WO2025173226A1 - Terminal device, base station device, control method for terminal device, and control method for base station device - Google Patents

Abstract

The present invention improves mobility management performance between a terminal device and a base station device. The terminal device comprises a reception unit, a prediction unit, and a transmission unit. The reception unit receives information about measurement settings that include a measurement event for measuring the reception quality of a cell and information that indicates permission to use cell prediction results from the base station device. The prediction unit outputs a reception quality for the cell as cell prediction results. The transmission unit reports the measurement event, a first reception quality that was actually measured with respect to the measurement event, and a second reception quality that is based on the cell prediction results to the base station device on the basis of the information that indicates permission to use cell prediction results.

Description

Terminal device, base station device, terminal device control method, and base station device control method

The present invention relates to a terminal device, a base station device, a method for controlling a terminal device, and a method for controlling a base station device.

The standardization project 3GPP (3rd Generation Partnership Project (registered trademark)) is considering technical specifications for communications standards that will meet the requirements of eMBB (Enhanced Mobile Broadband), Massive MTC (Machine Type Communications), and URLLC (Ultra-Reliable and Low Latency Communications) for NR (New Radio, also known as 5G), the fifth generation of mobile communications.

3GPP is studying methods for optimizing signaling and reporting values using AI/ML (Artificial Intelligence/Machine Learning). Specifically, they are studying technology that equips terminal devices or the network (i.e., base station devices, core network equipment, etc.) with learning models trained using machine learning (ML), a field of AI, and uses output values obtained by inputting specified input values into the learned learning model as a substitute for, complement to, or verification of actual measured values (Non-Patent Document 1).

In addition, 3GPP is also planning to study the use of AI/ML in mobility management. For example, studies are planned to be conducted with the aim of improving the performance and reliability of mobility management by predicting (inferring) the future quality of cells using trained learning models and determining in advance the evaluation of events such as handovers based on the predicted results (Non-Patent Document 2).

3GPP TR 38.843 V18.0.0 (2023-12) RP-234055

However, the various parameters used in conventional mobility management are determined by network operators (base station equipment) based on the actual surrounding environment of the cell and terminal device, and are not designed to conform to the cell quality predicted by the terminal device. Furthermore, measurement events are determined based on the results of actual cell measurements, and therefore are not intended to be evaluated using predicted values like AI/ML. Therefore, there is a problem in that predicting cell reception quality (cell quality) using AI/ML and simply using this for mobility management could actually degrade the performance of conventional mobility management, and no concrete solution has been mentioned to date.

In light of this problem, one aspect of the present invention aims to improve the performance of mobility management between terminal devices and base station devices by predicting cell reception quality using a trained model.

A terminal device according to one aspect of the present invention is a terminal device that communicates with a base station device, and includes a receiver that receives, from the base station device, information related to measurement settings including a measurement event for measuring the reception quality of a cell and information indicating permission to use the cell prediction result; a predictor that outputs fluctuations in the reception quality of the cell as the cell prediction result; and a transmitter that reports to the base station device, based on the information indicating permission to use the cell prediction result, the measurement event, a first reception quality actually measured for the measurement event, and a second reception quality based on the cell prediction result.

Furthermore, a base station device according to one aspect of the present invention is a base station device that communicates with a terminal device, and includes: a transmitter that transmits to the terminal device information related to measurement settings, including a measurement event for measuring the reception quality of a cell, and information indicating permission to use the cell prediction result; a prediction unit that controls the prediction of fluctuations in the cell reception quality, which is output by the terminal device as the cell prediction result; and a receiver that receives a measurement report message that includes the measurement event transmitted based on the information indicating permission to use the cell prediction result, a first reception quality actually measured by the terminal device related to the measurement event, and a second reception quality based on the cell prediction result.

According to the above-described aspect, by using a trained model to predict cell reception quality, it is possible to improve the performance of mobility management between terminal devices and base station devices.

1 is a diagram illustrating an example of a configuration of a wireless communication system according to an embodiment. FIG. 2 is a diagram illustrating an example of a functional configuration of a terminal device according to an embodiment. FIG. 2 is a diagram illustrating an example of a functional configuration of a base station device according to an embodiment. FIG. 10 is a diagram showing an example of reporting a prediction result of cell quality according to an embodiment. FIG. 10 is a diagram showing another example of reporting a prediction result of cell quality according to an embodiment. FIG. 1 is a diagram illustrating an example of the relationship between input data and output data of a trained model according to an embodiment. FIG. 10 is a sequence diagram illustrating an example of an RRC message according to the embodiment. This is a diagram showing the framework for AI/ML for air interface. FIG. 2 illustrates an example of a hardware configuration of a terminal device. FIG. 2 is a diagram illustrating an example of a hardware configuration of a base station device.

Embodiments of the present invention will be described in detail below with reference to the drawings. The problems and embodiments described in this specification are merely examples and do not limit the scope of the rights of the present application. In particular, even if the written expressions are different, the technology of the present application can be applied as long as they are technically equivalent, and this does not limit the scope of the rights. Furthermore, each embodiment can be combined as appropriate to the extent that there is no contradiction in the processing content. For example, an inactive period may be referred to as an inactive period.

Publicly known technologies may be used in wireless communication systems according to embodiments of the present invention, as appropriate. Applicable publicly known technologies may be, for example, 5G (NR), Beyond 5G, 5G-Advanced, 6G, or other wireless communication methods. Wireless communication systems according to embodiments of the present invention are primarily targeted at NR, but are not limited to this. For example, embodiments of the present invention are also applicable to LTE (Long Term Evolution) and LTE-Advanced. They are also applicable to wireless communication systems that use NR as part of the wireless communication system.

Furthermore, embodiments of the present invention are applicable to any wireless communication system that includes at least a terminal device and a base station device, and are also applicable to future wireless communication systems. In the following description, LTE and LTE-Advanced are also referred to as E-UTRA (Evolved Universal Terrestrial Radio Access), but the meaning is the same.

Below, embodiments of the base station device, terminal device, and wireless communication system disclosed in this application will be described with reference to the drawings. Note that the following embodiments do not limit the disclosed technology.

<Wireless communication system>
1 is a diagram showing an example of the configuration of a wireless communication system 1 according to an embodiment of the present invention. The wireless communication system 1 according to the embodiment is configured, for example, with a terminal device 10, base station devices 20A and 20B, and a core network 30. Note that when there is no need to distinguish between the base station devices 20A and 20B, they will simply be referred to as the base station device 20. Furthermore, there may be multiple terminal devices 10.

The terminal device 10 may be a wireless terminal such as a mobile phone, smartphone, PDA (Personal Digital Assistant), tablet, wearable device, personal computer, vehicle, or other device or equipment (sensor device, etc.) with wireless communication capabilities. The terminal device 10 may also be referred to as a wireless communication device, communication device, receiving device, mobile station, UE (User Equipment), user device, etc.

Wireless communication services are provided to terminal devices 10 by base station devices 20 and core network 30 in wireless communication system 1. The core network 30 has functions such as managing service subscriber information, session management for voice calls, and location registration management for terminal devices 10. The core network 30 also transmits control data and/or user data to terminal devices 10 via base station devices 20.

The core network 30 may be 5GC (5G Core) in 5G (NR) or EPC (Evolved Packet Core) in 4G (E-UTRA). The connection method between the core network 30 and the base station device 20 may be either the NSA (Non-Stand Alone) method or the SA (Stand Alone) method.

The 5G base station devices 20 connected to the 5GC are gNBs, and the 4G base station devices 20 connected to the EPC are eNBs. Furthermore, the 5G base station devices are connected via the Xn interface, and the 4G base station devices are connected via the X2 interface.

The area (coverage area) formed by the base station device 20 is sometimes called a "cell." E-UTRA and 5G are cellular communication systems constructed from multiple cells. The wireless communication system related to an embodiment of the present invention may use either TDD (Time Division Duplex) or FDD (Frequency Division Duplex), and different methods may be applied to each cell.

The base station device 20 may be configured, for example, as separate units: a CU (Centralized Unit), a DU (Distributed Unit), and a RU (Radio Unit). The CU is connected to the core network. The DU is connected to the terminal device 10 via the RU, for example. The communication path between the CU and DU is realized by a fronthaul interface (F1 interface), for example. Multiple DUs may be connected to one CU. Part of the base station device 20 may be configured as a program that can be executed on a cloud network.

In the example shown in Figure 1, data (DL data, downlink data) transmitted from the core network 30 to the terminal device 10 is transmitted from the core network 30 to the base station device 20, and then transmitted (forwarded) from the base station device 20 to the terminal device 10.

Data (UL data, uplink data) transmitted from the terminal device 10 to the core network 30 is transmitted from the terminal device 10 to the base station device 20, and then transmitted (forwarded) from the base station device 20 to the core network 30.

The terminal device 10 and the base station device 20 transmit and receive radio resource control (RRC) messages (also called RRC signaling) in the RRC layer. The terminal device 10 and the base station device 20 also transmit and receive medium access control (MAC) control elements (MAC CEs) in the MAC layer.

RRC messages are transmitted as RRC Protocol Data Units (PDUs) and are mapped to logical channels (LCHs), such as the Common Control Channel (CCCH), Dedicated Control Channel (DCCH), Paging Control Channel (PCCH), Broadcast Control Channel (BCCH), or Multicast Control Channel (MCCH).

MAC CEs are transmitted as MAC PDUs (or MAC subPDUs). A MAC subPDU is equivalent to a service data unit (SDU) at the MAC layer plus, for example, 8 bits of header information, and a MAC PDU contains one or more MAC subPDUs.

Next, the physical channels and physical signals according to the embodiment include a synchronization signal (Primary Synchronization Signal, Secondary Synchronization Signal), a physical broadcast channel (PBCH: Physical Broadcast Channel), a physical random access channel (PRACH: Physical Random Access Channel), a physical downlink control channel (PDCCH: Physical Downlink Control Channel), and a channel state information reference signal (CSI-RS: Channel State Information Reference Signal). There are at least three types of channels: PUCCH (Physical Uplink Control Channel), PDSCH (Physical Downlink Shared Channel), PUSCH (Physical Uplink Shared Channel), SRS (Scheduling Reference Signal), and DMRS (Demodulation Reference Signal), but detailed explanations will be omitted.

<Terminal Device>
2 is a diagram illustrating an example of the functional configuration of a terminal device 10 according to an embodiment. As illustrated in FIG. 2, the terminal device 10 includes, for example, a processing unit 11, a control unit 13, a receiving unit 15, a transmitting unit 17, and a transmitting/receiving antenna unit 19. The processing unit 11 includes, for example, a radio resource processing unit 111 and a prediction unit 113. Note that the functional configuration of the terminal device 10 illustrated in FIG. 2 is merely an example, and the functional divisions and names of each functional block may be different as long as the operations according to the embodiment can be performed. Furthermore, one or more blocks that realize other functions may be present.

The processing unit 11 generates, for example, control information for controlling the receiving unit 15 and transmitting unit 17, and outputs this to the control unit 13. The processing unit 11 performs processing related to, for example, the radio resource control layer, the Packet Data Convergence Protocol (PDCP) layer, the Radio Link Control (RLC) layer, and the medium access control layer.

The radio resource processing unit 111 manages various setting information (RRC parameters, information elements (IEs)) for the terminal device 10. For example, the radio resource processing unit 111 generates information to be placed on each physical uplink channel and outputs that information to the transmission unit 17. Furthermore, based on instructions from the base station device 20, the radio resource processing unit 111 performs measurements of the serving cell and surrounding cells, starting and stopping transmission and reception processing, DL synchronization procedures (cell search), UL synchronization procedures (random access procedures), reacquisition of system information, event evaluation related to mobility management, and a series of processes related to mobility management.

The prediction unit 113 is equipped with at least one trained learning model (a machine-learned model, hereafter also referred to as the trained model), and performs control processing to output a predetermined predicted value based on input data. In other words, the prediction unit 113 uses the trained model to calculate and process specific input information according to its intended use, and outputs the result as a predicted value. Based on instructions from the radio resource processing unit 111 or instructions from the base station device 20, the prediction unit 113 performs (executes) the activation, deactivation, switching, fallback (stopping use of the trained model), etc. of the trained model, and performs (executes) predictions of cell measurements and/or event evaluations.

The control unit 13 performs various controls in the terminal device 10. For example, the control unit 13 generates control signals or control data for controlling the receiving unit 15 and the transmitting unit 17 based on control information from the processing unit 11. The control unit 13 also controls uplink transmission to the base station device 20, scheduling request transmission, and downlink reception from the base station device 20 based on the prediction results from the prediction unit 113.

The receiver 15 separates, demodulates, and decodes various signals received from the base station device 20 via the transmitter/receiver antenna 19 based on control signals provided by the controller 13. The receiver 15 outputs the decoded information to the processor 11.

The transmitter 17 generates, for example, a physical uplink signal based on a control signal provided by the control unit 13, and performs encoding and modulation on the physical uplink signal or physical uplink channel provided by the processing unit 11. The transmitter 17 multiplexes various signals and transmits them to the base station device 20 via the transmitting/receiving antenna unit 19.

The processing unit 11 and the control unit 13 are realized, for example, by a processor system including a processor and memory. In this case, the processor provides the functions of the processing unit 11 and the control unit 13 by executing a program that describes the operation of the terminal device 10, which will be described later. The processing unit 11 and the control unit 13 may also be realized by a single processor system or by multiple processor systems. Alternatively, the processing unit 11 and the control unit 13 may also be realized by a DSP (Digital Signal Processor) or a hardware circuit, etc.

<Base station equipment>
3 is a diagram illustrating an example of the functional configuration of a base station device 20 according to an embodiment. As illustrated in FIG. 3, the base station device 20 includes, for example, a processing unit 21, a control unit 23, a receiving unit 25, a transmitting unit 27, and a transmitting/receiving antenna unit 29. The processing unit 21 illustratively includes a radio resource processing unit 211 and a prediction unit 213. Note that the functional configuration of the base station device 20 illustrated in FIG. 3 is merely an example, and the names of the functional divisions and functional blocks may be different as long as the operations according to the embodiment can be performed. Furthermore, one or more blocks that realize other functions may be present.

The processing unit 21 generates, for example, control information for controlling the receiving unit 25 and transmitting unit 27, and outputs this to the control unit 23. The processing unit 21 performs processing related to, for example, the radio resource control layer, the packet data integration protocol layer, the radio link control layer, and the medium access control layer.

The radio resource processing unit 211 generates, for example, downlink data, RRC messages, and MAC control elements to be placed on the physical downlink shared channel PDSCH, and outputs these to the transmission unit 27. The radio resource processing unit 211 also generates control signals or control data to be placed on the physical downlink control channel PDCCH, and outputs these to the transmission unit 27. Furthermore, the radio resource processing unit 211 manages various setting information for the terminal device 10. Based on signals from the terminal device 10 and notifications via RRC messages, the radio resource processing unit 211 performs operations such as starting and stopping transmission and reception processing, starting a UL synchronization procedure (random access procedure), updating system information, adjusting the beam transmission angle, and presetting parameters related to cell settings and measurement event types (measurement event identifiers) related to mobility management.

The prediction unit 213 performs processing to manage the prediction unit 113 of the terminal device 10. Based on information related to mobility management, such as the cell state, reported prediction values, and information for determining the accuracy and error of prediction values, the prediction unit 213 determines whether activation, deactivation, switching, or fallback of the trained model of the terminal device 10 is necessary, and determines whether to have the terminal device 10 perform cell measurement prediction and/or event evaluation prediction.

The control unit 23 performs various controls in the base station device 20. For example, the control unit 23 generates control signals or control data that control the receiving unit 25 and transmitting unit 27 based on control information from the processing unit 21. The control unit 23 also controls downlink transmission to the terminal device 10 and uplink reception from the terminal device 10 based on determination information from the prediction unit 213.

The receiving unit 25 separates, demodulates, and decodes various signals received from the terminal device 10 or core network 30 via the transmitting/receiving antenna unit 29 based on control signals provided by the control unit 23. The receiving unit 25 outputs the decoded information to the processing unit 21.

The transmitter 27 generates, for example, a downlink reference signal based on a control signal provided by the controller 23. The transmitter 27 encodes, modulates, multiplexes, etc., various information provided by the processor 21, and transmits the signal to the terminal device 10 via the transmitter/receiver antenna 29.

Furthermore, the transmitter 27 transmits data to the terminal device 10, another base station device 20, or the core network 30. The receiver 25 receives data from the terminal device 10, another base station device 20, or the core network 30.

The processing unit 21 and the control unit 23 are realized, for example, by a processor system including a processor and memory. In this case, the processor provides the functions of the processing unit 21 and the control unit 23 by executing a program that describes the operation of the base station device 20, which will be described later. The processing unit 21 and the control unit 23 may also be realized by a single processor system or by multiple processor systems. Alternatively, the processing unit 21 and the control unit 23 may also be realized by a DSP, hardware circuitry, etc.

<AI/ML for NR air interface>
The AI (artificial intelligence)/ML (machine learning) for air interface framework discussed by 3GPP will be briefly explained using Figure 8. This framework consists of Data Collection (300), Model Training (301), Management (302), Inference (303), and Model Storage (304). A machine learning model generated and trained using the framework of Figure 8 is called an AI/ML model, or simply a trained model.

Data Collection (300) has the function of collecting data and providing training data (Training Data) to Model Training (301), management data (Management Data) to Management (302), and inference data (Inference Data) to Inference (303).

Model Training (301) has the function of training, verifying, and testing AI/ML models. Model Training may also generate performance indicators for the model performance testing procedure. It may also perform pre-processing, cleaning, formatting, and transformation of Training Data. Note that building the AI/ML model itself while training is sometimes referred to as learning, but in this invention, the terms are used interchangeably. Model Training has the function of storing trained, verified, and tested AI/ML models, or updated AI/ML models, in Model Storage (304).

Management (302) has the functionality to manage and monitor the execution of AI/ML models, including activation, deactivation, switching, and fallback. Monitoring an AI/ML model means conducting performance monitoring to ensure that appropriate inferences (predictions) are being made based on the data input from Data Collection and Inference. In other words, Management evaluates the degree of discrepancy between the output data from Inference and the correct data.

Management outputs information (Management Instruction) necessary for managing the functions of Inference (303) to Inference. Management Instructions are commands that indicate, for example, activation, deactivation, switching, and fallback of AI/ML models. It also outputs a Model Transfer/Delivery Request to Model Storage (304) to request the transfer/delivery of AI/ML models. It also outputs a Performance Feedback/Retraining Request to Model Training (301) to train (retrain) and update AI/ML models.

Inference (303) has the function of providing output from a process that applies an AI/ML model when inference data provided by Data Collection (300) is used as input. It may also perform pre-processing, cleaning, formatting, and transformation of the inference data. It also outputs data (inference output) that is used by Management to monitor the AI/ML model.

Model Storage (304) has the function of storing trained/updated AI/ML models used in Inference. Model Storage (304) has the function of delivering AI/ML models to Inference (303) (Model Transfer/Delivery).

Here, the method for generating the trained model performed in Model Training (301) may be any method. For example, the trained model may acquire data on cell measurement values, the amount of fluctuation in measurement values over time, frequency information, the terminal's moving speed, etc. as training data, and output the measurement results of the cell after a certain time has passed (i.e., reception quality) as a predicted value using these as training data. The trained model used may be generated outside the terminal device 10 (for example, the base station device 20 or other external computing device) and transferred to the terminal device 10. Furthermore, the learning algorithm applied to the training, education, and reinforcement of the learning model may be any method that obtains the expected output, and may be, for example, a convolutional neural network, a multilayer neural network, a deep neural network, or a machine learning algorithm implemented using distributed computing. Supervised learning is preferable as the learning method, but unsupervised learning is also acceptable.

Note that some or all of the functions shown in Figure 8 can be executed by the terminal device 10, the base station device 20, or other devices. In other words, Figure 8 illustrates an overview of each function and their relationship with respect to the lifecycle of a machine learning model, and does not impose any restrictions on the location where the functions are executed, nor does it impose any restrictions on the input and output of data.

<Measurement settings and measurement report>
The base station device 20 notifies (configures, specifies, transmits) information regarding measurement configuration to the terminal device 10, thereby causing the terminal device 10 to measure frequencies (e.g., NR and/or EUTRA frequencies). Note that the information regarding measurement configuration is notified, for example, by an RRC message (e.g., RRCReconfiguration). Note that the information regarding measurement configuration may be referred to as measurement configuration, and hereinafter, the information regarding measurement configuration will be referred to as measurement configuration.

The measurement configuration includes at least the following parameters:
(1) Measurement object(s)
The measurement target includes information about a target on which the terminal device 10 performs measurements, and multiple targets can be set in a list format. The base station device 20 can indicate intra-frequency measurements, inter-frequency measurements, and inter-RAT (Radio Access Technology) E-UTRA measurements as measurement targets. In the case of inter-system EUTRA measurements, EUTRA frequencies are set as the measurement targets.

The base station device 20 can also include in the measurement objects a list of cells to which a cell-specific offset is assigned, a block cell list, and an allowed cell list. A cell-specific offset is an offset value added to the measurement result during measurement, a block cell list is a list indicating cells that are not applicable (non-target) for event evaluation (described below) or measurement reporting, and an allowed cell list is a list indicating cells that are applicable (target) for event evaluation or measurement reporting. To manage measurement objects, the base station device 20 sets a measurement object identifier (measObjectId) for each measurement object.

(2) Reporting configuration(s)
The reporting configuration includes information related to a measurement report, and one or more reporting configurations are set for each measurement target in a list format. To manage the reporting configurations, the base station device 20 sets a reporting configuration identifier (reportConfigId) for each reporting configuration.

(3) Measurement identity(ies)
The measurement identifier (measId) is an identifier for linking (associating, relating) one measurement object identifier (measObjectId) with one reporting configuration identifier (reportConfigId). Multiple measurement identifiers can be set in a list format. The measurement identifier may link multiple reporting configurations to one measurement object, or multiple measurement objects may be linked to the same reporting configuration. The measurement identifier is transmitted in a measurement report to report a measurement event that satisfies the trigger condition to the base station device 20.

With regard to NR measurement targets, the terminal device 10 measures and reports on the serving cell, listed cells, and detected cells. Listed cells are cells included in a list notified by the base station device 20. Detected cells refer to other cells that the terminal device 10 has independently detected.

The measured cell quality (reception quality, measurement quality) is calculated by measuring the synchronization signal block (SSB) or the channel state information reference signal (CSI-RS). Cell quality can be expressed using RSRP (Reference Signal Received Power), RSRQ (Reference Signal Received Quality), RSSI (Received Signal Strength Indicator), SINR (Signal to Interference plus Noise Ratio), or path loss.

The measurement events (Measurement event(s)) evaluated by the terminal device 10 are specified by the base station device 20. Measurement events are specified in the report settings and managed by an event identifier (eventId). When a measurement event is triggered (established), the terminal device 10 generates a measurement report message (Measurement Report) and transmits it to the base station device 20. The condition (measurement type) indicating the trigger for transmitting the measurement report message is either a periodic report or an event triggered report (Event triggered), and either one of these is specified by the base station device 20.

For each measurement event, the applicable cell to be evaluated is specified. For example, the applicable cell for event A1 is the serving cell. Similarly, the applicable cell for event A3 is a cell (neighboring cell) detected on the frequency to be measured that is linked to the reporting configuration that includes event A3.

The terminal device 10 initiates the measurement reporting procedure when the measurement type is an event-triggered report, the measurement results meet the conditions indicated by the measurement event, and continue to meet the conditions for a predetermined period of time thereafter. In other words, the measurement reporting procedure is initiated when the measurement results of the cell to be measured satisfy (are established) the measurement event corresponding to the event identifier specified in the reporting configuration included in the measurement configuration, and the measurement event continues to be satisfied for a predetermined period of time. At this time, the terminal device 10 reports the measurement results of the cell corresponding to the measurement identifier that satisfied the measurement event.

Here, the reception quality of the serving cell is defined as Mp, the reception quality of the surrounding cell as Mn, the frequency offset corresponding to the serving frequency as Ofp, the frequency offset corresponding to the frequency of the surrounding cell as Offn, the cell-specific offset corresponding to the serving cell as Ocp, the cell-specific offset corresponding to the surrounding cell as Ocn, the event-specific offset value as Off, the hysteresis value as Hys, and the quality-based threshold as Thresh (Thresh1, Thresh2). The base station device 20 transmits these parameters as part of the measurement configuration to the terminal device 10 using an RRC message. The base station device sets a parameter TTT (Time To Trigger) indicating the length of a predetermined time for the establishment of a measurement event in the terminal device 10.

If the cell measurement results after filtering (L3 filtering) for averaging/smoothing the measurement results satisfy Equation 1, the terminal device 10 determines that the event entering condition for event A3 is met. Similarly, if the measurement results satisfy Equation 2, the terminal device 10 determines that the event leaving condition for event A3 is met.

[Formula 1] Mn + Offn + Ocn - Hys > Mp + Ofp + Ocp + Off

[Equation 2] Mn + Ofn + Ocn + Hys < Mp + Ofp + Ocp + Off

<Conditional handover>
A terminal device 10 in a communication state moves within a cell formed by a base station device 20 using handover or conditional handover (CHO). In conditional handover, cell setting information specifying a candidate cell (target cell) as a handover destination and trigger conditions (measurement event types (measurement event, measurement report event)) for handover (conditional handover) are notified in advance from the base station device 20 to the terminal device 10. The measurement event (trigger condition) specified in the conditional handover setting is also referred to as an event condition (Conditional Event).

At this time, the base station device 20 can configure a maximum of eight candidate cells (i.e., a maximum of eight candidate cell configurations) for the terminal device 10. The terminal device 10 measures the serving cell and surrounding cells. The terminal device 10 also evaluates measurement events based on trigger conditions notified by the base station device 20. Hereinafter, one or more pieces of cell configuration information and trigger conditions are collectively referred to as a conditional handover configuration. The conditional handover configuration includes candidate cells and other necessary cell configurations, and is specified in the form of one or more lists. Here, the measurement target cell is a candidate cell included in the conditional handover configuration, and is identified by a physical cell identifier (PCI). In other words, the terminal device 10 considers the cell with the physical cell identifier specified in the RRC message (RRCReconfiguration) included in the conditional handover configuration to be the measurement target cell.

The base station device 20 and the terminal device 10 each identify and manage conditional handover settings using a handover condition reconfiguration identifier (CondReconfigId). The base station device 20 and the terminal device 10 can add, delete, or change each conditional handover setting corresponding to a handover condition reconfiguration identifier. In addition, the handover condition reconfiguration identifier (CondReconfigId) can specify an event condition by linking it to a measurement identifier (measId) included in the measurement setting.

When the trigger condition is met (the conditional handover condition is continuously satisfied for the TTT interval), the terminal device 10 applies the cell configuration of the candidate cell corresponding to the event condition as the handover destination cell. In other words, after the conditional handover is successful, cell configurations corresponding to other cells are no longer necessary. Therefore, a terminal device for which the conditional handover is successful autonomously deletes cell configurations corresponding to cells other than the destination cell.

Other examples of conditional handover events include quality-based event condition A3, event condition A4, and event condition A5. The conditions for achieving and leaving event condition A3 are the same as those for the corresponding measurement event, event A3, and the conditions for achieving and leaving event condition A4 and event condition A5 are the same as those for the corresponding events A4 and A5, respectively.

Taking the above points into consideration, embodiments of the present invention will be described with reference to the drawings. Note that in describing embodiments of the present invention, if specific descriptions of well-known functions or configurations related to the embodiments of the present invention obscure the gist of the embodiments of the present invention, such detailed descriptions will be omitted.

First Embodiment
4 and 5 are diagrams showing an example of fluctuations in cell reception quality predicted by the prediction unit 113 of the terminal device 10 according to the first embodiment and the corresponding relationship between the corresponding measurement reports. The horizontal axis represents the fluctuations over time, and the vertical axis represents the fluctuations in reception quality.

FIG. 6 is a diagram showing an example of the relationship between the prediction unit 113 of the terminal device 10 and the input data and output data of a trained model executed by the prediction unit 113. A trained model (trained model) that has already been trained is input to the prediction unit 113. The input trained model may be selected and set (notified, specified) by the base station device 20, or may be selected autonomously by the terminal device 10. At this time, multiple trained models may be selected, or a single suitable trained model may be selected. If a trained model has already been selected, the prediction unit 113 may switch the trained model.

Furthermore, the terminal device 10 activates/deactivates the trained model. The activation/deactivation of the trained model may be selected and set (notified, specified) by the base station device 20, or may be selected autonomously by the terminal device 10. The terminal device 10 and base station device 20 may each assign a model identifier (Model ID) to each trained model and manage them. The terminal device 10 may use a different trained model for each measurement event and/or measurement quantity (RSRP, RSRQ, etc.). The base station device 20 may instruct the terminal device 10 to use a different trained model for each measurement event and/or measurement quantity (RSRP, RSRQ, etc.).

The prediction unit 113 receives as input data (cell measurement results) representing the cell reception quality measured by the terminal device 10. The trained model activated and operating in the prediction unit 113 outputs data (cell prediction results) representing a predicted value of the fluctuation in reception quality after a predetermined time (e.g., time t) has elapsed for each of the input cell reception qualities. For example, if the measurement results corresponding to cell 0, cell 1, ..., cell n (n is a natural number) are m0, m1, ..., mn, the output predicted values will be e0, e1, ..., en. The predicted value may be a signed difference value from the input indicating the degree of fluctuation in the cell reception quality, or it may be the absolute value of the same measurement quantity, or it may be the absolute value of a measurement quantity different from the predicted value. For example, RSRP may be input as the cell reception quality, and a predicted value of RSRQ may be output as the output.

As described above, the output predicted value is the reception quality of each cell after the time t of each input value. Here, time t may be the TTT set for the measurement event, a time specified by the base station device 20, or a uniquely determined fixed value (e.g., 100 microseconds). Alternatively, time t may be scaled at the speed of the terminal device 10, or may be a different value for each cell. Furthermore, by specifying multiple values, multiple predicted values with different prediction times may be output for a single input.

The terminal device 10 in Figures 4 and 5 measures multiple cells (cell A, cell B, cell C) belonging to one or more base station devices 20. Figures 4 and 5 show an example in which the cell measurement results in the terminal device 10 are input into a trained model, and the output cell prediction results are illustrated as temporal fluctuations. The trained model used by the terminal device 10 is generated from, for example, training data such as physical cell ID information, fluctuations in reception quality of multiple cells, frequency information of the cell to be measured, the movement speed of the terminal device 10, location information of the terminal device 10 and base station device 20, non-line-of-sight physical cell IDs, transmission power of the base station device 20, weather, and the amount of interference between terminal devices 10. By inputting the reception quality of a cell, the trained model outputs the reception quality of the input cell after a predetermined time has elapsed, or the amount of fluctuation in reception quality.

At the start of Figures 4 and 5, the terminal device 10 is in connected mode (connected state) and is communicating with the base station device 20, with cell A as the serving cell. Cells B and C are neighboring cells that are the subject of measurement. The base station device 20 also sets a measurement setting in the terminal device 10 that evaluates a measurement event for cell B or cell C. At least event A3, which compares the reception quality of the serving cell and neighboring cells, is set as the measurement event.

The terminal device 10 in Figure 4 is instructed by the base station device 20 whether or not to perform event evaluation using the cell prediction result, which is the output of the trained model. In other words, the base station device 20 instructs the terminal device 10 whether or not to activate the trained model and trigger a measurement event using the output cell prediction result. The base station device 20 determines whether or not to perform event evaluation using the cell prediction result in the terminal device 10 based on the UE Capability message received from the terminal device 10.

By using the cell prediction results obtained from the trained model, the terminal device 10 can notify the evaluation results of the measurement event before actually measuring the cell, making it possible to prevent handover failures due to delays or failures in reporting measurement events related to handover, and is expected to improve the handover success rate. The base station device 20 can receive reports of the establishment of measurement events based on cell prediction results earlier than they actually are, and future cell prediction results can be reported, making it possible to accurately determine whether or not to perform a handover, which is expected to improve the handover success rate.

When using cell prediction results, the terminal device 10 reports (transmits) a measurement event that has occurred to the base station device 20 by adding information indicating whether the measurement event is a measurement event that used the cell prediction results. For example, the terminal device 10 may transmit a measurement report message that differs from conventional ones, may add a one-bit identifier to the measurement report message, or may add other identifiable information before reporting.

For example, the terminal device 10 may add the predicted cell reception quality (second reception quality, cell prediction result) to the measurement report message in addition to the actually measured cell reception quality (first reception quality, cell measurement result). The predicted cell reception quality to be added may be the measurement target cell of the measurement event, the serving cell, or a neighboring cell, or a combination of these. Alternatively, the base station device 20 may specify cell information to be predicted (e.g., a physical cell ID). The predicted cell reception quality is the cell reception quality after a predetermined time has elapsed from the current time. The predetermined time may be the same as the TTT set in the measurement event, or a value specified by the base station device 20.

Time T01 indicates the time when the reception quality of cell A falls below that of cell C based on the cell prediction results. In other words, it indicates the time when the entering condition for event A3 is met for cell C. Note that each reception quality takes into account various parameters used to evaluate measurement events, such as the frequency offset notified in the measurement settings, cell-specific offset, event-specific offset value, and hysteresis value.

Time T02 indicates the time at which the terminal device 10 determines that the event establishment condition for event A3 has been satisfied for a predetermined period of time from time T01. In other words, this means that, as the output of the trained model, the cell prediction result for cell C exceeds the cell prediction result for cell A between time T01 and time T02, and the terminal device 10 predicts that event A3 will be established for cell C. The predetermined period of time may be, for example, TTT, or may be based on information indicating a time length specified by the base station device 20. Here, if the terminal device 10 at time T01 can output (predict) the reception quality of each cell at time T02 using the trained model, it triggers the corresponding measurement event at time T01 without waiting for time T02, and transmits a measurement report message to the base station device 20.

At this time, if the terminal device 10 predicts the cell's reception quality from time T02 onwards from the output results of the trained model, additional prediction information regarding the cell's reception quality may be included in the measurement report message and transmitted. Examples of additional prediction information include information indicating that a handover of the source cell (cell A) may occur again after handover to the target cell (cell C) (so-called ping-pong), information indicating the possibility of handover failure or the magnitude of the possibility of handover failure, information indicating the time when the target cell's leaving condition will be met, and information indicating the predicted duration of stay in the target cell after handover. The base station device 20 may individually configure the terminal device 10 as to which additional prediction information to report.

Furthermore, the terminal device 10 evaluates the degree of deviation between the predicted value and the actual measurement value and verifies the prediction accuracy. As a result, if it is determined that the predicted value included in the measurement report message (first measurement report message) transmitted at time T01 is incorrect (the deviation from the predicted value is within an acceptable range), it may transmit a measurement report message (second measurement report message) based on the actual measurement result. At this time, the terminal device 10 transmits the second measurement report message including at least the measurement result for the cell ID that is the same as the measurement identifier reported in the first measurement report message.

A deviation from the predicted value may be determined when the difference between the predicted value and the actual measurement value is equal to or greater than a certain threshold, or when the cumulative difference between the predicted value and the actual measurement value is equal to or greater than a certain threshold. In this case, the threshold may be set in advance as an evaluation parameter by the base station device 20 in the terminal device 10. If the terminal device 10 determines that the predicted value included in the measurement report message transmitted at time T01 is correct (the deviation from the predicted value is outside the allowable range), it does not take any particular action and continues making judgments based on the prediction.

The terminal device 10 may constantly monitor the predicted value and transmit the second measurement report message when it determines that the predicted value is incorrect, or may make this determination each time a measurement report message is transmitted, or may make this determination based on information set by the base station device 20. For example, the terminal device 10 may transmit the second measurement report message periodically according to a set time interval, or may transmit the second measurement report message based on the number of times the first measurement report message has been transmitted (for example, transmitting the second measurement report message after transmitting the first measurement report message n times (n is a value set by the base station device 20)), or may transmit the second measurement report message aperiodically based on instructions from the base station device 20.

Aperiodic instructions from the base station device 20 may be notified using downlink control information included in L1 signaling (PDCCH), using MAC control elements, or using individual or common RRC messages.

Time T03 indicates the time when the reception quality of cell A falls below that of cell B based on the cell prediction result. In other words, it indicates the time when the entering condition of event A3 is met for cell B. Furthermore, time T04 indicates the time at which terminal device 10 determines that the entering condition of event A3 has been met for a predetermined period of time from time T03. In other words, this means that, as the output of the trained model, the cell prediction result of cell B exceeds the cell prediction result of cell A between time T03 and time T04, and terminal device 10 predicts that event A3 will be met for cell B.

At this time, if the terminal device 10 predicts the cell's reception quality from time T04 onwards from the output results of the trained model, it may transmit additional prediction information regarding the cell's reception quality by including it in the measurement report message. The additional prediction information may be the same as that described above. Alternatively, as shown in Figure 4, if the predicted stay time after handover to cell B continues for a certain period of time, the terminal device 10 may not transmit additional prediction information.

The period between time T04 and time T05 shows a state in which the serving cell of terminal device 10 is cell B, and the surrounding cells are cell A and cell C. Time T05 indicates the time when the reception quality of cell B falls below that of cell A based on the cell prediction result. In other words, it indicates the time when the entering condition for event A3 is met for cell A. Furthermore, time T06 indicates the time at which terminal device 10 determines that the entering condition for event A3 has been met for a predetermined period of time from time T05. In other words, this means that, as the output of the trained model, the cell prediction result for cell A exceeds the cell prediction result for cell B from time T05 to time T06, and terminal device 10 predicts that event A3 will be met for cell A.

At this time, if the terminal device 10 predicts the reception quality of the cell from time T06 onwards from the output results of the trained model, additional prediction information regarding the reception quality of the cell may be included in the measurement report message and transmitted. The additional prediction information may be the same as that described above. Furthermore, as shown in FIG. 4, the additional prediction information may include information indicating that the reception quality of another surrounding cell (cell C) will exceed that of the target cell after handover to the target cell (cell A), information indicating the predicted time when the reception quality of another surrounding cell (cell C) will exceed that of the target cell, information indicating the predicted time when the reception quality of another surrounding cell (cell C) will exceed that of the source cell (cell B), etc.

The terminal device 10 in Figure 5 differs from Figure 4 in that the base station device 20 instructs the terminal device 10 whether or not to report additional cell prediction results for the measurement event being reported. In other words, the base station device 20 instructs the terminal device 10 to perform event evaluation based on the actually measured cell reception quality, while also instructing the terminal device 10 whether or not to activate the trained model and add the output cell prediction results when reporting the measurement event. The base station device 20 determines whether or not to report cell prediction results in the terminal device 10 based on the UE Capability message received from the terminal device 10.

By notifying the terminal device 10 of the cell prediction results obtained from the trained model, it becomes possible for the base station device 20 to perform appropriate mobility management, which is expected to improve the handover success rate. In addition to reporting the establishment of a measurement event, the base station device 20 receives from the terminal device 10 judgment information that can be used for mobility management at the base station device 20, which enables the base station device 20 to accurately determine whether or not to perform a handover, which is expected to improve the handover success rate.

In addition to the actually measured cell reception quality, the terminal device 10 adds the predicted cell reception quality to the measurement report message and reports it. The predicted cell reception quality to be added is either the cell being measured for the measurement event, the serving cell, or a neighboring cell, or a combination of these. The predicted cell reception quality is the cell reception quality after a predetermined time has elapsed from the current time. The predetermined time may be the same as the TTT set for the measurement event, or may be based on information indicating the length of time specified by the base station device 20.

Time T11 indicates the time when the reception quality of cell A falls below that of cell C based on the actual measured reception quality of the cells. In other words, it indicates the time when the entering condition for event A3 is met for cell C. Note that each reception quality takes into account various parameters used to evaluate measurement events, such as the frequency offset notified in the measurement settings, cell-specific offset, event-specific offset value, and hysteresis value.

Time T12 indicates the time at which the terminal device 10 determines that the event establishment condition for event A3 has been satisfied for a predetermined period of time from time T11. In other words, this means that from time T11 to time T12, the reception quality of cell C exceeds the reception quality of cell A, and the terminal device 10 determines that event A3 has been established for cell C. The predetermined period of time is, for example, TTT.

Here, if the terminal device 10 at time T12 is able to output (predict) the reception quality of each cell at time T13 using the trained model, it will include the cell prediction result at time T13 in a measurement report message triggered and reported at time T12 and transmit it to the base station device 20. The time interval from time T12 to time T13 (e.g., time t2) may be, for example, TTT, or may be based on information indicating a time length specified by the base station device 20. The added cell prediction result may be the predicted value reported as is, or a difference value from the reception quality of the cell being reported may be calculated and reported, or the results of other detected neighboring cells with a certain quality or higher may be reported, or in addition to these, granularity information indicating the range of error in the cell prediction result may be included in the report.

Alternatively, when the terminal device 10 predicts the cell's reception quality from time T12 onwards from the output results of the trained model, additional prediction information regarding the cell's reception quality may be included in the measurement report message and transmitted. The additional prediction information may be, for example, information indicating that a handover of the source cell (cell A) may occur again after handover to the target cell (cell C) (so-called ping-pong), information indicating the possibility of handover failure or the magnitude of the possibility of handover failure, information indicating the time when the target cell's leaving condition will be met, information indicating the predicted stay time in the target cell after handover, etc. The base station device 20 may individually configure the terminal device 10 as to which prediction information to report additionally.

Furthermore, the terminal device 10 may determine that it should not transmit a measurement report message based on the actual measurement results, based on the predicted value predicted at time T13. The decision to transmit the measurement report message may also be based on the additional prediction information described above. When using the additional prediction information, threshold information (such as a threshold indicating a time or percentage) used for the decision is set in the terminal device 10 by the base station device 20. When it is determined that it should not transmit a measurement report message, the terminal device 10 may cancel the transmission of the measurement report message, suppress the transmission of the measurement report message, suspend the measurement identifier corresponding to the measurement event, stop evaluating the reporting settings corresponding to the measurement event, or consider the measurement event to not satisfy the event establishment condition (not be triggered).

The terminal device 10 may constantly monitor the predicted value and transmit a measurement report message based on the actual measurement results when it determines that the predicted value is incorrect. The accuracy of the predicted value may be determined in the same manner as described above. If the measurement report message was not transmitted based on the determination to transmit a measurement report message, the message may further include information on the time when the measurement event actually occurred and the reception quality of the cell. The terminal device 10 may also transmit information to the base station device 20 indicating that it has determined that the predicted value is incorrect.

A terminal device 10 that has decided not to send a measurement report message reports information about the unreported measurement event to the base station device 20. For example, the terminal device 10 may use a UE assistance information message, which is an RRC message. The information included in the RRC message may include, in addition to information indicating the unreported event, information about the measurement event (measurement identifier), information about the time when the measurement event actually occurred, or the reception quality of the cell, and the reason for the decision that the event was not transmitted.

Time T14 indicates the time when the reception quality of cell A falls below that of cell B based on the actual measured reception quality of the cells. In other words, it indicates the time when the entering condition of event A3 is met for cell B. Furthermore, time T15 indicates the timing at which terminal device 10 determines that the entering condition of event A3 has been met continuously for a predetermined time from time T14. In other words, this means that from time T14 to time T15, the reception quality of cell B exceeds the reception quality of cell A, and terminal device 10 determines that event A3 has been met for cell B. The predetermined time is, for example, TTT.

Here, if the terminal device 10 at time T15 is able to output (predict) the reception quality of each cell at time T16 using the trained model, it will include the cell prediction result at time T16 in a measurement report message triggered and reported at time T15 and transmit it to the base station device 20. The time interval from time T15 to time T16 (e.g., time t2) may be, for example, TTT, or may be based on information indicating a time length specified by the base station device 20. The added cell prediction result may be the same as that described above.

If the predicted value included in the measurement report message sent at time T15 is correct, the terminal device 10 does nothing and continues making judgments based on the prediction. As shown in Figure 5, if the predicted stay time after handover to cell B continues for a certain period of time (for example, until time T16), the terminal device 10 may stop making judgments about the accuracy of the predicted value included in the measurement report message and resume normal operation.

The period between time T16 and time T17 shows a state in which the serving cell of terminal device 10 is cell B, and the surrounding cells are cell A and cell C. Time T17 shows the time when the reception quality of cell B falls below that of cell A. In other words, it shows the time when the entering condition for event A3 is met for cell A. Furthermore, time T18 shows the timing at which terminal device 10 determines that the entering condition for event A3 has been met for a predetermined period of time from time T16. In other words, this means that the reception quality of cell A exceeds the reception quality of cell B from time T17 to time T18, and terminal device 10 determines that event A3 is met for cell A.

Here, if the terminal device 10 at time T18 can output (predict) the reception quality of each cell at time T19 using a trained model, the measurement report message triggered and reported at time T18 may include the cell prediction result at time T19 or additional prediction information and transmit it to the base station device 20. The additional prediction information may be the same as that described above. Furthermore, as shown in FIG. 5, additional prediction information may be transmitted, such as information indicating that the reception quality of another surrounding cell (cell C) will exceed that of the target cell after handover to the target cell (cell A), information indicating the predicted time when the reception quality of another surrounding cell (cell C) will exceed that of the target cell, information indicating the predicted time when the reception quality of another surrounding cell (cell C) will exceed that of the source cell (cell B), and the cell ID of a cell recommended as the target cell (cell C in the case of time T19).

Figure 7 is a sequence diagram illustrating an example of RRC messages exchanged between the terminal device 10 and the base station device 20. Although not shown, the diagram begins with the wireless connection (RRC setup) procedure between the terminal device 10 and the base station device 20 being completed, and the terminal device 10 transitioning to a communicating state (connected state, also referred to as an RRC Connected state). Furthermore, the terminal device 10 generates an RRC message (UE Capability message) and transmits it to the base station device 20 in order to notify the base station device 20 of its own wireless capabilities.

The terminal device 10 may transmit information such as the accuracy of the terminal device's 10 location information (positioning support information), information indicating the maximum time that can be predicted when using a trained model, and the maximum number of cells that can be predicted in a UE Capability message.

The base station device 20 transmits a first RRC message (RRC message 1 in the figure) to the terminal device 10 (step S100). The first RRC message is, for example, an individual RRC message such as an RRCReconfiguration message. The first RRC message is transmitted including a measurement setting for setting a measurement event for the terminal device 10. The first RRC message may also include a trained model setting that instructs activation, deactivation, switching, or fallback of the trained model used by the terminal device 10. When instructing activation, deactivation, or switching of a trained model, the base station device 20 notifies the identifier (Model ID) of the target trained model. The base station device 20 may also instruct activation or deactivation at the same time as switching the trained model.

In response to the first RRC message, the terminal device 10 transmits a second RRC message (RRC message 2 in the figure) to the base station device 20 (step S101). The second RRC message is, for example, an RRCReconfigurationComplete message. The second RRC message is also used by the base station device 20 to notify that activation, deactivation, switching, or fallback of a trained model specified by the base station device 20 has been successfully completed.

The terminal device 10, for which the measurement settings have been set and the learned model is activated, transmits a third RRC message (RRC message 3 in the figure) to the base station device 20 based on the measurement settings (step S102). The third RRC message is, for example, a measurement report message. The timing of transmission of the third RRC message by the terminal device 10 and the information contained in the third RRC message are the same as those described in Figures 4 and 5.

Alternatively, the terminal device 10 and the base station device 20 may be configured to operate by combining the operations of Figures 4 and 5. For example, when determining an event establishment condition, the operation of Figure 4 (i.e., evaluating a measurement event using the cell prediction result) may be performed, and when determining an event departure condition, the operation of Figure 5 (i.e., evaluating a measurement event using the cell measurement result and adding the cell prediction result to a report) may be performed, or vice versa. Alternatively, the operation of Figure 4 may be continued normally, and if it is determined that the cell prediction result is incorrect, it may switch to the operation of Figure 5. In other words, if the terminal device 10 and the base station device 20 determine that the accuracy of the output of the trained model in use is low, they fall back to conventional operation that uses actual cell measurement values when evaluating measurement events.

Alternatively, the base station device 20 may explicitly specify which operation to perform in an RRC message, or the operation may be switched using downlink control information or MAC control elements included in L1 signaling (PDCCH).

In this way, according to the first embodiment, the terminal device 10 and the base station device 20 predict the reception quality of the cell using a trained model, and transmit and receive measurement report messages including the predicted results of the reception quality of the cell, thereby improving the performance of mobility management between the terminal device 10 and the base station device 20.

Second Embodiment
The second embodiment will be described. Note that a description of configurations, functions, or procedures common to the first and second embodiments will be omitted. That is, the following mainly describes the differences from the first embodiment.

In the second embodiment, the terminal device 10 and base station device 20 use the cell prediction result, which is the output of the trained model, to evaluate a measurement event (event condition (Conditional Event)) used to trigger a conditional handover (CHO). The terminal device 10 is instructed by the base station device 20 whether or not it is permitted to evaluate an event condition using the cell prediction result, which is the output of the trained model. In other words, the base station device 20 instructs the terminal device 10 whether or not it is permitted to activate the trained model and perform a conditional handover using the output cell prediction result. The base station device 20 determines whether or not to evaluate an event condition using the cell prediction result in the terminal device 10 based on the UE Capability message received from the terminal device 10.

The base station device 20 may instruct the terminal device 10 whether or not to perform either or both of (1) evaluation of a measurement event using the cell prediction result and (2) evaluation of an event condition using the cell prediction result. The instruction may be given using downlink control information included in L1 signaling (PDCCH), a MAC control element, or an individual or common RRC message.

By using the cell prediction results obtained from the trained model, the terminal device 10 is able to evaluate event conditions before actually measuring the cell, which is expected to improve the success rate of conditional handover. Furthermore, the terminal device 10 is able to accurately determine whether or not to perform a conditional handover, which is expected to improve the success rate of conditional handover and reduce the frequency of radio link failures after a conditional handover.

For example, the terminal device 10 evaluates the event condition using the reception quality of the target cell after a predetermined time has elapsed from the current time (cell prediction result), and if the event condition set based on the cell prediction result is met, it performs a conditional handover to the target cell. The predetermined time may be the same as the TTT set for the measurement event, or may be a value specified by the base station device 20.

When the terminal device 10 executes a conditional handover using the cell prediction result, it reports (transmits) information indicating whether or not the cell prediction result was used to the base station device 20. For example, the terminal device 10 may add information indicating whether or not the cell prediction result was used to an RRC message (RRCReconfigurationComplete) that notifies the completion of the execution of the conditional handover.

Alternatively, the terminal device 10 may evaluate the event condition based on the actually measured reception quality of the target cell (first reception quality, cell measurement result), and if the set event condition is met, determine whether to perform conditional handover based on the predicted reception quality of the target cell (second reception quality, cell prediction result). The cell prediction result used is the cell prediction result obtained after a predetermined time has elapsed since the time the event condition was met. The predetermined time may be the same as the TTT set in the event condition, or may be a value specified by the base station device 20.

The terminal device 10 may determine not to perform a conditional handover based on the cell prediction result if a radio link failure is predicted after the conditional handover; more specifically, if the reception quality of other surrounding cells is predicted to exceed that of the target cell within a short time after handover to the target cell, if a handover of the source cell is performed again after handover to the target cell, if the reception quality of the target cell falls below a predetermined value after a predetermined time, if the event leaving condition of the target cell is satisfied, or if the predicted stay time in the target cell after handover is less than a predetermined time. Each of the parameters used in the above determination may be notified to the terminal device 10 in advance by the base station device 20.

If the terminal device 10 determines not to perform a conditional handover, it may transmit a measurement report message including the established measurement identifier to the base station device 20. Alternatively, it may use another RRC message (e.g., UE assistance information) to transmit information indicating that a conditional handover will not be performed and the reason for this determination.

In this way, according to the second embodiment, the terminal device 10 and the base station device 20 predict the cell reception quality using a trained model and perform conditional handover based on the predicted cell reception quality, thereby improving the performance of mobility management between the terminal device 10 and the base station device 20.

Note that the above-described embodiments are intended to facilitate understanding of the present invention and are not intended to limit the present invention. The present invention may be modified or improved without departing from its spirit, and the present invention also includes equivalents.

<Hardware configuration of each device in each embodiment>
The hardware configuration of each device in the wireless communication system of each embodiment will be described with reference to FIGS.

Figure 9 is a diagram showing an example of the hardware configuration of terminal device 10. As shown in Figure 9, terminal device 10 has, as hardware components, an RF (Radio Frequency) circuit 32 equipped with an antenna 31, a CPU (Central Processing Unit) 33, and memory 34. Furthermore, terminal device 10 may have a display device such as an LCD (Liquid Crystal Display) connected to CPU 33. Memory 34 includes at least one of RAM (Random Access Memory) such as SDRAM (Synchronous Dynamic Random Access Memory), ROM (Read Only Memory), and flash memory, and stores programs, control information, and data signals.

The correspondence between the functional configuration of the terminal device 10 shown in FIG. 2 and the hardware configuration of the terminal device 10 shown in FIG. 9 will be explained. The transmitting/receiving antenna unit 19, transmitting unit 17, and receiving unit 15 are realized, for example, by an RF circuit 32, or an antenna 31 and an RF circuit 32. The control unit 13 and processing unit 11 are realized, for example, by a CPU 33, memory 34, a digital electronic circuit (not shown), etc. Examples of digital electronic circuits include an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), and an LSI (Large Scale Integration).

FIG. 10 is a diagram showing an example of the hardware configuration of a base station device 20. As shown in FIG. 10, the base station device 20 has, as hardware components, an RF circuit 42 equipped with an antenna 41, a CPU 43, a DSP 44, a memory 45, and a network IF (Interface) 46. The CPU 43 is connected via a bus to enable input and output of various signals and data signals. The memory 45 includes at least one of a RAM such as SDRAM, a ROM, and a flash memory, and stores programs, control information, and data signals.

The correspondence between the functional configuration of the base station device 20 shown in FIG. 3 and the hardware configuration of the base station device 20 shown in FIG. 10 will be explained. The transmitting/receiving antenna unit 29, transmitting unit 27, and receiving unit 25 are realized, for example, by an RF circuit 42, or an antenna 41 and an RF circuit 42. The control unit 23 and processing unit 21 are realized, for example, by a CPU 43, a DSP 44, a memory 45, a digital electronic circuit (not shown), etc. Examples of digital electronic circuits include an ASIC, an FPGA, and an LSI.

REFERENCE SIGNS LIST 1 wireless communication system 10 terminal device 20 base station device 30 core network 11, 21 processing units 13, 23 control units 15, 25 receiving units 17, 27 transmitting units 19, 29 transmitting and receiving antenna units 31, 41 antennas 32, 42 RF circuits 33, 43 CPU
34, 45 Memory 44 DSP
46 Network IF
111, 211 Radio resource processing unit 113, 213 Prediction unit 300 Data Collection
301 Model Training
302 Management
303 Inference
304 Model Storage

Claims (12)

A terminal device that communicates with a base station device,
a receiving unit that receives information about a measurement configuration including a measurement event for measuring the reception quality of a cell and information indicating permission to use a cell prediction result from the base station device;
a prediction unit that outputs a prediction of fluctuations in the reception quality of the cell as a cell prediction result;
A terminal device comprising: a transmitting unit that reports to the base station device, based on information indicating permission to use the cell prediction result, the measurement event, a first reception quality actually measured for the measurement event, and a second reception quality based on the cell prediction result. The terminal device according to claim 1, further comprising a prediction unit that inputs the first reception quality of the cell into a trained learning model that has undergone machine learning to predict fluctuations in the reception quality of the cell, and obtains the second reception quality of the cell from the trained learning model. The terminal device according to claim 1, wherein, when use of the cell prediction result is permitted and when the first reception quality satisfies the condition for the measurement event for a predetermined time, the terminal device transmits a measurement report message including the first reception quality and the second reception quality of the cell related to the measurement event. The terminal device of claim 3, wherein even if the first reception quality satisfies the condition for the measurement event to be established for a predetermined period of time, if it predicts that handover to the cell is inappropriate, the establishment of the measurement event is suppressed. The terminal device of claim 1, wherein, when use of the cell prediction result is permitted, the measurement event is not evaluated using the first reception quality, and when the second reception quality satisfies the condition for the measurement event for a predetermined time, the terminal device transmits a measurement report message including the first reception quality and the second reception quality of the cell related to the measurement event. The terminal device according to claim 1, wherein, when a conditional handover setting corresponding to the measurement event is configured and the second reception quality in the measurement target cell for the conditional handover setting satisfies the establishment condition of the measurement event for a predetermined period of time, the terminal device executes a conditional handover procedure corresponding to the measurement event. A base station device that communicates with a terminal device,
a transmitter that transmits to the terminal device information relating to measurement configuration including a measurement event for measuring the reception quality of a cell and information indicating permission to use a cell prediction result;
a prediction unit that performs control related to prediction of fluctuations in reception quality of the cell, which is output by the terminal device as a cell prediction result;
A base station device comprising: a receiving unit that receives a measurement report message including the measurement event transmitted based on information indicating permission to use the cell prediction result, a first reception quality actually measured by the terminal device for the measurement event, and a second reception quality based on the cell prediction result. The base station device of claim 7, wherein the first reception quality of the cell is input to a trained learning model that has undergone machine learning to predict fluctuations in the reception quality of the cell provided in the terminal device, and the second reception quality of the cell is obtained from the training model. The base station device according to claim 7, wherein an evaluation parameter is set in the terminal device for evaluating the degree of deviation between the first reception quality actually measured by the terminal device and the second reception quality based on the cell prediction result. The base station device according to claim 7, wherein a conditional handover setting corresponding to the measurement event is configured in the terminal device, and execution of the conditional handover procedure based on the cell prediction result is permitted. A method for controlling a terminal device that communicates with a base station device, comprising:
receiving, from the base station device, information on measurement configuration including a measurement event for measuring the reception quality of a cell and information indicating permission to use a cell prediction result;
outputting the prediction of fluctuations in the reception quality of the cell as a cell prediction result;
A control method for a terminal device, which executes a step of reporting to the base station device each of the measurement event, a first reception quality actually measured for the measurement event, and a second reception quality based on the cell prediction result, based on information indicating permission to use the cell prediction result. A method for controlling a base station device that communicates with a terminal device, comprising:
transmitting information regarding measurement configuration including a measurement event for measuring the reception quality of a cell and information indicating permission to use the cell prediction result to the terminal device;
performing control related to prediction of fluctuations in reception quality of the cell, which is output by the terminal device as a cell prediction result;
A control method for a base station device, which executes a step of receiving a measurement report message including the measurement event transmitted based on information indicating permission to use the cell prediction result, a first reception quality actually measured by the terminal device for the measurement event, and a second reception quality based on the cell prediction result.