example of the configuration of a gNB (base station) according to the first embodiment. FIG. 4 is a diagram showing an example of the configuration of a protocol stack according to the first embodiment. FIG. 5 is a diagram showing an example of the configuration of a protocol stack according to the first embodiment. FIG. 6 is a diagram showing an example of the configuration of functional blocks of the AI / ML technology according to the first embodiment. FIG. 7 is a diagram showing an example of operation in the AI / ML technology according to the first embodiment. FIG. 8 is a diagram showing an example of the arrangement of functional blocks of the AI / ML technology according to the first embodiment. FIG. 9 is a diagram showing an example of reducing CSI-RS according to the first embodiment. FIG. 10 is a diagram showing an example of reducing CSI-RS according to the first embodiment. FIG. 11 is a diagram showing an example of operation according to the first embodiment. FIG. 12 is a diagram showing an example of the arrangement of functional blocks of the AI / ML technology according to the first embodiment. FIG. 13 is a diagram showing an example of the arrangement of functional blocks of the AI / ML technology according to the first embodiment. FIG. 14 is a diagram illustrating an example of the layout of functional blocks of AI / ML technology according to the first embodiment. FIG. 15 is a diagram illustrating an example of operation according to the first embodiment. FIG. 16 is a diagram illustrating an example of the layout of functional blocks of AI / ML technology according to the first embodiment. FIG. 17 is a diagram illustrating an example of operation according to the first embodiment. FIG. 18 is a diagram illustrating an example of operation according to the first embodiment. FIG. 19 is a diagram illustrating an example of a setting message according to the first embodiment. FIGS. 20(A) and 20(B) illustrate an example of a DRX cycle according to the first embodiment, and FIG. 20(C) illustrates a flow of wake-up determination according to the first embodiment. FIG. 21 is a diagram illustrating a first example of operation according to the first embodiment. FIG. 22 is a diagram illustrating a second example of operation according to the first embodiment. FIGS. 23(A) and 23(B) illustrate an example of timing according to the first embodiment. FIG. 24 is a diagram illustrating a first example of operation according to the second embodiment. FIGS. 25(A) to 25(C) illustrate an example of timing according to the second embodiment. Fig. 26 is a diagram showing a second operation example according to the second embodiment. Fig. 27 is a diagram showing an operation example of the control period method according to the second embodiment. Figs. 28(A) to 28(C) are diagrams showing timing examples according to the second embodiment. Fig. 29 is a diagram showing a third operation example according to the second embodiment.30(A) to 30(C) are diagrams showing an example of timing according to the second embodiment. FIG. 31 is a diagram showing a first example of operation according to the third embodiment. FIGS. 32(A) to 32(D) are diagrams showing an example of timing according to the third embodiment. FIG. 33 is a diagram showing a second example of operation according to the third embodiment. FIGS. 34(A) to 34(D) are diagrams showing an example of timing according to the third embodiment.

[0008] [First embodiment] A mobile communication system according to a first 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.

[0009] (Configuration of mobile communication system) The configuration of a mobile communication system according to the first embodiment will be described. FIG. 1 is a diagram showing an example of the configuration of a mobile communication system 1 according to the first embodiment. The mobile communication system 1 conforms to the 5th Generation System (5GS) of the 3GPP standard. Although 5GS will be described below as an example, the mobile communication system may also be at least partially applied to an LTE (Long Term Evolution) system. The mobile communication system may also be at least partially applied to a sixth generation (6G) system or later system.

[0010] 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.

[0011] 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 (including a smartphone) and / or a tablet terminal, a notebook PC, a communication module (including 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).

[0012] The NG-RAN 10 includes a base station (called a "gNB" in a 5G system) 200. 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").

[0013] 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.

[0014] 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 300 are connected to the gNB 200 via an NG interface, which is an interface between a base station and a core network. The AMF and the UPF 300 may be core network devices included in the CN 20.

[0015] 2 is a diagram showing an example of the configuration of a UE 100 (user equipment) according to the first embodiment. The UE 100 includes a receiving unit 110, a transmitting unit 120, and a control unit 130. The receiving unit 110 and the transmitting unit 120 constitute a communication unit that performs wireless communication with the gNB 200. The UE 100 is an example of a communication device.

[0016] 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.

[0017] 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.

[0018] The control unit 130 performs various controls and processes in the UE 100. Such processes include processes of each layer described below. 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 processes by the processor. The processor may include a baseband processor and a CPU (Central Processing Unit). The baseband processor performs modulation / demodulation, encoding / decoding, etc. of baseband signals. The CPU executes programs stored in the memory to perform various processes. Note that the processes or operations performed in the UE 100 may be performed in the control unit 130.

[0019] 3 is a diagram showing an example of the configuration of a gNB 200 (base station) according to the first embodiment. The gNB 200 includes a transmitter 210, a receiver 220, a controller 230, and a backhaul communication unit 250. The transmitter 210 and the receiver 220 constitute a communication unit that performs wireless communication with the UE 100. The backhaul communication unit 250 constitutes a network communication unit that communicates with the CN 20. The gNB 200 is another example of a communication device.

[0020] 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.

[0021] 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.

[0022] The control unit 230 performs various controls and processes in the gNB 200. Such processes include processes for each layer described below. The control unit 230 includes at least one processor and at least one memory. The memory stores programs executed by the processor and information used in the processes by the processor. The processor may include a baseband processor and a CPU. The baseband processor performs modulation / demodulation, encoding / decoding, etc. of baseband signals. The CPU executes programs stored in the memory to perform various processes. Note that the processes or operations performed in the gNB 200 may be performed by the control unit 230.

[0023] The backhaul communication unit 250 is connected to adjacent base stations via an Xn interface, which is an interface between base stations. The backhaul communication unit 250 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.

[0024] FIG. 4 is a diagram showing an example of the configuration of a protocol stack of a radio interface of a user plane that handles data.

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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.

[0029] The MAC layer performs data priority control, retransmission processing using Hybrid Automatic Repeat reQuest (HARQ), random access procedures, etc. Data and control information are transmitted between the MAC layer of the UE 100 and the MAC layer of the gNB 200 via a transport channel. The MAC layer of the gNB 200 includes a scheduler. The scheduler determines the uplink and downlink transport format (transport block size, modulation and coding scheme (MCS)) and the resource blocks to be allocated to the UE 100.

[0030] The RLC layer transmits data to the receiving RLC layer using the functions of the MAC layer and PHY layer. Data and control information are transmitted between the RLC layer of the UE 100 and the RLC layer of the gNB 200 via a logical channel.

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

[0032] The SDAP layer maps IP flows, which are units for Quality of Service (QoS) control by the core network, to radio bearers, which are units for QoS control by the access stratum (AS). Note that if the RAN is connected to the EPC, SDAP may not be required.

[0033] FIG. 5 is a diagram showing the configuration of a protocol stack of a radio interface of a control plane that handles signaling (control signals).

[0034] The protocol stack of the radio interface of the control plane includes a radio resource control (RRC) layer and a non-access stratum (NAS) instead of the SDAP layer shown in FIG.

[0035] RRC signaling for various settings is transmitted between the RRC layer of UE100 and the RRC layer of gNB200. The RRC layer controls logical channels, transport channels, and physical channels according to the establishment, re-establishment, and release of radio bearers. When there is a connection (RRC connection) between the RRC of UE100 and the RRC of gNB200, UE100 is in an RRC connected state. When there is no connection (RRC connection) between the RRC of UE100 and the RRC of gNB200, UE100 is in an RRC idle state. When the connection between the RRC of UE100 and the RRC of gNB200 is suspended, UE100 is in an RRC inactive state.

[0036] The NAS, 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 300. Note that the UE 100 has an application layer and the like in addition to the radio interface protocol. Also, the layer below the NAS is called an Access Stratum (AS).

[0037] (AI / ML Technology) Next, the AI / ML technology according to the embodiment will be described. Fig. 6 is a diagram showing an example of the configuration of functional blocks of the AI / ML technology in the mobile communication system 1 according to the first embodiment.

[0038] The functional block configuration example 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.

[0039] The data collection unit A1 collects input data, specifically, learning data and inference data. The data collection unit A1 outputs the learning data to the model learning unit A2. The data collection unit A1 also 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.

[0040] The model learning unit A2 performs model learning. Specifically, the model learning unit A2 optimizes parameters of the learning model through machine learning using the learning data, and derives (or generates, or updates) a learned model. The model learning unit A2 outputs the derived learned model to the model inference unit A3. 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 answer data as learning data. For example, in unsupervised learning, feature points are memorized from a large amount of learning data, and the correct answer is determined (range estimation). Reinforcement learning is a method of assigning a score to an output result and learning how to maximize the score. Although supervised learning will be described below, unsupervised learning or reinforcement learning may also be applied as machine learning.

[0041] The model inference unit A3 performs model inference. 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. Here, there are various model approaches, such as 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.

[0042] The data processing unit A4 receives the inference result data and performs processing that utilizes the inference result data.

[0043] FIG. 7 is a diagram illustrating an example of operation in the AI / ML technology according to the first embodiment.

[0044] The transmitting entity TE is, for example, an entity in which machine learning is performed. The transmitting entity TE performs machine learning to derive a trained model. The transmitting entity TE then generates inference result data as an inference result using the trained model. The transmitting entity TE transmits the inference result data to the receiving entity RE.

[0045] On the other hand, the receiving entity RE is, for example, an entity in which machine learning is not performed. The transmitting entity TE performs various processes using the inference result data received from the transmitting entity TE.

[0046] The entity may be, for example, a device, a functional block included in the device, or a hardware block included in the device.

[0047] For example, the transmitting entity TE may be the UE 100, and the receiving entity RE may be the gNB 200 or a core network device. Alternatively, the transmitting entity TE may be the gNB 200 or a core network device, and the receiving entity RE may be the UE 100.

[0048] As shown in Fig. 7, in step S1, the transmitting entity TE transmits control data related to AI / ML technology to the receiving entity RE and receives the control data from the receiving entity RE. The control data may be an RRC message, which is signaling of the RRC layer (i.e., Layer 3). The control data may be a MAC Control Element (CE), which is signaling of the MAC layer (i.e., Layer 2). The control data may be Downlink Control Information (DCI), which is signaling of the PHY layer (i.e., Layer 1). The downlink signaling may be UE-specific signaling. The downlink signaling may be broadcast signaling. The control data may be a control message in a control layer (e.g., AI / ML layer) dedicated to artificial intelligence or machine learning.

[0049] (Layout Examples and Use Cases) Next, a description will be given of how the functional blocks shown in Fig. 6 are arranged in the mobile communication system 1. Below, layout examples of the functional blocks will be described along with specific use cases.

[0050] For example, there are three use cases in which AI / ML technology is applied:

[0051] (1.1) "CSI (Channel State Information) Feedback Enhancement"

[0052] (1.2) "Beam management"

[0053] (1.3) "Positioning Accuracy Enhancement" Below, an example of the placement of functional blocks for each use case will be described.

[0054] (1.1) Example of functional block arrangement in "CSI feedback improvement" "CSI feedback improvement" represents a use case in which, for example, machine learning technology is applied to CSI fed back from UE100 to gNB200. CSI is information about the channel state in the downlink between UE100 and gNB200. The CSI includes at least one of a channel quality indicator (CQI), a precoding matrix indicator (PMI), and a rank indicator (RI). The gNB200 performs, for example, downlink scheduling based on the CSI feedback from UE100.

[0055] 8 is a diagram showing an example of the arrangement of each functional block in "CSI feedback improvement". In the example of "CSI feedback improvement" shown in FIG. 8, a data collection unit A1, a model learning unit A2, and a model inference unit A3 are included in the control unit 130 of the UE 100. On the other hand, a data processing unit A4 is included in the control unit 230 of the gNB 200. That is, model learning and model inference are performed in the UE 100. FIG. 8 shows an example in which the transmitting entity TE is the UE 100 and the receiving entity RE is the gNB 200.

[0056] In "CSI feedback improvement", the gNB 200 transmits a reference signal for the UE 100 to estimate the downlink channel state. As the reference signal, a CSI reference signal (CSI-RS) will be described as an example below, but the reference signal may be a demodulation reference signal (DMRS).

[0057] First, in model learning, UE100 (receiving unit 110) receives a first reference signal from gNB200 using a first resource. Then, UE100 (model learning unit A2) derives a learned model for inferring CSI from the reference signal using learning data including the first reference signal and CSI. Such a first reference signal is sometimes referred to as a full CSI-RS.

[0058] For example, the CSI generation unit 131 performs channel estimation using the received signal (CSI-RS) received by the receiving unit 110 to generate CSI. The transmitting unit 120 transmits the generated CSI to the gNB 200. The model learning unit A2 performs model learning using a set of the received signal (CSI-RS) and the CSI as learning data, and derives a learned model for inferring the CSI from the received signal (CSI-RS).

[0059] Second, in model inference, the receiver 110 receives a second reference signal from the gNB 200 using a second resource that is less than the first resource. Then, the model inference unit A3 uses the trained model to infer CSI as inference result data using the second reference signal as inference data. Hereinafter, such a second reference signal may be referred to as a partial CSI-RS or a punctured CSI-RS.

[0060] For example, the model inference unit A3 inputs the partial CSI-RS received by the receiving unit 110 as inference data into the trained model, and infers CSI from the CSI-RS. The transmitting unit 120 transmits the inferred CSI to the gNB 200.

[0061] This enables UE 100 to feed back (or transmit) accurate (complete) CSI to gNB 200 from the small amount of CSI-RS (partial CSI-RS) received from gNB 200. For example, gNB 200 can reduce (puncture) CSI-RS when intended to reduce overhead. In addition, UE 100 can respond to situations where the radio conditions deteriorate and some CSI-RS cannot be received normally.

[0062] 9 and 10 are diagrams illustrating an example of reducing CSI-RS according to the first embodiment.

[0063] FIG. 9 shows an example of reducing CSI-RS by reducing the number of antenna ports that transmit CSI-RS. For example, the gNB 200 performs the following process. That is, when the UE 100 is in a mode in which model learning is performed (hereinafter, sometimes referred to as the "learning mode"), the gNB 200 transmits CSI-RS from all antenna ports of the antenna panel. On the other hand, when the UE 100 is in a mode in which model inference is performed (hereinafter, sometimes referred to as the "inference mode"), the gNB 200 reduces the number of antenna ports that transmit CSI-RS and transmits CSI-RS from half the antenna ports of the antenna panel. This reduces overhead, improves antenna port utilization efficiency, and achieves a reduction in power consumption. Note that the antenna port is an example of a resource.

[0064] On the other hand, FIG. 10 shows an example in which the radio resources used for transmitting the CSI-RS, specifically, the gNB 200, reduces the time-frequency resources. For example, the gNB 200 performs the following process. That is, when the UE 100 is in learning mode, the gNB 200 transmits the CSI-RS using predetermined time-frequency resources. On the other hand, when the UE 100 is in inference mode, the gNB 200 transmits the CSI-RS using time-frequency resources that are less than the predetermined time-frequency resources. This reduces overhead, improves the utilization efficiency of radio resources, and reduces power consumption.

[0065] As shown in Figures 9 and 10, gNB200 transmits full CSI-RS using a predetermined amount of first resources and transmits partial CSI-RS using second resources that have a smaller amount of resources than the first resources.

[0066] FIG. 11 is a diagram illustrating an example of operation in "CSI feedback improvement" according to the first embodiment.

[0067] 11, in step S101, the gNB 200 may notify or set the transmission pattern (puncture pattern) of the CSI-RS in the inference mode as control data to the UE 100. For example, the gNB 200 transmits to the UE 100 the antenna port and / or time-frequency resource that transmits or does not transmit the CSI-RS in the inference mode.

[0068] In step S102, gNB200 may send a switching notification to UE100 to start learning mode.

[0069] In step S103, the UE 100 starts the learning mode.

[0070] In step S104, the gNB 200 transmits the full CSI-RS. The receiver 110 of the UE 100 receives the full CSI-RS, and the CSI generator 131 generates (or estimates) CSI based on the full CSI-RS. In the learning mode, the data collector A1 collects the full CSI-RS and CSI. The model learning unit A2 creates a learned model using the full CSI-RS and the CSI as learning data.

[0071] In step S105, UE100 transmits the generated CSI to gNB200.

[0072] Thereafter, in step S106, when the model learning is completed, the UE 100 transmits a completion notification indicating that the model learning is completed to the gNB 200. The UE 100 may transmit a completion notification when the creation of the learned model is completed.

[0073] In step S107, in response to receiving the completion notification, gNB200 sends a switching notification to UE100 to switch UE100 from learning mode to inference mode.

[0074] In step S108, in response to receiving the switching notification, the UE 100 switches from the learning mode to the inference mode.

[0075] In step S109, the gNB 200 transmits a partial CSI-RS. The receiver 110 of the UE 100 receives the partial CSI-RS. In the inference mode, the data collector A1 collects the partial CSI-RS. The model inference unit A3 inputs the partial CSI-RS as inference data into the trained model, and obtains CSI as the inference result.

[0076] In step S110, the UE 100 feeds back (or transmits) the CSI, which is the inference result, to the gNB 200 as inference result data. In the UE 100, by repeating model learning in the learning mode, a trained model with a predetermined accuracy or higher can be generated. It is expected that the inference result using the trained model generated in this way will also have a predetermined accuracy or higher.

[0077] In addition, in step S111, if UE100 determines that model learning is necessary, it may send a notification indicating that model learning is necessary to gNB200 as control data.

[0078] In the example shown in Fig. 11, an example has been described in which the training data is "(full) CSI-RS" and "CSI", and the inference data is "(partial) CSI-RS". Hereinafter, the training data and / or the inference data may be referred to as a "dataset".

[0079] In "improving CSI feedback," in addition to "CSI-RS" and "CSI," at least one of the following data or information may be used as a data set:

[0080] (X1) RSRP (Reference Signals Received Power), RSRQ (Reference Signal Received Quality), SINR (Signal-to-interference-plus-noise ratio), or AD converter output waveform (These measurements may be CSI-RS. These measurements may also be other received signals received from the gNB 200.)

[0081] (X2) Bit Error Rate (BER) or Block Error Rate (BLER) (The total number of transmitted bits (or the total number of transmitted blocks) is known, and the BER (or BLER) may be measured based on the CSI-RS.)

[0082] (X3) The movement speed of UE100 (which may be measured by a speed sensor within UE100). The data set to be used for machine learning may be set. For example, the following processing may be performed. That is, UE100 transmits capability information indicating which type of input data it can handle in machine learning to gNB200 as control data. The capability information may represent, for example, any of the data or information shown in (X1) to (X3). The capability information may be information in which learning data and inference data are separately specified. Then, gNB200 transmits data type information to be used as the data set to UE100 as control data. The data type information may represent, for example, any of the data or information shown in (X1) to (X3). Furthermore, the data type information may specify separately data type information to be used as learning data and data type information to be used as inference data.

[0083] (1.2) Example of functional block arrangement in "beam management" Next, an example of functional block arrangement in "beam management" will be described. "Beam management" represents a use case in which, for example, machine learning technology is used to manage which beam is the optimal beam among the beams transmitted from gNB200.

[0084] In "beam management," gNB200 sequentially transmits beams with different directivities. Each beam includes, for example, a reference signal. UE100 measures the reception quality of each beam using the reference signal included in each beam. UE100, for example, determines the beam with the best reception quality as the optimal beam.

[0085] Figure 12 is a diagram showing an example of the arrangement of each functional block in "beam management". In the example of "beam management" shown in Figure 12, a data collection unit A1, a model learning unit A2, and a model inference unit A3 are included in the control unit 130 of UE100. On the other hand, a data processing unit A4 is included in the control unit 230 of gNB200. That is, Figure 12 shows an example in which model learning and model inference are performed in UE100. Figure 12 shows an example in which the transmitting entity TE is UE100 and the receiving entity RE is gNB200.

[0086] As shown in FIG. 12, the UE 100 has an optimal beam determination unit 132. The optimal beam determination unit 132 determines the optimal beam based on, for example, the reception quality for the reference signal included in each beam. As with "CSI feedback," an example will be described in which a CSI-RS is used as the reference signal, but a demodulation reference signal (DMRS) may also be used as the reference signal. The transmitter 120 transmits information representing the determined optimal beam to the gNB 200 as the "optimal beam."

[0087] An example of the operation in "beam management" can be implemented by replacing "CSI feedback" with "optimal beam" in Figure 11.

[0088] In the learning mode (step S103), the gNB 200 sequentially transmits beams with different directivities to the UE 100 (step S104). Each beam includes a full CSI-RS. In the learning mode, the data collection unit A1 of the UE 100 collects the full CSI-RS and the optimal beam (information representing the optimal beam). The model learning unit A2 creates a learned model using the CSI-RS and the optimal beam (information representing the optimal beam) as learning data. The full CSI-RS is an example of a first reference signal, and the partial CSI-RS is an example of a second reference signal.

[0089] In the inference mode (step S108), the gNB 200 sequentially transmits beams with different directivities. Each beam includes a partial CSI-RS. In the inference mode, the data collection unit A1 collects the partial CSI-RS. The model inference unit A3 inputs the partial CSI-RS as inference data into the trained model, and obtains the optimal beam (information representing the optimal beam) as the inference result. The UE 100 transmits the inference result (optimal beam) to the gNB 200 as inference result data.

[0090] In "beam management," in addition to "CSI-RS" and "optimal beam," at least one of the following data or information may be used as data in the data set.

[0091] (Y1) SSB (Synchronization Signal Block) received from gNB200

[0092] (Y2) RSRP, RSRQ, SINR, or AD converter output waveform (these measurements may be CSI-RS. These measurements may also be other received signals received from gNB200)

[0093] (Y3) BER or BLER (BER (or BLER) may be measured based on CSI-RS with the total number of transmission bits (or the total number of transmission blocks) known.)

[0094] (Y4) Number of beams or beam pattern

[0095] (Y5) Beam measurement value(s)

[0096] (Y6) UE100's movement speed (may be measured by a speed sensor within UE100) UE100 may transmit capability information indicating which type of input data it can handle in machine learning to gNB200 as control data. The capability information may include any of the information or data from (Y1) to (Y6). The capability information may include any of the information or data from (Y1) to (Y6), separating the learning data and the inference data. In addition, gNB200 may transmit data type information used as a data set to UE100 as control data. The data type information may include, for example, any of the data or information shown in (Y1) to (Y6). The data type information may include any of the information or data from (Y1) to (Y6), separating the learning data and the inference data.

[0097] (1.3) Example of Arrangement of Functional Blocks in "Improvement of Location Accuracy" Next, an example of arrangement of functional blocks in "Improvement of Location Accuracy" will be described. "Improvement of Location Accuracy" represents a use case in which, for example, the accuracy of location information measured by the UE 100 is improved by using machine learning technology.

[0098] Figure 13 is a diagram showing an example of the arrangement of each functional block in "improving location accuracy". In the example of "improving location accuracy" shown in Figure 9, the data collection unit A1, model learning unit A2, and model inference unit A3 are included in the control unit 130 of the UE 100. On the other hand, the data processing unit A4 is included in the control unit 230 of the gNB 200. That is, Figure 13 shows an example in which model learning and model inference are performed in the UE 100. Figure 13 shows an example in which the transmitting entity TE is the UE 100 and the receiving entity RE is the gNB 200.

[0099] As shown in FIG. 13 , the UE 100 includes a location information generation unit 133. The UE 100 may include a GNSS (Global Navigation Satellite System) receiver 150. The location information generation unit 133 generates location data for the UE 100 based on a positioning reference signal (PRS) (full PRS or partial PRS) received from the gNB 200. The location information generation unit 133 may receive a GNSS signal (full GNSS signal or partial GNSS signal) received by the GNSS receiver 150, and generate location data for the UE 100 based on the GNSS signal.

[0100] Note that the gNB 200 transmits the full PRS using a predetermined amount of first resources (for example, all antenna ports as shown in FIG. 9, or a predetermined amount of time-frequency resources as shown in FIG. 10), similar to the full CSI-RS. Also, the gNB 200 transmits the partial PRS using second resources (for example, half the antenna ports in the antenna panel as shown in FIG. 9, or half the predetermined amount of time-frequency resources as shown in FIG. 10) that have a smaller amount of resources than the first resources, similar to the partial CSI-RS.

[0101] The full GNSS signal may also be a GNSS signal that is received continuously over time by the GNSS receiver 150. Furthermore, the partial GNSS signal may also be a GNSS signal that is received intermittently by the GNSS receiver 150. That is, a predetermined amount of first resources may be used for the full GNSS signal, and second resources having a smaller amount than the first resources may be used for the partial GNSS signal.

[0102] An example of the operation for "improving location accuracy" can be implemented by replacing "full CSI-RS" with "full PRS," "partial CSI-RS" with "partial PRS," and "CSI feedback" with "location data" in Figure 11.

[0103] In the learning mode (step S103), the location information generation unit 133 generates location data for the UE 100 based on the full PRS received from the gNB 200. The location information generation unit 133 may receive a full GNSS signal received by the GNSS receiver 150 and generate location data for the UE 100 based on the full GNSS signal. The transmission unit 120 feeds back (or transmits) the location data to the gNB 200. The data collection unit A1 collects the full PRS (or full GNSS signal) and location data. The model learning unit A2 creates a learned model using the full PRS (or full GNSS signal) and location data as learning data.

[0104] In the inference mode (step S108), the data collection unit A1 collects the partial PRS received by the receiving unit 110 (or the partial GNSS signal received by the GNSS receiver 150). The model inference unit A3 inputs the partial PRS (or the partial GNSS signal) as inference data into the trained model, and obtains location data as an inference result. The UE 100 transmits the inference result (location data) to the gNB 200 as inference result data.

[0105] In "improving position accuracy," in addition to "PRS" (or "GNSS signal") and "position data," at least one of the following data or information may be used in the data set:

[0106] (Z1) RSRP, RSRQ, SINR (Signal-to-interference-plus-noise ratio), or AD converter output waveform (these measurements may be PRS. These measurements may also be other received signals received from gNB200.)

[0107] (Z2) LOS (Line of Sight) or NLOS (Non Line of Sight)

[0108] (Z3) Measurement timing, accuracy, likelihood

[0109] (Z4) RF Fingerprint (Cell ID and reception quality in the cell of the cell ID)

[0110] (Z5) Angle of Arrival (AOA), reception level for each antenna, reception phase for each antenna, and observed time difference of arrival (OTDOA) for each antenna

[0111] (Z6) Received information of beacons used in wireless LANs (Local Area Networks) such as Wi-Fi (registered trademark) or short-range wireless communications such as Bluetooth (registered trademark)

[0112] (Z7) Movement speed of UE100 (The movement speed may be measured by the GNSS receiver 150. The movement speed may be measured by a speed sensor within UE100.) UE100 may transmit capability information indicating which type of input data it can handle in machine learning as control data to gNB200. The capability information may include any of the information or data from (Z1) to (Z7). The capability information may include any of the information or data from (Z1) to (Z7), separating the learning data and the inference data. In addition, gNB200 may transmit data type information to be used as a data set as control data to UE100. The data type information may include, for example, any of the data or information shown in (Z1) to (Z7). The data type information may include any of the information or data from (Z1) to (Z7), separating the learning data and the inference data.

[0113] (1.4) Other Arrangement Examples Next, other arrangement examples will be described.

[0114] Figure 14 is a diagram showing another example of the arrangement of "CSI feedback improvement" according to the first embodiment. Figure 14 shows an example in which a data collection unit A1, a model learning unit A2, a model inference unit A3, and a data processing unit A4 are included in a gN200. That is, Figure 14 shows an example in which model learning and model inference are performed in the gNB200. Figure 14 shows an example in which the transmitting entity TE is the gNB200 and the receiving entity RE is the UE100.

[0115] 14 shows an example in which AI / ML technology is introduced into CSI estimation performed by gNB200 based on SRS (Sounding Reference Signal). Therefore, gNB200 has a CSI generation unit 231 that generates CSI based on SRS. The CSI is information indicating the channel state of the uplink between UE100 and gNB200. gNB200 (e.g., data processing unit A4) performs, for example, uplink scheduling based on the CSI generated based on SRS.

[0116] FIG. 15 is a diagram illustrating an example of operation in another arrangement example according to the first embodiment.

[0117] 15 , in step S201, the gNB 200 performs SRS transmission configuration for the UE 100. The SRS transmission configuration may include type information of the reference signal transmitted by the UE 100.

[0118] In step S202, gNB200 starts learning mode.

[0119] In step S203, UE100 transmits the full SRS to gNB200 according to the SRS transmission setting (step S201). The receiver 220 of gNB200 receives the full SRS. In the learning mode, the CSI generator 231 generates (or estimates) CSI based on the full SRS. The data collector A1 collects the full SRS and CSI. The model learning unit A2 creates a learned model using the full SRS and CSI as learning data.

[0120] In step S204, the gNB 200 identifies an SRS transmission pattern (puncture pattern) to be input to the learned model as inference data, and sets the identified SRS transmission pattern to the UE 100. The gNB 200 may transmit an SRS transmission configuration including the identified SRS transmission pattern to the gNB 200.

[0121] In step S205, gNB200 switches from learning mode to inference mode. gNB200 starts model inference using the trained model.

[0122] In step S206, UE100 transmits a partial SRS in accordance with the SRS transmission setting (step S204). When gNB200 inputs the SRS as inference data into the trained model to obtain a channel estimation result, it uses the channel estimation result to perform uplink scheduling of UE100 (for example, control of uplink transmission weight, etc.). Note that if the inference accuracy using the trained model deteriorates, gNB200 may reconfigure UE100 to transmit a full SRS.

[0123] (1.5) Example of Arrangement When Federated Learning is Performed Next, an example of the arrangement of each functional block when federated learning is performed will be described. Federated learning is, for example, a machine learning technique in which machine learning is performed in a distributed state without aggregating data (or data sets). In federated learning, each entity does not need to transmit data, so the security of each entity can be ensured. Furthermore, federated learning is said to be able to obtain learning results with the same accuracy as conventional centralized machine learning.

[0124] Figure 16 is a diagram showing an example of a configuration when federated learning according to the first embodiment is performed. The example shown in Figure 16 shows an example where location estimation of UE100 is performed using federated learning. Figure 16 shows an example where UE100 has a data collection unit A1, a model learning unit A2, and a model inference unit A3. That is, it shows an example where model learning and model inference are performed in UE100. Figure 16 shows an example where UE100 is the transmitting entity TE, and gNB200 and / or location server 400 is the receiving entity RE.

[0125] The associative learning shown in FIG. 16 is performed, for example, in the following procedure.

[0126] First, the location server 400 transmits to the UE 100 a model that is the basis for model learning.

[0127] Second, UE 100 (model learning unit A2) performs model learning using data present in UE 100. The data present in UE 100 is, for example, the PRS received from gNB 200 and / or output data (GNSS signal) of GNSS receiver 150. The data present in UE 100 may include location data generated by location information generation unit 133 based on the reception result of the PRS and / or the output data of GNSS receiver 150.

[0128] Third, UE 100 applies the learned model, which is the learning result, in model inference unit A3, and transmits variable parameters (hereinafter, sometimes referred to as "learned parameters") included in the learned model to location server 400. In the above example, the optimized a (slope) and b (intercept) correspond to the learned parameters.

[0129] Fourth, location server 400 (associated learning unit A5) collects learned parameters from multiple UEs 100 and integrates them. Location server 400 may transmit the learned model obtained by the integration to UE 100. Location server 400 can estimate the location of UE 100 based on the learned model and measurement reports from UE 100.

[0130] FIG. 17 is a diagram illustrating an example of operation in the federated learning according to the first embodiment.

[0131] 17, in step S301, the gNB 200 may notify the UE 100 of a model that serves as a basis for learning. The location server 400 may notify the model via the gNB 200.

[0132] In step S302, the gNB 200 instructs the UE 100 to learn the model. The gNB 200 may set the reporting timing (trigger condition) of the learned parameters. The reporting timing may be periodic. The reporting timing may be triggered by the learning proficiency satisfying the condition (i.e., an event trigger).

[0133] In step S303, the UE 100 starts a learning mode. The UE 100 performs model learning using the full PRS (or full GNSS signal) and the position data generated by the position information generating unit 133 as learning data.

[0134] In step S304, when the reporting timing condition is met, UE100 transmits the learned parameters at that time to the network (gNB200 or location server 400).

[0135] In step S305, the location server 400 integrates the learned parameters reported from the plurality of UEs 100.

[0136] (1.6) Model transfer example

[0137] In (1.1) to (1.5), examples of the arrangement of each functional block of AI / ML technology have been described. Below, an example of model transfer will be described. The model to be transferred may be a trained model used in model inference. The model may also be an untrained (or training) model used in model training.

[0138] (1.6.1) First operation pattern related to model forwarding Figure 18 is a diagram showing an example of an operation of the first operation pattern related to model forwarding according to the first embodiment. In the example shown in Figure 18, the description will be given assuming that the receiving entity RE is mainly the UE 100, but the receiving entity RE may be the gNB 200 or the AMF 300. Also, in the example shown in Figure 18, the description will be given assuming that the transmitting entity TE is the gNB 200, but the transmitting entity TE may be the UE 100 or the AMF 300.

[0139] 18, in step S401, the gNB 200 transmits a capability inquiry message to the UE 100 to request transmission of a message including an information element (IE) indicating execution capability for machine learning processing. The UE 100 receives the capability inquiry message. However, the gNB 200 may transmit the capability inquiry message when executing the machine learning processing (when determining that the processing is to be executed).

[0140] In step S402, the UE 100 transmits to the gNB 200 a message including an information element indicating execution capability for machine learning processing (or, from another perspective, the execution environment for machine learning processing). The gNB 200 receives the message. The message may be an RRC message (for example, a "UE Capability" message or a newly defined message (for example, a "UE AI Capability" message, etc.)). Alternatively, the transmitting entity TE may be the AMF 300, and the message may be a NAS message. Alternatively, if a new layer for performing or controlling machine learning processing (AI / ML processing) is defined, the message may be a message of the new layer.

[0141] The information element indicating the execution capability related to the machine learning process may be an information element indicating the capability of a processor for executing the machine learning process and / or an information element indicating the capability of a memory for executing the machine learning process. Specifically, the information element indicating the processor capability may be an information element indicating the product number (or model number) of the AI ​​processor. Specifically, the information element indicating the memory capability may be information indicating the memory capacity.

[0142] Alternatively, the information element indicating the execution capability of machine learning processing may be an information element indicating the execution capability of inference processing (model inference). Specifically, the information element indicating the execution capability of inference processing may be an information element indicating whether a deep neural network model is supported. The information element may also be an information element indicating the time (or response time) required to execute the inference processing.

[0143] Alternatively, the information element indicating the execution capability related to the machine learning process may be an information element indicating the execution capability of the learning process (model learning). Specifically, the information element indicating the execution capability of the learning process may be an information element indicating the number of concurrent executions of the learning process. The information element may be an information element indicating the processing capacity of the learning process.

[0144] In step S403, gNB200 determines the model to be configured (or deployed) in UE100 based on the information elements contained in the message received in step S402.

[0145] In step S404, gNB200 transmits a message including the model determined in step S403 to UE100. UE100 receives the message and performs machine learning processing (i.e., model learning processing and / or model inference processing) using the model included in the message. A specific example of step S404 will be described in the following second operation pattern.

[0146] (1.6.2) Second operation pattern related to model transfer FIG. 19 is a diagram showing an example of a configuration message including a model and additional information according to the first embodiment. The configuration message may be an RRC message transmitted from the gNB 200 to the UE 100 (for example, an "RRC Reconfiguration" message, or a newly defined message (for example, an "AI Deployment" message or an "AI Reconfiguration" message, etc.). Alternatively, the configuration message may be a NAS message transmitted from the AMF 300 to the UE 100. Alternatively, when a new layer for performing or controlling machine learning processing (AI / ML processing) is defined, the message may be a message of the new layer.

[0147] In the example of FIG. 19, the setting message includes three models (Model #1 to #3). Each model is included as a container in the setting message. However, the setting message may include only one model. The setting message further includes, as additional information, three individual additional information (Info #1 to #3) provided individually corresponding to each of the three models (Model #1 to #3), and common additional information (Meta-Info) commonly associated with the three models (Model #1 to #3). Each of the individual additional information (Info #1 to #3) includes information unique to the corresponding model. The common additional information (Meta-Info) includes information common to all models in the setting message.

[0148] The individual additional information may be a model index indicating an index (index number) assigned to each model, or may be a model execution condition indicating the performance (e.g., processing delay) required to apply (execute) the model.

[0149] The individual additional information or the common additional information may be a model usage that specifies a function to which a model is to be applied (e.g., "CSI feedback," "beam management," "positioning," etc.). The individual additional information or the common additional information may be a model selection criterion that applies (executes) a corresponding model depending on whether a specified criterion (e.g., a moving speed) is satisfied.

[0150] (1.7) Communication Control Method According to First Embodiment Next, a description will be given of a communication control method according to First Embodiment. As mentioned above, Non-Patent Document 1 discusses that when an AI algorithm is applied to DRX to perform a simulation to predict the next traffic burst, it was possible to significantly reduce delay while maintaining the same power consumption as a conventional DRX configuration.

[0151] However, Non-Patent Document 1 assumes that DRX operation is performed so that the prediction result by the AI ​​algorithm matches the next traffic burst, but does not specifically show how to perform DRX operation. Also, Non-Patent Document 2 also discusses identifying high-layer use cases to which the AI / ML model is applied, but does not specifically discuss how to apply the AI ​​algorithm to DRX operation.

[0152] Therefore, the first embodiment aims to enable the mobile communication system 1 to appropriately perform DRX using the AI / ML model.

[0153] (1.7.1) DRX Here, the DRX according to the first embodiment will be described.

[0154] DRX is, for example, a technique for discontinuously monitoring the PDCCH for the UE 100. The UE 100 (its MAC entity) configured for DRX applies DRX operation to the active serving cell to discontinuously monitor the PDCCH. That is, the UE 100 configured for DRX turns off its wireless communication function, for example, in "sleep" mode, and monitors the PDCCH in "wake-up" mode. The periodic repetition of "sleep" mode and "wake-up" mode is sometimes referred to as DRX. In DRX, there is a period during which the UE 100 is in "sleep" mode, and therefore, the power consumption of the UE 100 can be reduced compared to when the UE 100 constantly monitors the PDCCH.

[0155] In order to perform DRX operation for UE 100, gNB 200 notifies UE 100 of the DRX setting (DRX-Config). gNB 200 notifies UE 100 of the DRX setting by sending an RRC message (e.g., an RRCReconfiguration message, an RRCResume message, or an RRCSetup message) including the DRX setting to UE 100.

[0156] The DRX settings include the "on-duration" ("drx-onDurationTimer") in DRX, the "DRX cycle" ("drx-LongCycleStartOffset") representing one period in DRX, the "delay time" ("drx-SlotOffset") before the start of "drx-onDurationTimer", and the "inactivity timer" ("drx-InactivityTimer") representing the duration for a new DL transmission (or UL transmission) after receiving a PDCCH.

[0157] 20(A) and 20(B) are diagrams showing examples of a DRX cycle according to the first embodiment. In the UE 100, a DRX cycle and a DRX on-duration are set by the DRX setting. The UE 100 enters a wake-up mode during the on-duration and monitors the PDCCH. On the other hand, the UE 100 enters a sleep mode during periods other than the on-duration and turns off some of the functions without monitoring the PDCCH. In the wake-up mode, the UE 100 can transmit SRS or feedback information in addition to monitoring the PDCCH.

[0158] Note that, when the UE 100 receives a DRX command (DRX Command MAC CE, which is a MAC Control Element (CE)) during the on period, the UE 100 stops (or ends) the “on period” and does not monitor the PDCCH.

[0159] The above-described DRX setting basically represents the setting of a long DRX cycle. In the DRX setting, a short DRX cycle shorter than the long DRX cycle can be set as an option. That is, as the DRX setting, a "short DRX cycle" ("drx-ShortCycle") and a "duration" ("drx-ShortCycleTimer") for which the UE 100 continues the short DRX cycle can be set. This makes it possible to set a "short DRX cycle" during the off period of the long DRX setting.

[0160] Further, the above-mentioned DRX control has been described using as an example a connected mode DRX (C-DRX) in which the UE 100 performs DRX operation when in an RRC connected state. There is also an idle mode DRX (I-DRX) in which the UE 100 performs DRX operation when in an RRC idle state or an RRC inactive state. In this case, the UE 100 and the gNB 200 use the UE 100 identifier (IMSI: International Mobile Subscriber Identity, or 5G-S-TMSI (Temporary Mobile Subscriber Identity), etc.) to calculate a paging occasion (PO), which is a subframe in which a paging message is transmitted, and a paging frame (PF), which is a radio frame including the PO. The gNB 200 transmits a paging message in a periodic PF, allowing the UE 100 to receive the paging message. In the embodiments described below, C-DRX is mainly used as an example, but unless otherwise specified, it may also be applied to I-DRX.

[0161] The above is a description of DRX.

[0162] Existing DRX control has the following problems, for example. That is, if there is no DL data (data in the downlink) when the UE 100 is awake, the wake-up is wasted from the viewpoint of the power consumption of the UE 100. Also, if the timing at which the DL data is input to the gNB 200 does not match the on-period of the DL data, the UE 100 will wait until the next on-period to receive the DL data, and this waiting time becomes latency. It is desirable that DRX control using the AI / ML model will also solve such problems of power consumption and latency.

[0163] (1.7.2) Terminology Next, the terms used in the embodiment will be explained.

[0164] Hereinafter, the DRX on-duration may be simply referred to as an “on-duration.” The “on-duration” may also be referred to as a transmission opportunity for DL ​​data (data in the downlink).

[0165] Furthermore, the "wake-up mode" may be simply referred to as "wake-up." When DRX setting is performed, the UE 100 basically "wakes up" during the on period and monitors the PDCCH, etc. "Wake-up" may mean turning on the receiver. Alternatively, "wake-up" may mean monitoring the PDCCH.

[0166] Furthermore, the "sleep mode" may be simply referred to as "sleep."

[0167] Furthermore, an "AI / ML model" may refer to a data-driven algorithm that generates a series of outputs consisting of prediction information and / or parameters based on a series of inputs, for example, by applying machine learning techniques. An "AI / ML model" may also be a "trained algorithm" that inputs inference data and outputs inference result data. Hereinafter, the terms "AI / ML model" and "trained model" may be used interchangeably. An "AI / ML" model may also be referred to as an "inference model." An "inference model" may also be a "trained model."

[0168] (1.7.3) First Operation Example According to First Embodiment Next, a first operation example according to the first embodiment will be described.

[0169] In the first operation example, UE100 uses the AI / ML model to infer whether DL data traffic will occur in the next on-period, and based on the inference result, either wakes up or skips waking up in the next on-period.

[0170] Specifically, first, the user equipment (e.g., UE 100) uses the AI / ML model to infer whether or not downlink data traffic will occur in the next DRX on-duration. Second, the user equipment either wakes up in the next DRX on-duration or skips wake-up in the next DRX on-duration based on the inference result of whether or not data traffic will occur.

[0171] In this way, when UE 100 infers that no DL data traffic will occur during the on-period, it skips waking up during the on-period. On the other hand, when UE 100 infers that DL data traffic will occur during the on-period, it performs a wake-up operation during the on-period. As a result, for example, UE 100 can perform a DRX operation that reflects the inference result using the AI / ML model, and can perform DRX appropriately using the AI / ML model. Furthermore, since UE 100 may skip waking up during the on-period, it is possible to reduce the power consumption of UE 100 compared to when UE 100 always wakes up during the on-period.

[0172] In the first operation example, the UE 100 has an AI / ML model, and model inference using the AI / ML model is performed in the UE 100. The first operation example represents an example of a "UE-side one-sided model" in which the AI / ML model exists on the UE 100 side.

[0173] FIG. 21 is a diagram illustrating a first operation example according to the first embodiment.

[0174] As shown in FIG. 21 , in step S501, the UE 100 may notify the gNB 200 that it has the capability of wake-up skip. The UE 100 may perform the notification by transmitting an RRC message (for example, a UE capability message) including information indicating the presence or absence of the capability. "Wake-up skip" may represent skipping an on-duration ("on-duration skip"). The notification may mean that the UE 100 has AI-based DRX capability. Alternatively, the notification may mean that the UE 100 has an inference model (or a learned model) for DRX optimization.

[0175] In step S502, the gNB 200 performs DRX configuration for the UE 100. Specifically, the gNB 200 may perform the configuration by transmitting an RRC message (e.g., an RRC Reconfiguration message) including the DRX configuration to the UE 100. The DRX configuration may include various existing information elements (IEs) such as "drx-onDurationTimer". The DRX configuration may include permission information that permits the UE 100 to skip wake-up during the on period. With the permission information, the gNB 200 configures the UE 100 to permit the UE 100 to skip wake-up during the on period, thereby permitting the UE 100 to exercise discretion in skipping. The permission information may be notified to the UE 100 using a MAC CE or DCI (step S503). The permission information may be information that does not permit wake-up skipping, instead of information that permits wake-up skipping. The permission information may be information that indicates either that wake-up skipping is permitted or that wake-up skipping is not permitted. The permission information may be set for each model. The permission information may also be set for all models.

[0176] In step S504, the UE 100 identifies a DRX cycle and an on-duration in the DRX cycle based on the DRX setting.

[0177] In step S505, UE 100 performs model inference using the inference model to infer whether DL data traffic will occur in the next on-period.

[0178] First, the UE 100 selects an inference model associated with a currently running application. When data communication or RRC signaling is used for the application, the UE 100 may select an inference model based on the data communication or the RRC signaling. A plurality of inference models may be selected. In this case, the UE 100 may execute a plurality of inference models in parallel (or simultaneously). The UE 100 may infer whether DL data traffic is generated or not based on inference results of a plurality of inference models.

[0179] Second, the inference data input to the inference model of UE 100 and the inference result data output from the inference model are, for example, as follows: That is, the inference data is information indicating whether DL data has occurred in the current on-period (or whether UE 100 has received DL data). The inference data may be information indicating whether DL data has occurred in a past on-period. When the MAC layer of UE 100 receives information regarding traffic characteristics from a higher layer (e.g., an application layer), the information may be used as inference data. On the other hand, the inference result data is information indicating whether DL data traffic will occur in the next on-period. The wake-up determination result (whether to wake up or to skip a wake-up), which will be described later, may also be used as inference result data. Note that in the first operation example, the occurrence of DL data traffic is inferred using the AI / ML model. However, instead of the AI / ML model, DL data traffic may be inferred using a method other than the AI / ML model, such as statistical processing of past data.

[0180] Third, the UE 100 performs a wake-up determination. Specifically, the UE 100 performs either waking up in the next on-duration or skipping the wake-up in the next on-duration based on the inference result of whether or not DL data traffic is generated.

[0181] When the UE 100 infers that DL data traffic will occur, the UE 100 wakes up during the next on-period. When the UE 100 selects multiple inference models, the UE 100 may determine to wake up when the logical sum of the inference results of each inference model is true. That is, the UE 100 may determine to wake up when it obtains an inference result that DL data traffic will occur in at least one inference model.

[0182] On the other hand, if UE 100 infers that no DL data traffic will occur, it skips wake-up in the next on-duration. When multiple inference models are selected, UE 100 may determine to skip wake-up if the logical sum of the inference results of each inference model is false. That is, UE 100 may determine to skip wake-up if an inference result indicating that no DL traffic will occur is obtained in all inference models. The wake-up skip may be to continue sleeping. Alternatively, the wake-up skip may be to either turn off the receiver or not turn on the receiver. Alternatively, the wake-up skip may be to skip monitoring the PDCCH. The wake-up skip may be to not monitor the PDCCH. The wake-up skip may cause UE 100 to enter sleep mode.

[0183] Fourth, the UE 100 may adjust the wake-up period according to the probability of occurrence of DL data traffic. For example, the UE 100 calculates the probability of occurrence of DL data in the on-period, and if the occurrence probability is lower than a threshold, the UE 100 wakes up for a period shorter than the on-period. If the occurrence probability is equal to or greater than a threshold, the UE 100 wakes up for a period longer than the on-period. The threshold may be set by the gNB 200.

[0184] In step S506, the UE 100 wakes up or skips waking up in the next on-period according to the result of the wake-up determination. Ideally, the UE 100 wakes up when DL data traffic occurs. Therefore, compared with the case where the UE 100 always wakes up in the on-period, the power consumption of the UE 100 can be reduced and the DRX effect in the standby state can be maximized.

[0185] 20(C) is a diagram showing a series of steps in the wake-up determination process according to the first embodiment. As shown in FIG. 20(C), the UE 100 performs model inference and determines to skip wake-up during the next on-period based on the inference result. The UE 100 also determines to skip wake-up during the next on-period. The UE 100 subsequently repeats this process, using the inference model to obtain an inference result regarding whether DL data traffic is occurring, and then makes a wake-up determination during the next on-period based on the inference result.

[0186] (1.7.4) Another Example of the First Operation Example According to the First Embodiment Next, another example of the first operation example according to the first embodiment will be described.

[0187] In the first operation example, the UE 100 skips wake-up. In this case, for example, the UE 100 skips wake-up, but does not know whether DL data really did not exist (or whether DL data existed). On the other hand, the gNB 200 can determine whether DL data was transmitted but not received by the UE 100 using HARQ feedback (when there is no HARQ feedback for a certain period of time, or when a NACK is returned).

[0188] Therefore, the gNB 200 may provide the UE 100 with information indicating the presence or absence of DL data for each on-period, and the UE 100 may use this information to perform model learning. The gNB 200 may transmit timing information of the on-period (e.g., a radio frame number, a subframe number, or a slot number) and information on the presence or absence of DL data (e.g., 1-bit information) to the UE 100. The gNB 200 may also transmit information on the bearer from which the DL data has occurred (e.g., the bearer ID of the bearer) to the UE 100. The gNB 200 may transmit this information using an RRC message. The gNB 200 may transmit this information in response to a request from the UE 100. The gNB 200 may also transmit this information when it is determined that the reception status of the UE 100 is not good.

[0189] (1.8) Second Operation Example According to First Embodiment Next, a second operation example according to the first embodiment will be described. The second operation example will be described focusing on the differences from the first operation example.

[0190] In the first operation example, it has been described that the UE 100 may skip wake-up during the on-period.

[0191] Here, for example, the following case is assumed. That is, there is a case where the inference model infers that DL data traffic will not occur for a long time for some reason, such as an estimation error due to overlearning. In such a case, the UE 100 continues the wake-up skip, and communication with the gNB 200 becomes impossible for a long time. Therefore, even if DL data traffic occurs, the DL data is not transmitted to the UE 100 for a long time, and latency increases. Not only DL data, but also signaling related to control is not transmitted, and control of the UE 100 becomes impossible for a long time.

[0192] Therefore, in the second operation example, an example will be described in which the gNB 200 imposes restrictions on wake-up skipping on the UE 100. Specifically, a base station (e.g., the gNB 200) sets an operational restriction on wake-up skipping on a user device (e.g., the UE 100).

[0193] In this way, for example, an operation restriction is imposed on the wake-up skip in the UE 100, so it is possible to avoid an increase in latency due to the wake-up skip continuing for a long time, and to avoid a long-term continuation of uncontrollability of the UE 100. Furthermore, since the wake-up skip of the UE 100 is also permitted under certain conditions, the second operation example also makes it possible to reduce the power consumption of the UE 100, similar to the first operation example.

[0194] FIG. 22 is a diagram illustrating a second operation example according to the first embodiment.

[0195] As shown in Figure 22, in step S601, gNB200 performs DRX configuration for UE100. The DRX configuration includes information regarding wake-up skip operation restrictions (hereinafter, sometimes referred to as "restriction information").

[0196] First, the restriction information may be information that limits the number of consecutive wake-up skips. UE 100 counts wake-up skips using a counter, and when the number of consecutive wake-up skips reaches (or exceeds) an upper limit, the UE 100 stops performing wake-up skips regardless of the inference result of the inference model. The restriction information may be an upper limit for the number of consecutive wake-up skips. Hereinafter, a method of counting wake-up skips using a counter in this manner may be referred to as a "counter method."

[0197] Secondly, the restriction information may be information that restricts the continuous execution time of the wake-up skip. The restriction information may be a timer value that indicates the upper limit of the continuous execution time of the wake-up skip. That is, the UE 100 starts counting by a timer, and when the count value reaches the timer value (or exceeds the upper limit time, or the timer value expires), the wake-up skip is not performed regardless of the inference result by the inference model. Hereinafter, the method of counting the continuous execution time of the wake-up skip using a timer in this way may be referred to as a "timer method."

[0198] Third, the restriction information may be a recurring period during which the device must wake up. This recurring period is called a "wake-up period."

[0199] 23(A) and 23(B) are diagrams showing an example of timing according to the first embodiment. As shown in FIGS. 23(A) and 23(B), UE 100 wakes up during an on-period at the boundary of the wake-up period, regardless of the inference result of the DL data traffic by the inference model, and this is repeated for each wake-up period. Then, during on-periods other than the on-period, UE 100 wakes up or performs a wake-up skip according to the inference result by the inference model. Note that the period in which UE 100 must wake up may be the on-period next to the boundary. Alternatively, the period in which UE 100 must wake up may be any on-period within the wake-up period. The on-period is a repetitive period in which wake-up skipping is not performed.

[0200] First, the DRX setting includes information about the reference point (or start timing) of the wake-up period. The existence of the reference point (or start timing) allows the gNB 200 to identify an opportunity to transmit DL data and transmit the DL data with pinpoint accuracy.

[0201] Second, the DRX configuration may include an offset (a timing offset from the start timing) of the wake-up period.

[0202] Third, the DRX configuration may include the length of a wake-up period. The length of the wake-up period may be expressed as an absolute value (e.g., the number of slots) or as a scaled value (e.g., a multiple of the DRX cycle). The wake-up period is expressed as a period synchronized with the DRX cycle.

[0203] Fourth, the DRX configuration may include information indicating which on-duration to wake up during during the wake-up period. If the DRX configuration is to wake up during an on-duration other than the reference point, the DRX configuration may include information indicating the on-duration to wake up during.

[0204] In this way, gNB200 can set operational restrictions on skipping wake-up in UE100 through DRX settings.

[0205] 22 , in step S602, the gNB 200 may transmit permission information permitting the UE 100 to skip wake-up during the on period. The gNB 200 may include the permission information in the DRX setting (step S601), as in the first embodiment. The gNB 200 may transmit the permission information separately using the MAC CE or DCI.

[0206] In step S603, the UE 100 configures DRX according to the DRX configuration, and infers DL data traffic in the next on-duration using the inference model, as in the first embodiment. Based on the inference result, the UE 100 skips wake-up in the next on-duration.

[0207] First, in the case of the "counter method," for example, the wake-up skip operation is restricted as follows. That is, the UE 100 resets (or sets to zero (or sets a timer value)) a counter when it wakes up, and increments the count value of the counter by one each time it performs a wake-up skip. Alternatively, the UE 100 may reset the counter when it performs a wake-up skip for the first time after it wakes up, and increment the counter by one when it performs a wake-up skip in both the previous on-period and the current on-period. Alternatively, the UE 100 may reset the counter when it has successfully received DL data (for example, when it has transmitted a HARQ ACK). Then, when the counter value reaches or exceeds an upper limit value (control information), the UE 100 wakes up in the next on-period without skipping a wake-up, regardless of the inference result based on the inference model.

[0208] The above example has been described as an example of a "counting method" that counts the number of wake-up skips, but the counting target may be an on-period. That is, UE100 resets (or sets to zero (or sets the timer value)) the counter at the on-period (reference point) that is the starting point, and increments the counter by 1 at the next on-period. When the count reaches (or exceeds) the upper limit value (restriction information), UE100 wakes up without skipping a wake-up during the on-period (or the next on-period), regardless of the inference result by the inference model.

[0209] Secondly, in the case of the "timer method", for example, the operation of the wake-up skip is restricted as follows. That is, when UE 100 performs a wake-up, it resets the count value of the timer (or sets it to zero (or sets the timer value)) and starts counting by the timer. When UE 100 performs the first wake-up skip after performing a wake-up, UE 100 may start counting by the timer (or reset, or set it to zero (or set the timer value)). Alternatively, UE 100 may start counting by the timer (or reset, or set it to zero (or set the timer value)) when UE 100 has successfully received DL data (for example, when HARQ ACK has been transmitted). Then, when UE 100 performs a wake-up skip, it does not do anything to the timer, and when the count value reaches the timer value (restriction information) (or the count value exceeds the timer value, or the timer value expires), it wakes up in the next on-period without skipping wake-up, regardless of the inference result by the inference model.

[0210] In the case of the "timer method," UE 100 may also start counting by the timer (or reset, or set to zero (or set the timer value)) based on the on period (reference point) that is the starting point. In this case, UE 100 does not do anything to the timer in the next on period, and when the count value reaches the timer value (restriction information) (or the count value exceeds the timer value, or the timer value expires), UE 100 wakes up in the on period (or the next on period) without skipping wakeup.

[0211] Thirdly, in the case of the "wake-up period", for example, the operation of the wake-up skip is restricted as follows. That is, as described above, the UE 100 wakes up without performing a wake-up skip at the boundary (or any on-period) of the "wake-up period", regardless of the inference result by the inference model, and repeats this for each "wake-up period" (see Figures 23(A) and 23(B)).

[0212] In step S604, gNB200 transmits DL data at the timing of waking up. In step S605, UE100 is restricted in the wake-up skip operation, and performs the wake-up operation at the timing and receives the DL data.

[0213] In this way, in the second operation example according to the first embodiment, it is also possible to think that UE100 performs (or is permitted to perform) wake-up skip operation at certain times, and performs the same operation as existing DRX operation at other times (such as when the timing expires or during the period when it must wake up during the wake-up period).

[0214] Second Embodiment Next, a second embodiment will be described, focusing on the differences from the first embodiment.

[0215] In the first embodiment, an example in which model inference is performed in UE 100 is described. In the second embodiment, an example in which model inference is performed in gNB 200 is described. That is, an example of a "gNB side one-sided model" in which gNB 200 has an AI / ML model is described.

[0216] As in the first embodiment, the second embodiment also aims to enable appropriate DRX using an AI / ML model. In addition, in the second embodiment, since inference is performed in the gNB 200, it may also aim to correctly convey the inference result of the gNB 200 to the UE 100.

[0217] Therefore, in the second embodiment, first, a base station (e.g., gNB200) uses an AI / ML model to infer whether or not data traffic will occur in the downlink during the next DRX on period (DRX on-duration). Second, the base station, based on the inference result of whether or not data traffic will occur, transmits a first dynamic DRX instruction to the user equipment (e.g., UE100) to instruct the user equipment to either wake up during the next DRX on period or sleep during the next DRX on period.

[0218] As a result, for example, UE100 can wake up in the next on-period or sleep in the next on-period according to the first dynamic DRX instruction received from gNB200, thereby performing DRX operation that reflects the inference result of the AI / ML model in gNB200. Therefore, even in the second embodiment, DRX can be appropriately performed using the AI / ML model. Furthermore, in the second embodiment, gNB200 generates a first dynamic DRX instruction based on its own inference result and transmits the first dynamic DRX instruction to UE100, so that the inference result in gNB200 can be correctly conveyed to UE100.

[0219] In the second embodiment, the "wake-up skip" may be described as "sleep". In the UE 100, the sleep state is continued by skipping the wake-up operation. Therefore, the terms "wake-up skip" and "sleep" may be used interchangeably.

[0220] (2.1) First Operation Example According to Second Embodiment Next, a first operation example according to the second embodiment will be described.

[0221] FIG. 24 is a diagram illustrating a first operation example according to the second embodiment.

[0222] As shown in FIG. 24, in step S701, the gNB 200 performs DRX configuration for the UE 100. Specifically, the gNB 200 performs the configuration by transmitting an RRC message (e.g., an RRC Reconfiguration message) including the DRX configuration. The DRX configuration may include information indicating whether or not to receive a first dynamic DRX instruction. The DRX configuration may also include a value representing a DRX-RNTI (Radio Network Temporary Identifier). When the first dynamic DRX instruction is transmitted by DCI (e.g., new DCI), the DRX-RNTI is used in the UE 100 to decode (or descramble) the PDCCH carrying the DCI. Therefore, when gNB200 transmits the first dynamic DRX instruction using DCI, it encodes (or scrambles) the PDCCH carrying the DCI using DRX-RNTI.

[0223] In step S702, the gNB 200 uses an inference model to infer whether DL data traffic will occur in the next on-period. The input (inference data) and output (inference result data) to the inference model are the same as those in the first embodiment. Based on the inference result, the gNB 200 determines whether the UE 100 will wake up or sleep in the next on-period (wake-up determination). In response to the wake-up determination, the gNB 200 generates a first dynamic DRX instruction that instructs the UE 100 to wake up in the next on-period or to sleep in the next on-period. Specifically, if the gNB 200 infers that DL data traffic will occur in the inference model, it instructs the UE 100 to wake up in the next DRX on-period, and if it infers that DL data traffic will not occur, it generates a first dynamic DRX instruction that instructs the UE 100 to sleep in the next DRX on-period.

[0224] In step S703, gNB200 transmits a first dynamic DRX instruction to UE100 during the DRX on period. gNB200 may transmit the first dynamic DRX instruction to UE100 using DCI (or new DCI), or may transmit the first dynamic DRX instruction to UE100 using MAC CE. Alternatively, gNB200 may transmit the first dynamic DRX instruction to UE100 using an RRC message (e.g., an RRC reconfiguration message, etc.).

[0225] In step S704, the UE 100 receives a first dynamic DRX instruction during the on-period. Here, for example, it is assumed that the first dynamic DRX instruction includes an instruction to sleep during the next on-period. The first dynamic DRX instruction may include an instruction to wake up during the next on-period.

[0226] In step S705, the UE 100 performs a wake-up operation or a sleep operation in the next on-period according to the first dynamic DRX instruction. Note that, if the UE 100 does not receive the first dynamic DRX instruction, the UE 100 performs a wake-up operation in the next on-period, similar to the existing DRX operation.

[0227] 25(A) to 25(C) are diagrams illustrating an example of timing according to the second embodiment. As shown in Fig. 25(A) to 25(C), when the UE 100 receives a first dynamic DRX instruction instructing the UE 100 to sleep in the next on-period, the UE 100 performs a sleep operation in the next on-period, and when the UE 100 does not receive the first dynamic DRX instruction, the UE 100 performs a wake-up operation in the next on-period as in the existing DRX operation.

[0228] (2.2) Second Operation Example According to Second Embodiment Next, a second operation example according to the second embodiment will be described. The second operation example according to the second embodiment will be described, focusing on the differences from the first operation example according to the second embodiment.

[0229] In the first operation example according to the second embodiment, an example in which the operation for the next on-period is instructed by the first dynamic DRX instruction has been described, but this is not limited to this. For example, the gNB 200 may instruct the UE 100 to perform sleep operation not only in the next on-period but also in a plurality of on-periods including the next on-period.

[0230] Specifically, the first dynamic DRX instruction includes an instruction indicating that the user equipment (e.g., the UE 100) is to sleep in a plurality of DRX-on periods including the next DRX-on period (or on period). This enables the UE 100 to sleep continuously not only in the next on period but also in subsequent on periods in accordance with the first dynamic DRX instruction.

[0231] In the second operation example according to the second embodiment, there are three cases for counting a plurality of on periods: (2.2.1) when the UE 100 uses a counter; (2.2.2) when the UE 100 uses a timer; and (2.2.3) when a control period (DRX Control Period) method is used. These cases will be described in order.

[0232] (2.2.1) Counter Method FIG. 26 is a diagram illustrating a second operation example according to the second embodiment.

[0233] As shown in FIG. 26, in step S801, gNB200 performs DRX configuration for UE100.

[0234] In step S802, the gNB 200 uses an inference model to infer whether DL data traffic is occurring during multiple on periods. The inference data (input) in the inference model may be whether DL data traffic is occurring during multiple past on periods, including the current on period. The inference result data (output) in the inference model is whether DL data traffic is occurring during multiple future on periods, including the next on period. The gNB 200 makes a wake-up determination (determination of whether to sleep or wake up) during the multiple on periods based on the inference result. Then, the gNB 200 generates a first dynamic DRX instruction instructing the UE 100 to sleep during the multiple on periods, including the next on period, based on the determination result. The first dynamic DRX instruction may include the number of continuations of the on periods during which the UE 100 will sleep. The first dynamic DRX instruction may include an instruction to perform sleep operation. The first dynamic DRX instruction may imply an instruction to perform sleep operation by including the number of continuations.

[0235] In step S803, gNB200 transmits a first dynamic DRX instruction.

[0236] In step S804, the UE 100 receives a first dynamic DRX instruction during the on period.

[0237] In step S805, the UE 100 continues to perform the sleep operation in accordance with the first dynamic DRX instruction. At this time, the UE 100 counts the number of on-periods using a counter and performs the sleep operation until the number of continuations included in the first dynamic DRX instruction is reached. Then, when the on-period reaches (or exceeds) the number of continuations indicated in the first dynamic DRX instruction, the UE 100 ends (or resets) the count by the counter.

[0238] (2.2.2) Timer Method In the case of the timer method, the operation example shown in Fig. 26 is also used. In this case, the DRX setting (step S801) may include setting information of a timer value indicating a period during which sleep continues. For example, the setting information may include the start timing of the timer value, a start offset, or a counting unit (such as a slot unit).

[0239] The first dynamic DRX instruction (step S803) may also include the timer value, which may be expressed as a time representing a number of on-periods inferred by the inference model during which no DL data traffic occurs. The inclusion of the timer value in the first dynamic DRX instruction may imply an instruction for sleep operation.

[0240] The UE 100 starts a timer in response to receiving the first dynamic DRX (step S804). The UE 100 performs a sleep operation while the timer is running (step S805). The UE 100 performs the existing DRX operation when the count value of the timer reaches or exceeds the timer value (i.e., when the timer value expires). That is, the UE 100 wakes up for each DRX cycle.

[0241] (2.2.3) Control Period Method Fig. 27 is a diagram illustrating an example of operation of the control period method in the second operation example according to the second embodiment. The control period represents either a period in which the UE 100 is continuously made to perform a wake-up operation or a period in which the UE 100 is continuously made to perform a sleep operation.

[0242] 27, in step S901, the gNB 200 performs DRX configuration for the UE 100. The DRX configuration includes configuration information regarding the control period. The configuration information includes, for example, the length of the control period, the start point of the control period, or the start offset.

[0243] In step S902, the gNB200 uses an inference model to infer whether DL data traffic will occur during multiple on periods, including the next on period, and makes a wake-up decision based on the inference result. Here, the inference model is described as inferring that DL data traffic will not occur during the multiple on periods. The gNB200 then makes a wake-up decision based on the inference result and decides to sleep during the multiple on periods. The gNB200 sets the multiple on periods to be subject to sleep as control periods and generates a first dynamic DRX instruction including the control periods. The first dynamic DRX instruction may include an instruction to perform sleep operation. The inclusion of a control period in the first dynamic DRX instruction may imply an instruction to perform sleep operation.

[0244] In step S903, gNB200 transmits the first dynamic DRX instruction to UE100 during the on period.

[0245] In step S904, the UE 100 receives the first dynamic DRX instruction during the on-period. The UE 100 checks the control period and checks that the UE 100 will continue to sleep during the control period.

[0246] In step S905, the UE 100 continues to sleep during the control period in accordance with the first dynamic DRX instruction.

[0247] 28(A) to 28(C) are diagrams illustrating an example of timing according to the second embodiment. In the examples shown in FIG. 28(A) to 28(C), the control period is 3 DRX cycles, and the UE 100 performs sleep operation during this period. As shown in FIG. 28(A) to 28(C), if the UE 100 does not receive a first dynamic DRX instruction including a control period, the UE 100 performs the existing DRX operation.

[0248] In the above-described control period method, an example in which the UE 100 performs a sleep operation during the control period has been described. However, the UE 100 may also perform a wake-up operation during the control period. In this case, the first dynamic DRX instruction (step S903) may include the length of the control period and an instruction to perform the wake-up operation. The UE 100 continuously performs the wake-up operation during the control period in accordance with the first dynamic DRX instruction (step S905).

[0249] Thus, the first dynamic DRX instruction includes an instruction to either continue waking up or continue sleeping during a control period that includes multiple on-periods.

[0250] (2.3) Third Operation Example According to Second Embodiment Next, a third operation example according to the second embodiment will be described. The third operation example according to the second embodiment will be described, focusing on the differences from the first operation example according to the second embodiment and the second operation example according to the second embodiment.

[0251] In the first operation example according to the second embodiment (and the second operation example according to the second embodiment), the control of the DRX operation of the UE 100 in the on period has been described. In the third operation example according to the second embodiment, the control of the DRX operation of the UE 100 within the DRX cycle will be described.

[0252] Specifically, first, the base station (e.g., gNB200) uses the AI / ML model to infer whether DL data traffic is occurring within the DRX cycle. Second, the base station transmits a second dynamic DRX instruction to the user equipment (e.g., UE100) instructing the user equipment (e.g., UE100) to wake up or sleep within the DRX cycle based on the inference result of whether DL data traffic is occurring within the DRX cycle.

[0253] In this way, gNB200 generates a second dynamic DRX instruction that instructs at least one of waking up and sleeping within the DRX cycle based on the inference result of the inference model, and transmits the second dynamic DRX instruction to UE100. Therefore, UE100 can perform DRX operation according to the inference result of gNB200 by performing wake-up operation or sleep operation in accordance with the second dynamic DRX instruction. Therefore, even in the third operation example according to the second embodiment, DRX can be appropriately performed using the AI / ML model. Furthermore, in the third operation example, since DRX operation within the DRX cycle is controlled, gNB200 can transmit DL data within the DRX cycle, and it is possible to achieve low latency of DL data compared to when transmitting DL data only during on periods.

[0254] The DRX cycle may be, for example, a long DRX cycle. The DRX cycle may be a newly defined DRX cycle. The DRX cycle refers to, for example, one DRX cycle, which is a period from the start of an on-period to the start of the next on-period.

[0255] FIG. 29 is a diagram illustrating a third operation example according to the second embodiment.

[0256] As shown in FIG. 29, in step S1001, the gNB 200 performs DRX configuration on the UE 100. The DRX configuration includes a long DRX configuration. The long DRX configuration includes an "on duration" ("drx-onDurationTimer"), a "DRX cycle" ("drx-LongCycleStartOffset"), and the like. The long DRX configuration may be an existing DRX configuration. The DRX configuration also includes a dynamic DRX configuration. The dynamic DRX configuration is, for example, a DRX configuration for causing the UE 100 to operate in accordance with a second dynamic DRX instruction within the DRX cycle.

[0257] First, the dynamic DRX setting includes a DRX control unit period. The DRX control unit period represents a unit time of DRX control (e.g., an on pattern or an off pattern) within a DRX cycle. The DRX control unit period may be expressed in slot units. Alternatively, the DRX control unit period may be expressed as a division result of dividing a long DRX cycle. For example, if the long DRX cycle is 2.56 seconds and the division setting is 4, the DRX control unit period is 0.64 seconds. The gNB 200 can issue a wake-up or sleep instruction for each DRX control unit period included in the DRX cycle. The DRX control unit period may be expressed as a dynamic DRX cycle ("dynamic DRX cycle").

[0258] Second, the dynamic DRX setting includes an "on-duration timer" that indicates the length of the on-period within the DRX cycle. The "on-duration timer" does not need to be set to a different length as long as it is the same as the length of the on-period in the case of long DRX.

[0259] Third, the dynamic DRX setting includes a DRX-RNTI. If the second dynamic DRX instruction is a DCI, the DRX-RNTI is used to decode the DCI in the UE 100.

[0260] In step S1002, the UE 100 performs a wake-up operation for each long DRX cycle.

[0261] In step S1003, the gNB200 uses an inference model to infer whether DL data traffic is occurring in the DRX cycle. The inference data (input) of the inference model is whether DL data was generated (or received) in the previous DRX cycle. This may be based on whether DL data was generated in a past DRX cycle, or on information provided by a higher layer regarding traffic characteristics. The inference result data (output) of the inference model is whether DL data is occurring in the current DRX cycle. The inference result data may be the result of a wake-up determination (wake-up operation or sleep operation in a dynamic DRX cycle). The gNB200 makes a wake-up determination within the DRX cycle based on the inference result. Specifically, the gNB200 determines whether to wake up or sleep for each DRX control unit period within the DRX cycle based on the inference result. gNB200 generates a second dynamic DRX instruction including an instruction for wake-up operation or sleep operation for each DRX control unit period according to the judgment result of the wake-up judgment.

[0262] 30(A) to 30(C) are diagrams illustrating an example of timing according to the second embodiment. Fig. 30(B) illustrates an example of a second dynamic DRX instruction. As shown in Fig. 30(B), the second dynamic DRX instruction instructs a wake-up operation or a sleep operation for each DRX control unit.

[0263] 29 , in step S1004, gNB200 transmits a second dynamic DRX instruction during the on period of the DRX cycle. gNB200 may transmit the second dynamic DRX instruction using MAC CE or DCI. Alternatively, gNB200 may transmit the second dynamic DRX instruction using an RRC message.

[0264] First, the second dynamic DRX instruction may be represented by a bitmap indicating wake-up or sleep. A DRX control unit period may be represented by one bit. In this case, "0" may represent sleep and "1" may represent wake-up (the bit values ​​may be reversed). For example, if the DRX control unit period is "2" slots and the second dynamic DRX instruction is {0, 1, 1, 0}, the following is represented: "slot #0" and "slot #1" represent sleep, "slot #2" to "slot #5" represent wake-up, and "slot #6" and "slot #7" represent sleep.

[0265] Second, the second dynamic DRX instruction may be information indicating how many slots after which the device will wake up. For example, if the second dynamic DRX instruction is an instruction to "wake up after four slots," the device will perform a wake-up operation four slots after the start (or end) of the on-period. Conversely, the second dynamic DRX instruction may be information indicating how many slots after which the device will sleep.

[0266] In step S1005, the UE 100 receives a second dynamic DRX instruction during the on period of the DRX cycle.

[0267] In step S1006, the UE 100 performs either a wake-up operation or a sleep operation for each DRX control unit period within the DRX cycle in accordance with the second dynamic DRX instruction. Fig. 30(C) shows an example of the operation of the UE 100 when the second dynamic DRX instruction is received.

[0268] In addition, when the UE 100 does not receive the second dynamic DRX instruction, the UE 100 performs a wake-up operation for each on-duration, similarly to the existing DRX operation.

[0269] Third Embodiment Next, a third embodiment will be described, focusing on the differences between the first and second embodiments.

[0270] In the first embodiment, an example in which inference is performed in UE 100 ("UE side one-sided model") has been described. In the second embodiment, an example in which inference is performed in gNB 200 ("gNB side one-sided model") has been described. In the third embodiment, an example in which inference is performed in both UE 100 and gNB 200 will be described.

[0271] When inference is performed by both the UE 100 and the gNB 200, if the inference results differ between the two, it may be a problem as to how to perform DRX. Therefore, the third embodiment, like the first embodiment, also aims to be able to appropriately perform DRX using an AI / ML model.

[0272] (3.1) First Operation Example According to Third Embodiment Next, a first operation example according to the third embodiment will be described.

[0273] The first operation example according to the third embodiment is an example in which UE100 performs a wake-up operation when the inference result of gNB200 and the inference result of UE100 match.

[0274] Specifically, first, a base station (e.g., gNB200) uses an AI / ML model to infer whether data traffic is occurring in the downlink during a DRX cycle. Second, the base station transmits a second dynamic DRX instruction to a user equipment (e.g., UE100) during a DRX cycle, instructing the user equipment to wake up or sleep during the DRX cycle based on the inference result of whether data traffic is occurring. Third, the user equipment uses the AI / ML model to infer whether data traffic is occurring during a DRX cycle. Fourth, the user equipment wakes up based on the second dynamic DRX instruction and the inference result of the user equipment at a timing when both the second dynamic DRX instruction and the inference result of the user equipment indicate wakeup.

[0275] Thus, in the first operation example of the third embodiment, the wake-up operation of UE100 is performed at the timing when the inference result of gNB200 and the inference result of UE100 match, so that even if the inference results of the two are different, DRX can be appropriately performed using the AI / ML model, as in the first embodiment.

[0276] 32(A) to 32(D) are diagrams showing timing examples according to the third embodiment. As shown in FIG. 32(C), the second dynamic DRX instruction by gNB200 (FIG. 32(B)) and the inference result in UE100 (FIG. 32(C)) are both wake-up timings. A wake-up operation is performed in UE100.

[0277] FIG. 31 is a diagram illustrating a first operation example according to the third embodiment.

[0278] As shown in Figure 31, in step S1101, the gNB 200 performs RRC configuration for the UE 100. The RRC configuration may include information indicating that the UE 100 and the gNB 200 jointly determine the wake-up timing. The RRC configuration may include the long DRX configuration and dynamic DRX configuration described in the third operation example of the second embodiment.

[0279] In step S1102, the UE 100 performs a wake-up operation for each long DRX cycle.

[0280] In step S1103, the gNB200 uses the inference model to infer whether DL traffic is occurring. Then, the gNB200 performs a wake-up determination based on the inference result and generates a second dynamic DRX instruction. Step S1103 is the same as the third operation example (step S1003) of the second embodiment.

[0281] In step S1104, gNB200 transmits a second dynamic DRX instruction to UE100 during the on period of the long DRX cycle.

[0282] In step S1105, UE100 receives the second dynamic DRX instruction during the on period. Then, UE100 uses an inference model to infer whether data traffic is occurring within the DRX cycle. The inference model used by UE100 and the inference model used by gNB200 may be the same or different. The inference data (input) and inference result data (output) of the inference model used by UE100 are the same as those in the third operation example (step S1003) of the second embodiment.

[0283] In step S1106, the UE 100 performs a wake-up operation at a timing when both the second dynamic DRX instruction and the inference result of the UE 100 indicate wake-up, based on the second dynamic DRX instruction and the inference result of the UE 100. The UE 100 may perform a wake-up operation at a timing when either the second dynamic DRX instruction or the inference result of the UE 100 indicates wake-up, based on the second dynamic DRX instruction and the inference result of the UE 100.

[0284] (3.1.1) Another example 1 of the first operation example according to the third embodiment In the first operation example according to the third embodiment, the case where the second dynamic DRX instruction is used has been described, but this is not limited to this. For example, even when the first dynamic DRX instruction is used, if the inference result of the gNB 200 and the inference result of the UE 100 match, the wake-up operation of the UE 100 may be performed.

[0285] Specifically, first, the base station (e.g., gNB200) uses the AI / ML model to infer whether data traffic will occur in the downlink during the next DRX-on period. Second, based on the inference result of whether data traffic will occur, the base station transmits a first dynamic DRX instruction to the user equipment (e.g., UE100) instructing the user equipment to either wake up during the next DRX-on period or sleep during the next DRX-on period. Third, the user equipment uses the AI / ML model to infer whether data traffic will occur during the next DRX-on period. Fourth, based on the first dynamic DRX instruction and the inference result of the user equipment, the user equipment wakes up at a timing when both the first dynamic DRX instruction and the inference result of the user equipment indicate wake-up.

[0286] The other example 1 may use the operation example shown in Fig. 31. In this case, the estimation of DL data traffic (step 1103) is the same as the first operation example (step S702) according to the second embodiment, and the "second dynamic DRX instruction" (steps S1104 and S1106) can be read as the "first dynamic DRX instruction."

[0287] (3.1.2) Another example 2 of the first operation example according to the third embodiment In the first operation example according to the third embodiment, an example in which the wake-up operation of UE100 is performed at the timing when the inference result of gNB200 and the inference result of UE100 match has been described, but this is not limited to this. For example, the sleep operation of UE100 may be performed at the timing when the inference result of gNB200 and the inference result of UE100 match.

[0288] For example, in the example of Figure 32 (D), UE100 performs sleep operation at a timing when the sleep timing indicated by the second dynamic DRX instruction of gNB200 coincides with the sleep timing inferred by UE100.

[0289] As a result, in this other example 2, as in the first operation example of the third embodiment, DRX using the AI / ML model can be appropriately performed even if the inference results differ between UE100 and gNB200.

[0290] (3.2) Second Operation Example According to Third Embodiment Next, a second operation example according to the third embodiment will be described. The second operation example according to the third embodiment will be described, focusing on the differences from the first operation example according to the third embodiment.

[0291] In the second operation example according to the third embodiment, when an instruction is not received from the gNB 200, either a wake-up operation or a sleep operation is performed using the inference result of the UE 100. Specifically, when the user equipment (for example, the UE 100) does not receive the second dynamic DRX instruction, either a wake-up operation or a sleep operation is performed based on the inference result of the user equipment.

[0292] For example, in the case of DCI, even if gNB200 transmits a second dynamic DRX instruction to UE100, feedback information is not transmitted from UE100. Therefore, gNB200 does not know whether the second dynamic DRX instruction has been received by UE100. For example, even if gNB200 transmits the DCI, a case is assumed in which UE100 is unable to receive the second dynamic DRX instruction due to deterioration of the radio conditions, etc. In the second operation example according to the third embodiment, even in such a case, an inference determination for UE100 is permitted and DRX operation is performed based on the inference result of UE100, thereby appropriately performing DRX using the AI / ML model.

[0293] FIG. 33 is a diagram illustrating a second operation example according to the third embodiment.

[0294] 33, in step S1201, the gNB 200 performs RRC configuration for the UE 100. The RRC configuration may include information indicating that the wake-up timing is jointly determined, as in the first operation example according to the third embodiment, and may include a long DRX configuration and a dynamic DRX configuration.

[0295] In step S1202, the UE 100 performs a wake-up for each long DRX cycle.

[0296] In step S1203, the gNB 200 uses the inference model to infer whether DL data traffic is occurring. Similar to the first operation example according to the third embodiment, the gNB 200 performs a wake-up determination based on the inference result and generates a second dynamic DRX instruction.

[0297] In step S1204, gNB200 transmits a second dynamic DRX instruction during the long DRX on period.

[0298] In step S1205, the UE 100 receives a second dynamic DRX instruction during the on-duration. In this case, in step S1206, the UE 100 performs either a wake-up operation or a sleep operation in accordance with the second dynamic DRX instruction.

[0299] In step S1207, the UE 100 does not receive the second dynamic DRX instruction during the on-period. In this case, in step S1208, the UE 100 uses the inference model to infer whether DL data traffic is occurring, and performs either a wake-up operation or a sleep operation according to the inference result.

[0300] 34(A) to 34(D) are diagrams showing timing examples according to the third embodiment. As shown in FIG. 34(D), when UE100 receives a second dynamic DRX instruction from gNB200, it performs either a wake-up operation or a sleep operation according to the second dynamic DRX instruction. On the other hand, if UE100 does not receive a second dynamic DRX instruction, it performs either a wake-up operation or a sleep operation according to its own inference result.

[0301] In the second operation example according to the third embodiment described above, the operation when the UE 100 does not receive the second dynamic DRX instruction has been described, but the present invention is not limited to this. The operation can also be performed when the UE 100 does not receive the first dynamic DRX instruction instead of the second dynamic DRX instruction. In this case, when the UE 100 does not receive the first dynamic DRX instruction, the UE 100 may perform a wake-up operation and a sleep operation during the on period according to its own inference result, similar to the second operation example according to the third embodiment described above.

[0302] [Other Embodiments] In the first to third embodiments described above, supervised learning has been mainly described, but the present invention is not limited to this. For example, the first embodiment may be applied to unsupervised learning or reinforcement learning.

[0303] The above-described operational flows are not limited to being implemented independently, but can also be implemented by combining two or more operational flows. For example, some steps of one operational flow may be added to another operational flow, or some steps of one operational flow may be replaced with some steps of another operational flow. In each flow, it is not necessary to execute all steps, and only some steps may be executed.

[0304] In the above-described embodiments and examples, an example in which the base station is an NR base station (gNB) has been described, but the base station may be an LTE base station (eNB) or a 6G base station. The base station may also be a relay node such as an IAB (Integrated Access and Backhaul) node. The base station may also be a DU of the IAB node. The UE 100 may also be an MT (Mobile Termination) of the IAB node.

[0305] 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.

[0306] Furthermore, a program (e.g., an information processing program) that causes a computer to execute each process or function according to the above-described embodiments may be provided. Alternatively, a program (e.g., a mobile communication program) that causes the mobile communication system 1 to execute each process or function according to the above-described embodiments may be provided. The program may be recorded on a computer-readable medium. Using a computer-readable medium, the program can be installed on a computer. Here, the computer-readable medium on which the program is recorded may be a non-transitory recording medium. The non-transitory recording medium is not particularly limited, and may be, for example, a recording medium such as a CD-ROM or DVD-ROM. Such a recording medium may be memory included in the UE 100 and the gNB 200. Furthermore, circuits that execute each process performed by the UE 100 or the gNB 200 may be integrated, and at least a portion of the UE 100 or the gNB 200 may be configured as a semiconductor integrated circuit (chip set, SoC: System on a chip).

[0307] 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.

[0308] As used in this disclosure, the terms "based on" and "depending on / in response to" do not mean "based only on" or "depending only on," unless expressly stated otherwise. The term "based on" means both "based only on" and "based at least in part on." Similarly, the term "depending on" means both "depending only on" and "depending at least in part on." The terms "include," "comprise," and variations thereof do not mean including only the listed items, but may mean including only the listed items or may include additional items in addition to the listed items. Additionally, the term "or," as used in this disclosure, is not intended to mean an exclusive or. Furthermore, any reference to elements using designations such as "first," "second," etc., as used in this disclosure does not generally limit the quantity or order of those elements. These designations may be used herein as a convenient method of distinguishing between two or more elements. Thus, a reference to a first and a second element does not imply that only two elements may be employed therein or that the first element must precede the second element in some way. In this disclosure, where articles are added by translation, such as a, an, and the in English, these articles shall include the plural unless the context clearly indicates otherwise.

[0309] Although the embodiments have been described in detail above with reference to the drawings, the specific configuration is not limited to the above, and various design changes can be made without departing from the spirit of the invention. Furthermore, it is also possible to combine the embodiments, operation examples, or processes within a consistent range.

[0310] This application claims priority to U.S. Provisional Application No. 63 / 444,305 (filed February 9, 2023), the entire contents of which are incorporated herein by reference.

[0311] (Supplementary Note) (Supplementary Note 1) A communication control method in a mobile communication system, comprising: a step in which a user device uses an AI / ML model to infer whether or not data traffic will occur in downlink during a next DRX on-duration; and a step in which the user device either wakes up during the next DRX on-duration or skips the wake-up during the next DRX on-duration based on the inference result of whether or not data traffic will occur.

[0312] (Supplementary Note 2) The communication control method according to Supplementary Note 1, wherein the step of either waking up or skipping the wake-up includes a step of waking up in the next DRX-on period if the user equipment infers that the data traffic will occur, and skipping the wake-up in the next DRX-on period if the user equipment infers that the data traffic will not occur.

[0313] (Supplementary Note 3) The communication control method according to Supplementary Note 1 or Supplementary Note 2, further comprising the step of: a network node configuring the user equipment to allow skipping of the wake-up.

[0314] (Supplementary Note 4) The communication control method according to any one of Supplementary Note 1 to Supplementary Note 3, further comprising the step of adjusting the wake-up period by the user equipment in accordance with the probability of occurrence of the data traffic.

[0315] (Supplementary Note 5) The communication control method according to any one of Supplementary Note 1 to Supplementary Note 4, wherein the inferring step includes a step in which the user device infers whether or not the data traffic is occurring based on inference results of a plurality of the AI / ML models.

[0316] (Supplementary Note 6) The communication control method according to any one of Supplementary Notes 1 to 5, further comprising the step of: a network node setting, in the user equipment, an operational restriction on skipping the wake-up.

[0317] (Supplementary Note 7) The communication control method according to any one of Supplementary Note 1 to Supplementary Note 6, wherein the operational restriction is any one of an upper limit on the number of consecutive skips, an upper limit on the duration of consecutive skips, and a repetition period during which the wake-up must be performed.

[0318] (Supplementary Note 8) A communication control method in a mobile communication system, comprising: a step in which a network node uses an AI / ML model to infer whether or not data traffic will occur in downlink in a next DRX-on period; a step in which the network node transmits a first dynamic DRX instruction to a user equipment, the first dynamic DRX instruction instructing the user equipment to either wake up in the next DRX-on period or to sleep in the next DRX-on period, based on a result of the inference of whether or not data traffic will occur; a step in which the user equipment uses the AI / ML model to infer whether or not data traffic will occur in the next DRX-on period; and a step in which the user equipment performs the wake-up based on the first dynamic DRX instruction and the inference result of the user equipment, at a timing when both the first dynamic DRX instruction and the inference result of the user equipment indicate wake-up.

[0319] (Supplementary Note 9) The communication control method according to Supplementary Note 8, wherein the step of waking up includes a step of performing either the wake-up or the sleep according to an inference result of the user equipment when the user equipment does not receive the first dynamic DRX instruction.

[0320] 1: Mobile communication system 20: 5GC (CN) 100: UE 110: Receiving unit 120: Transmitting unit 130: Control unit 200: gNB 210: Transmitting unit 220: Receiving unit 230: Control unit 250: Backhaul communication unit A1: Data collection unit A2: Model learning unit A3: Model inference unit A4: Data processing unit TE: Transmitting entity RE: Receiving entity

Claims

1. A communication control method in a mobile communication system, comprising: The user equipment uses an AI (Artificial Intelligence) / ML (Machine Learning) model to infer whether or not downlink data traffic will occur during a next DRX on-duration; and The user equipment either wakes up in the next DRX-on period or skips the wake-up in the next DRX-on period based on the inference result of whether or not the data traffic is generated. Communication control method.

2. The step of waking up or skipping the wake-up includes the step of waking up in the next DRX-on period when the user equipment determines that the data traffic will occur, and skipping the wake-up in the next DRX-on period when the user equipment determines that the data traffic will not occur. The communication control method according to claim 1.

3. The network node further comprises configuring the user equipment to allow skipping of the wake-up. The communication control method according to claim 1.

4. The user equipment further includes adjusting the wake-up period according to the probability of occurrence of the data traffic. The communication control method according to claim 1.

5. The inferring includes the user device inferring whether or not the data traffic will occur based on inference results of the plurality of AI / ML models. The communication control method according to claim 1.

6. and a network node setting an operational restriction on the user equipment for skipping the wake-up. The communication control method according to claim 1.

7. The operation restriction is any one of an upper limit of the number of times the skip can be continuously performed, an upper limit of the time for which the skip can be continuously performed, and a repetition period during which the wake-up must be performed.

7. The communication control method according to claim 6.

8. A communication control method in a mobile communication system, comprising: the network node uses the AI / ML model to infer whether data traffic will occur in the downlink in the next DRX-on period; The network node transmits a first dynamic DRX instruction to the user equipment, the first dynamic DRX instruction instructing the user equipment to either wake up in the next DRX-on period or sleep in the next DRX-on period based on the inference result of whether or not the data traffic is generated; and The user equipment uses an AI / ML model to infer whether or not the data traffic will occur in the next DRX-on period; The user equipment performs the wake-up based on the first dynamic DRX instruction and the inference result of the user equipment at a timing when both the first dynamic DRX instruction and the inference result of the user equipment indicate a wake-up. Communication control method.

9. The waking up includes, when the user equipment does not receive the first dynamic DRX instruction, performing either the waking up or the sleep according to an inference result of the user equipment. The communication control method according to claim 8.

10. A user equipment in a mobile communication system, comprising: The control unit is configured to use an AI (Artificial Intelligence) / ML (Machine Learning) model to infer whether or not data traffic will occur in downlink during a next DRX on-duration, and to perform either a wake-up during the next DRX on-duration or a skip of the wake-up during the next DRX on-duration based on the inference result of whether or not data traffic will occur. User equipment.