Terminal device for improving handover performance using artificial intelligence (AI) / machine learning (ML), base station device, and control method

Abstract

Provided is a terminal device that: measures the radio quality of a signal transmitted from a connected base station device; inputs the radio quality acquired by the terminal device in an inference phase to a learned model acquired by machine learning, in which the radio quality acquired in a learning phase is used as an input and that uses, as teacher data, a predetermined value for determining whether or not an event related to handover from a cell provided by the base station device to another cell is presumed to occur after a predetermined period from the timing at which the radio quality is acquired, to determine whether or not the event is presumed to occur after the predetermined period from the timing at which the radio quality is acquired; and transmits a predetermined report to the base station device when the event is presumed to occur after the predetermined period.

Description

Terminal device, base station device, and control method for improving handover performance using artificial intelligence (AI) / machine learning (ML)

[0001] The present invention relates to an advanced handover technique in a cellular communication system.

[0002] In wireless communication systems compliant with the cellular communication standard of the Third Generation Partnership Project (3GPP (registered trademark)), a handover process is defined for switching the base station to which a mobile terminal device is connected, so that the mobile terminal device can continue to communicate with high quality. The handover process is performed, for example, when the wireless quality of a signal transmitted from a base station to which the mobile terminal device is currently connected falls below a predetermined level for a certain period of time, by transmitting a measurement result to the base station, and the base station then instructs the mobile terminal device to perform a handover.

[0003] For example, if the wireless quality of the terminal device further deteriorates during the time between when the wireless quality falls below a predetermined level and when a handover command is transmitted from the base station, the handover process may fail, resulting in a decrease in communication efficiency. Also, since it takes time for the terminal device to detect a more suitable base station to connect to and when a handover command is transmitted from the base station, an opportunity to improve communication efficiency may be missed.

[0004] The present invention provides a technique for enhancing handover processing and improving communication efficiency.

[0005] A terminal device according to one aspect of the present invention comprises: a measurement means for measuring the wireless quality of a signal transmitted from a base station device to which it is connected; a determination means for inputting the wireless quality acquired by the terminal device in the inference phase into a trained model acquired by machine learning, which inputs the wireless quality acquired in the learning phase and uses as training data a predetermined value for determining whether an event related to a handover from a cell provided by the base station device to another cell is estimated to occur a predetermined period from the time the wireless quality was acquired; and a transmission means for transmitting a predetermined report to the base station device if it is estimated that the event will occur after the predetermined period.

[0006] A base station device according to one aspect of the present invention has a receiving means for receiving a predetermined report from a terminal device connected to a cell provided by the base station device, the result of measurement of the wireless quality of the cell by the terminal device in an inference phase being input to a trained model obtained by machine learning, which inputs the result of measurement of the wireless quality of the cell in a learning phase and uses as training data a predetermined value for determining whether an event related to handover from the cell to another cell is estimated to occur a predetermined period of time after the result of the measurement is acquired, indicating that the terminal device has determined that the event is estimated to occur a predetermined period of time after the result of the measurement is acquired; and an instruction means for instructing the terminal device to perform a handover based on the receipt of the predetermined report.

[0007] According to the present invention, the handover process can be enhanced to improve communication efficiency.

[0008] Other features and advantages of the present invention will become apparent from the following description taken in conjunction with the accompanying drawings, in which the same or similar elements are designated by the same reference numerals.

[0009] The accompanying drawings are incorporated in and constitute a part of the specification, illustrate embodiments of the present invention, and together with the description are used to explain the principles of the present invention. Figure 1 is a diagram showing an example of the configuration of a wireless communication system. Figure 2 is a diagram showing an example of the hardware configuration of a base station device and a terminal device. Figure 3 is a diagram showing an example of the functional configuration of a terminal device. Figure 4 is a diagram showing an example of the functional configuration of a base station device. Figure 5 is a diagram showing an example of the flow of processing executed in the wireless communication system.

[0010] Hereinafter, the embodiments will be described in detail with reference to the accompanying drawings. Note that the following embodiments do not limit the scope of the invention as claimed, and not all combinations of features described in the embodiments are necessarily essential to the invention. Two or more of the features described in the embodiments may be combined in any desired manner. Furthermore, the same reference numerals are used to designate identical or similar components, and redundant descriptions will be omitted.

[0011] (System Configuration) FIG. 1 shows an example configuration of a communication system according to this embodiment. This communication system is, for example, a wireless communication system conforming to the Long Term Evolution (LTE) or fifth generation (5G) cellular communication standards of the Third Generation Partnership Project (3GPP (registered trademark)), or their successor standards. This wireless communication system includes a base station device 101 and a terminal device 111. The terminal device 111 establishes a connection with the base station device 101 and performs wireless communication in a cell 121 provided by the base station device 101. The terminal device 111 is assumed to be, for example, portable by a user and to be mobile. If the terminal device 111 moves beyond the range of the cell 121, it will no longer be able to maintain communication in that cell 121. Therefore, for example, the terminal device 111 performs handover to another cell (cell 122 or cell 123) upon the occurrence of a predetermined event, such as a deterioration in communication quality in the currently connected cell 121. Note that the cells 122 and 123 may be provided by a base station device other than the base station device 101, or may be provided by the base station device 101. In other words, the base station device 101 may provide multiple cells.

[0012] Conventionally, the terminal device 111 measures the wireless quality of signals transmitted from the currently connected cell 121 and other adjacent cells (cells 122 and 123), and determines whether an event has occurred based on whether the wireless quality satisfies a predetermined condition. Events are defined in cellular communication standards. Examples of events include event A1, which is determined to have occurred when the wireless quality of the currently connected cell exceeds a predetermined threshold, and event A2, which is determined to have occurred when the wireless quality of the currently connected cell falls below a predetermined threshold. Events also include event A3, which is determined to have occurred when the wireless quality of the adjacent cell becomes higher (by a predetermined offset) than the wireless quality of the currently connected cell. Events also include event A4, which is determined to have occurred when the wireless quality of the adjacent cell exceeds a predetermined threshold, and event A5, which is determined to have occurred when the wireless quality of the currently connected cell falls below a first predetermined threshold and the wireless quality of the adjacent cell exceeds a second predetermined threshold.

[0013] When the terminal device 111 determines that one of the events set by the base station device 101 has occurred, it transmits a predetermined notification to the base station device 101. Then, in response to receiving the predetermined notification, the base station device 101 executes processing for handing over the terminal device 111 from the currently connected cell 121 to another cell (e.g., cell 122 or cell 123). Note that the handover of the terminal device 111 can be performed, for example, by transmitting setting information for communication in an adjacent cell from the base station device 101 to the terminal device 111 before the event occurs, and then transmitting a command from the base station device 101 to the terminal device 111 instructing the handover. Furthermore, after the event occurs, the handover process can be started by transmitting setting information for communication in an adjacent cell from the base station device 101 to the terminal device 111.

[0014] The base station device 101 notifies the terminal device 111 in advance of configuration information indicating the threshold, offset value, and hysteresis value to be used for each event, as well as the time until it is determined that the event has occurred (Time To Trigger). The terminal device 111 determines the occurrence of an event based on this information. For example, the terminal device 111 may determine that the occurrence criterion for Event A1 has been satisfied when the wireless quality measured for the connected cell exceeds a value obtained by adding the hysteresis value to a predetermined threshold notified for determining Event A1. Furthermore, the terminal device 111 may determine that the state in which the occurrence criterion for Event A1 was satisfied has been resolved when the wireless quality measured for the connected cell falls below a value obtained by subtracting the hysteresis value from the predetermined threshold notified for determining Event A1 after the occurrence criterion for Event A1 has been satisfied. Then, when the state in which the occurrence criteria for event A1 are satisfied continues for longer than the time length indicated by TimeToTrigger, the terminal device 111 determines that event A1 has occurred and sends a predetermined report to the base station device 101. The base station device 101 can also notify the terminal device 111 of setting information (reportOnLeave) indicating whether or not to send a predetermined notification when the state in which the event occurred is resolved. For example, when reportOnLeave is set to True, the terminal device 111 can send a predetermined report to the base station device 101 in response to the fact that the occurrence criteria for the event are no longer satisfied after the event has occurred. Note that for other events, similar information is notified to the terminal device 111 in advance (for example, when the base station device 101 and the terminal device 111 are connected), and the terminal device 111 can determine whether or not the event has occurred based on that information.

[0015] Conventionally, handover processing is initiated when the wireless quality measured at that time in the terminal device 111 satisfies one of the above-mentioned events. In this procedure, for example, the wireless quality of the connected cell (serving cell) deteriorates in event A2 or event A3, and a predetermined report is transmitted to the base station device 101 after the event occurs. Then, a handover instruction is transmitted from the base station device 101. Therefore, a certain period of time is required from the deterioration of wireless quality to the execution of handover. Then, during the period from when the terminal device 111 detects the occurrence of the event to when the base station device 101 transmits the handover instruction, the wireless quality may further deteriorate, and the handover instruction may not be received by the terminal device 111.

[0016] In recent years, the application of artificial intelligence (AI) / machine learning (ML) to cellular communication systems has been discussed. Using AI / ML, for example, prediction of whether an event will occur in the future can be performed based on the wireless quality of the currently connected cell. For example, a trained model can be acquired by machine learning using the wireless quality of the cell 121 acquired in the learning phase as input and a predetermined value for determining whether an event related to a handover from the cell 121 to another cell (e.g., cell 122 or cell 123) is predicted to occur a predetermined period after the wireless quality is acquired as training data. When such a trained model is acquired, the terminal device 111 can input the results of measuring the wireless quality of a signal transmitted from the cell 121 in the inference phase to determine whether an event is predicted to occur a predetermined period after the wireless quality is acquired. In this embodiment, the terminal device 111 makes such a determination, and processes such as handover are performed based on the inference of the occurrence of a future event. That is, the terminal device 111 transmits a predetermined report to the base station device 101 based on an event that has not occurred at present but is expected to occur in the future, and the base station device 101 can instruct the terminal device 111 to start handover processing based on the predetermined report, regardless of the current situation. This makes it possible to prevent handover failure due to a decrease in wireless quality in the terminal device 111 during the period from the occurrence of an event until the actual execution of handover.

[0017] Note that a trained model may be defined for each event, or machine learning may be performed so that a type of event that is predicted to occur by one trained model is output. Furthermore, multiple timings after a predetermined period may be set. That is, it may be determined whether an event is predicted to occur at each of multiple future timings. Furthermore, multiple trained models may be prepared for inference about the same event and the same timing, and the base station device 101 may notify the terminal device 111 in advance (e.g., upon connection with the terminal device 111) of information indicating which of the trained models should be used. Note that examples of multiple trained models will be described later.

[0018] Furthermore, the base station device 101 may determine whether to permit the execution of event determination by inference using a trained model, and notify the terminal device 111 of the determination. Furthermore, the terminal device 111 may transmit capability information (UE Capability) including information indicating whether or not the terminal device 111 is capable of executing event determination by inference using a trained model to the base station device 101. The base station device 101 may permit such event determination only for terminal devices 111 that are capable of executing event determination by inference using a trained model. Note that the following description focuses on the cell 121 to which the terminal device 111 is connected, but the same applies to other cells. Note that a different trained model may be generated for each cell, but a trained model common to multiple cells may also be generated.

[0019] Furthermore, the "radio quality" in this embodiment may be, for example, reference signal received power (RSRP), but other indices such as reference signal received quality (RSRQ), signal-to-noise ratio (SNR), and signal-to-noise and interference ratio (SINR) may also be used. However, a common indices are used in the learning phase and inference phase of machine learning. That is, when RSRP is used as input in the learning phase, RSRP is also used as input in the inference phase. Note that when the output of the model is radio quality, the same indices may be used for the input and output of the model, but the input and output may be expressed by different indices, such as when RSRP is used as input and RSRQ is used as output. In one example, RSRP of layer 1 may be used as input and RSRP of layer 3 may be used as output. In addition, the reference signal used for measuring RSRP etc. may be, for example, a synchronization signal (SS) / physical broadcast channel (PBCH) block (SSB) or a channel state information-reference signal (CSI-RS), but other reference signals may also be used.

[0020] Below, several examples of trained models are described. Various trained models can be obtained by setting various predetermined values ​​used as training data in the learning phase. Therefore, below, examples of predetermined values ​​used as training data, examples of expected outputs in trained models, and examples of how the terminal device 111 determines that an event will occur in the future are described.

[0021] The predetermined value used as training data may be, for example, a value indicating whether an event occurrence condition is satisfied a predetermined period after the wireless quality of the cell 121 is acquired in the learning phase. That is, each terminal device that previously communicated through the cell 121 measures the wireless quality of the cell 121, and whether it is determined that any of the above-described events A1 to A5 (or other events such as event A6, event B1, or event B2) occurred a predetermined period after the wireless quality was acquired is collected for machine learning. Then, the results of the wireless quality measurement are input, and information indicating whether the event occurred is used as training data (correct answer data) to perform machine learning. In the inference phase, the wireless quality measured in the cell 121 is input into the trained model obtained by the machine learning, thereby obtaining an output indicating, for example, whether the event will occur after a predetermined period or the probability of the event occurring. Then, for example, if it is inferred that an event will occur in the inference phase, the terminal device 111 may transmit a predetermined report to the base station device 101. Furthermore, for example, when the probability of an event occurrence is acquired in the inference phase, the terminal device 111 may determine that the event is estimated to occur within a predetermined period of time based on the probability being equal to or greater than a predetermined value, and may transmit a predetermined report to the base station device 101. Note that information on the predetermined value of the probability may be notified in advance from the base station device 101 to the terminal device 111 as setting information. That is, similar to setting information related to conventional events, setting information to be used for determining future events based on AI / ML may be prepared. Note that information indicating the probability of an event occurrence may be stored in the predetermined report.

[0022] The terminal device 111 may be configured to acquire, for example, whether an event will occur or the probability of the event occurring for multiple timings after a predetermined period. In this case, in the learning phase, information indicating whether an event occurred (whether an occurrence condition was satisfied) at multiple different timings after a predetermined period from the timing at which the input wireless quality was acquired is used as training data. Then, in the inference phase, the trained model is configured to output, for an input wireless quality measurement value, whether an event will occur (whether an occurrence condition is satisfied) at multiple different timings after a predetermined period from the timing at which the measurement value was acquired, or an estimated value of the probability of the event occurring. Then, the terminal device 111 may transmit a predetermined report to the base station device 101 when it is estimated that an event will occur within a predetermined period or when the probability of the event occurrence is maintained at or above a predetermined value for a predetermined period. Information about this predetermined period may be notified to the terminal device 111 in advance from the base station device 101. That is, a period equivalent to the Time To Trigger for a conventional event may be set as the predetermined period for a future event.

[0023] Furthermore, the predetermined value used as the training data may be, for example, a second wireless quality of a signal transmitted in the cell 121 a predetermined period after a timing at which a first wireless quality of a signal transmitted in the same cell 121 is acquired in the learning phase. That is, the first wireless quality acquired in the cell 121 is used as input in the learning phase, and a second wireless quality acquired in the same cell 121 a predetermined period after the first wireless quality is acquired may be used as training data. Then, in the inference phase, the wireless quality measured in the cell 121 is input to the trained model obtained by the machine learning, thereby outputting, for example, an estimated value of the wireless quality in the cell 121 a predetermined period after the timing at which the wireless quality is measured. The terminal device 111 measures the wireless quality of a signal transmitted in the cell 121 (from the base station device 101) and inputs the measurement result into the trained model, thereby obtaining an estimated value of the wireless quality in the cell 121 a predetermined period after the measurement value is acquired. The terminal device 111 can then use the estimated wireless quality to determine whether an event such as the above-described events A1 to A5 will occur. For example, if the estimated wireless quality falls below a predetermined level for event A2, the terminal device 111 can determine that event A2 is estimated to occur after a predetermined period of time. Note that, although information such as a threshold value (predetermined level) for an event can be reused from conventional event-related setting information notified in advance from the base station device 101 to the terminal device 111, this is not limitative. In other words, setting information for AI / ML may be separately prepared and notified from the base station device 101 to the terminal device 111.

[0024] The terminal device 111 may be configured to acquire estimated values ​​of wireless quality for multiple timings after a predetermined period. In this case, in the learning phase, wireless qualities obtained at multiple different timings after a predetermined period from the timing at which the input wireless quality was acquired are used as training data. Then, in the inference phase, the trained model is configured to output, for an input wireless quality measurement value, estimated values ​​of wireless quality at multiple different timings after a predetermined period from the timing at which the measurement value was acquired. Then, the terminal device 111 may transmit a predetermined report to the base station device 101 if the estimated value of wireless quality continues to satisfy the occurrence condition of each event over a predetermined period. For example, if the estimated value of wireless quality falls below a predetermined level related to event A2 consecutively at multiple timings corresponding to the predetermined period, the terminal device 111 can determine that event A2 is estimated to occur after the predetermined period. Information about this predetermined period may use a Time To Trigger related to a conventional event, or a predetermined period related to a future event may be separately set. Incidentally, setting information relating to conventional events, such as hysteresis values ​​and reportOnLeave, may be used as is, or corresponding information relating to future events may be set separately.

[0025] Although the above example describes event A2, the terminal device 111 can estimate whether other events will occur. To estimate the wireless quality of other cells, machine learning must be performed. For example, in the learning phase, machine learning can be performed using the wireless quality measured in cell 121 as input and the wireless quality of each of other cells (cells 122 and 123) obtained a predetermined period after the wireless quality was obtained as training data, thereby acquiring a trained model. As a result, in the inference phase, when the measured value of the wireless quality in cell 121 is input to the trained model, estimated values ​​of the wireless quality of each of candidate handover destination cells, such as cells 122 and 123, a predetermined period after the measurement value is obtained can be output. Using such a trained model, the terminal device 111 can acquire estimated values ​​of the future wireless quality of each candidate handover destination cell and, based on the estimated values, determine whether, for example, event A4 is predicted to occur in the future. The terminal device 111 can also determine whether it is estimated that event A3 or event A5 will occur in the future based on the estimated value of the wireless quality of the currently connected cell 121 and the estimated values ​​of the future wireless quality of each of the candidate handover destination cells. In this case, too, a trained model may be generated to obtain estimated values ​​for multiple timings. Then, when the estimated value of the wireless quality satisfies the occurrence condition of each event at multiple consecutive timings corresponding to a predetermined length of time, the terminal device 111 can determine that the event is estimated to occur after a predetermined period of time.

[0026] Furthermore, in the learning phase, a trained model may be generated by performing machine learning using the wireless quality of a neighboring cell (cell 122 or cell 123) measured by a terminal device connected to cell 121 as input and the wireless quality of the neighboring cell a predetermined period after the wireless quality was acquired as training data. That is, the future wireless quality of the neighboring cell may be estimated in the same manner as the above-described estimation of the future wireless quality of cell 121. Note that a trained model may be generated that estimates the wireless quality of cell 121 and the neighboring cell together, or the wireless quality of the currently connected cell and other cells may be estimated using separate trained models. When the wireless quality of cell 121 and the neighboring cell is estimated together, the trained model may be generated by inputting the wireless quality of cell 121 and the neighboring cell, respectively, in the learning phase, and using the wireless quality of cell 121 and the neighboring cell a predetermined period after the wireless quality was acquired as training data. Furthermore, the wireless quality of multiple other cells may be estimated using separate trained models. Furthermore, as described above, measured values ​​of wireless quality at multiple timings a predetermined period after the timing at which the input wireless quality is acquired may be used as training data to generate a trained model that estimates wireless quality at multiple future timings.

[0027] Furthermore, as described above, a trained model may be generated that outputs whether or not an event A3, event A5, or the like occurs after a predetermined period from the time when the wireless quality used as input in the learning phase is acquired, as training data. That is, machine learning may be performed using the wireless quality of the cell 121 as input, without using the wireless quality of other cells, or using the wireless quality of other cells as input, and using as training data whether or not event A3 or event A5 occurs after a predetermined period from the time when the wireless quality is acquired. In this way, the terminal device 111 may input the wireless quality of the cell 121 (and the wireless quality of neighboring cells, if necessary) into the trained model obtained by the machine learning, thereby acquiring whether or not event A3 or event A5 occurs, or the probability of the occurrence of the event, without obtaining an estimate of the wireless quality of the neighboring cells after a predetermined period.

[0028] Furthermore, the above-described machine learning may be performed using only the wireless quality of the neighboring cell, without using the wireless quality of the cell 121. That is, when the wireless quality of the neighboring cell is input, a trained model may be generated that has been trained to output an estimated value of the wireless quality of the cell 121 a predetermined period after the timing at which the wireless quality is acquired, or whether or not an event will occur, or the probability of the event occurring.

[0029] Furthermore, the wireless quality of the cell 121 (alternatively or additionally, the wireless quality of the neighboring cell) used as an input in the above description may be the wireless quality at a single timing, or a predetermined number of wireless qualities acquired at a predetermined time interval. That is, the above-described machine learning may be performed using wireless qualities at multiple timings as input to generate a trained model. In this case, the terminal device 111 can perform the above-described estimation by measuring a predetermined number of wireless qualities at the predetermined time interval and inputting the measurement results into the trained model.

[0030] The terminal device 111 may generate a trained model by performing machine learning, or may acquire a separately generated trained model from the base station device 101. When machine learning is performed in the terminal device 111, a trained model cannot be acquired until training data has been acquired a sufficient number of times, but a trained model suitable for the terminal device 111 can be acquired. On the other hand, when a trained model is provided from the base station device 101, a large amount of training data can be obtained from communications by a large number of terminal devices previously connected to the cell 121, allowing learning to be completed quickly. The base station device 101 may also notify the terminal device 111 of information to be input into the trained model and information indicating the output of the trained model at that time. In accordance with the notification, the terminal device 111 may collect, for example, information to be input into the trained model provided from the base station device 101 (the wireless quality of the currently connected cell 121 or other cells) and input it into the trained model. Then, in accordance with the notification, the terminal device 111 may identify the type of information output from the trained model and, accordingly, determine, for example, whether an event is estimated to occur. The terminal device 111 may also perform machine learning in accordance with the notification.

[0031] Furthermore, information specifying a future event that the terminal device 111 should determine may be specified from the base station device 101. The terminal device 111 can execute determination of only the specified event. This prevents the terminal device 111 from performing unnecessary event determination. Furthermore, the base station device 101 may specify, for example, a future timing. In this case, the terminal device 111 estimates whether or not an event will occur at that timing.

[0032] When the base station device 101 receives a predetermined report indicating that the terminal device 111 has determined that an event is predicted to occur in the future as described above, the base station device 101 causes the terminal device 111 to execute a handover in the same manner as a conventional event-based handover. That is, the base station device 101 starts handover processing when it is predicted by inference using a trained model that an event will occur within a predetermined period of time, regardless of whether the event has actually occurred. This allows the base station device 101 to predict a situation in which a handover is necessary and execute the handover in advance, thereby reducing the probability of handover failure and improving communication efficiency, compared to when the handover processing is executed after an event actually occurs.

[0033] Note that performance evaluation of the trained model may be performed periodically, for example. For example, in some cases where the base station device 101 receives the above-mentioned predetermined report, the base station device 101 may perform conventional event-based handover processing instead of performing estimation-based handover processing. The base station device 101 may then evaluate the trained model as unsuitable for the real environment and decide to perform re-learning (additional learning) if, for example, the error between the estimated timing of an event occurrence and the actual timing of the event is greater than or equal to a predetermined value. Furthermore, the terminal device 111 may evaluate the trained model as unsuitable for the real environment if, for example, the difference between the estimated value and the actual measured value of wireless quality at a specific timing is greater than or equal to a predetermined value, and notify the base station device 101 of the evaluation result. Furthermore, the terminal device 111 may evaluate the trained model as unsuitable for the real environment if, for example, the difference between the estimated value and the actual measured value of wireless quality for the maximum value or a predetermined number of highest values ​​of wireless quality for multiple cells is greater than or equal to a predetermined value, and notify the base station device 101 of the evaluation result. The base station device 101 may decide to perform re-learning (additional learning) in accordance with the notification. This allows the trained model to be maintained in an appropriate state, making it possible to execute handover processing based on predictions at the appropriate time.

[0034] (Device Configuration) FIG. 2 shows an example of the hardware configuration of the base station device 101 and the terminal device 111 according to this embodiment. In one example, the base station device 101 and the terminal device 111 are configured to include a processor 201, a ROM 202, a RAM 203, a storage device 204, and a communication circuit 205. The processor 201 is a computer configured to include one or more processing circuits, such as a general-purpose CPU (Central Processing Unit) or an ASIC (Application Specific Integrated Circuit), and performs the overall processing of the device and each of the above-mentioned processes by reading and executing programs stored in the ROM 202 or the storage device 204. The ROM 202 is a read-only memory that stores information such as programs and various parameters related to the processing performed by the base station device 101 and the terminal device 111. The RAM 203 functions as a workspace when the processor 201 executes a program and is also a random access memory that stores temporary information. The storage device 204 is configured, for example, by a removable external storage device. The communication circuit 205 is configured, for example, by a circuit for wireless communication of 5G or a successor standard. While FIG. 2 illustrates one communication circuit 205, the base station device 101 and the terminal device 111 may have multiple communication circuits. For example, the base station device 101 and the terminal device 111 may have wireless communication circuits for 5G and a successor standard, respectively, and a common antenna for these circuits. The base station device 101 and the terminal device 111 may also have separate antennas suitable for each standard. The base station device 101 may also have a wired communication circuit used when communicating with other base station devices or nodes in the core network. The terminal device 111 may also have a communication circuit compliant with a wireless communication standard other than a cellular communication standard, such as a wireless local area network (LAN) or Bluetooth (registered trademark). The base station device 101 and the terminal device 111 may have separate communication circuits 205 for each of the multiple available frequency bands, or may have a common communication circuit 205 for at least some of the frequency bands.

[0035] FIG. 3 shows an example of the functional configuration of the terminal device 111. The terminal device 111 includes, for example, a measurement unit 301, an event determination unit 302, a reporting unit 303, and a setting information receiving unit 304. The terminal device 111 may also include, as an option, a learning unit 305. Note that FIG. 3 only shows functions particularly related to this embodiment, and does not illustrate various other functions that the terminal device 111 may have. For example, the terminal device 111 naturally has other functions that terminal devices compliant with LTE, 5G, or subsequent standards generally have. The functional blocks in FIG. 3 are shown schematically, and the respective functional blocks may be integrated or further subdivided. The functions in FIG. 3 may be realized, for example, by the processor 201 executing a program stored in the ROM 202 or the storage device 204, or by a processor within the communication circuit 205 executing predetermined software. A storage medium storing a program for implementing the functions may also be provided. Since the details of the processes executed by each functional unit have been described above, only the general functions of the terminal device 111 will be outlined here.

[0036] The measurement unit 301 observes signals (e.g., reference signals) transmitted in the connected cell 121 and other candidate handover cells (e.g., cell 122 and cell 123) and measures their wireless quality. The event determination unit 302 inputs the wireless quality of the cell 121 (and other cells) measured by the measurement unit 301 into a trained model to perform inference processing and determine whether an event related to the occurrence of a handover from the cell 121 to another cell is estimated to occur a predetermined period after the timing at which the wireless quality is acquired by the measurement unit 301. The report unit 303 transmits a predetermined report to the base station device 101 based on the determination by the event determination unit 302 that an event is estimated to occur. The predetermined report includes information notifying the occurrence of an event based on estimation by the trained model, and may further include information indicating the probability of the output of the trained model and information indicating the wireless quality, as the case may be. Note that the predetermined report may implicitly notify the occurrence of an event based on estimation by the trained model, and the predetermined report does not necessarily include explicit information indicating the occurrence of an event based on the estimation. The setting information receiving unit 304 receives setting information for event determination based on future predictions using a trained model from the connected base station device 101. The setting information receiving unit 304 may receive, for example, the trained model itself to be used in the terminal device 111. Furthermore, when multiple trained models are available in the terminal device 111, the setting information receiving unit 304 may receive, from the base station device 101, information specifying which trained model to use. Furthermore, the setting information receiving unit 304 may receive, from the base station device 101, information specifying an event to be determined and information specifying the input and output of the trained model. In addition to these, the setting information receiving unit 304 may also receive various other information, such as those described above. When a trained model should be generated in the terminal device 111, the learning unit 305 generates the trained model through machine learning. Furthermore, the learning unit 305 may re-train the trained model, for example, in response to an instruction from the base station device 101.For example, if handover processing is not initiated after a predetermined report is transmitted, but is instead performed after a conventional event occurrence is reported, the learning unit 305 may identify a difference between the estimated values ​​of the event occurrence timing and wireless quality based on the trained model and the actual measured values ​​of the event occurrence timing and wireless quality based on conventional event determination, and notify the base station device 101 of the difference. Furthermore, if the difference between the estimated values ​​and the actual measured values ​​exceeds a predetermined value, the learning unit 305 may determine that re-learning is necessary and notify the base station device 101 of information indicating that re-learning should be performed. That is, the need for re-learning may be determined by the base station device 101 or may be determined by the terminal device 111. The learning unit 305 may perform re-learning without obtaining permission from the base station device 101.

[0037] FIG. 4 shows an example of the functional configuration of the base station device 101. The base station device 101 includes a setting information notification unit 401, a report receiving unit 402, and a handover control unit 403. The base station device 101 may also include a learning unit 404 as an option. Note that FIG. 4 only illustrates functions particularly related to this embodiment, and does not illustrate various other functions that the base station device 101 may have. For example, the base station device 101 naturally has other functions that are generally possessed by base station devices compliant with LTE, 5G, or subsequent standards. The functional blocks in FIG. 4 are shown schematically, and the respective functional blocks may be integrated or further subdivided. The functions in FIG. 4 may be realized, for example, by the processor 201 executing a program stored in the ROM 202 or the storage device 204, or by a processor within the communication circuit 205 executing predetermined software. A storage medium storing a program for implementing the functions may also be provided. Since the details of the processes executed by each functional unit have been described above, only the general functions of the base station device 101 will be outlined here.

[0038] The setting information notification unit 401 notifies the connected terminal device 111 of setting information for determining an event based on a future prediction by the trained model. The setting information transmitted here is information received by the setting information receiving unit 304 of the terminal device 111. The report receiving unit 402 receives from the terminal device 111 a predetermined report transmitted in response to the terminal device 111 determining that an event based on a future prediction by the trained model is estimated to occur. In response to receiving the predetermined report, the handover control unit 403 initiates handover processing to transfer the cell to which the terminal device 111 is connected to another cell, regardless of whether a conventional event has occurred. Furthermore, for example, in some cases where the predetermined report is received, the handover control unit 403 may wait for a conventional event to occur and initiate handover processing according to a conventional procedure. For example, depending on the type of communication being performed by the terminal device 111, the handover control unit 403 may initiate handover processing for a terminal device 111 that requires highly reliable communication upon receiving a predetermined report, and may perform conventional handover processing for terminal devices 111 that perform other communication. The learning unit 404 performs machine learning to generate a trained model for event determination based on future predictions. Note that it is sufficient for either the learning unit 305 of the terminal device 111 or the learning unit 404 of the base station device 101 to perform machine learning; it is not necessary for both to perform machine learning. Furthermore, machine learning may be performed in a network node different from either the base station device 101 or the terminal device 111. Note that, when conventional handover processing is performed, the base station device 101 may transmit an instruction to the terminal device 111 to report to the base station device 101 the difference between the estimated values ​​of the event occurrence timing and wireless quality based on the trained model and the actual measured values ​​of the event occurrence timing and wireless quality based on conventional event determination. Then, if the difference exceeds a predetermined value, either the learning unit 305 of the terminal device 111 or the learning unit 404 of the base station device 101 performs re-learning of the trained model. Also, instead of the difference value between the estimated value and the actual measured value described above, information indicating that re-learning is necessary may be notified from the terminal device 111 to the base station device 101.In addition, when machine learning is performed in a network node different from both the base station device 101 and the terminal device 111, the base station device 101 may notify the network node that re-learning should be performed.

[0039] (Processing Flow) An example of a processing flow according to this embodiment is shown in Fig. 5. Note that, since the details of the processing executed in the wireless communication system are as described above, only an overview of the processing flow will be given here, and the details will not be repeated.

[0040] First, the base station device 101 transmits configuration information for estimating the occurrence of a future event using a trained model (AI / ML) to the terminal device 111 (S501). This configuration information includes information such as whether to activate estimation of the occurrence of a future event using AI / ML, the type of event, and setting values ​​for determining the event (e.g., the probability of the above-mentioned event occurring, information corresponding to a conventional event, and information on a predetermined period corresponding to TimeToTrigger). This configuration information is notified from the base station device 101 to the terminal device 111 using, for example, an RRC (Radio Resource Control) message including ReportConfig. The configuration information may be notified using other existing information elements (e.g., MeasConfig), or a new information element for notifying the configuration information may be defined. The configuration information may also be notified as information on the MAC (Media Access Control) layer or the physical layer. The terminal device 111 retains the configuration information and, when instructed to activate estimation of the occurrence of a future event using AI / ML, starts the process of estimating the occurrence of a future event. In a process of estimating the occurrence of a future event, the terminal device 111 measures the wireless quality of the cell 121 based on a signal such as a reference signal transmitted from the base station device 101 (S502). Furthermore, the terminal device 111 measures the wireless quality of a neighboring cell (e.g., cell 122 or cell 123) from a signal transmitted in that neighboring cell as needed. The terminal device 111 may measure only the wireless quality of the neighboring cell. The terminal device 111 then inputs the measurement results into a trained model to perform inference (S503), and determines whether the inference predicts that an event that requires the triggering of handover processing will occur within a predetermined period from the timing at which the measurement value was acquired (S504). If the terminal device 111 determines that an event will occur within the predetermined period, it transmits a predetermined report to the base station device 101 (S505). In response to receiving this predetermined report, the base station device 101 starts handover processing and transmits a handover instruction (RRC Reconfiguration message or Handover command) to the terminal device 111 even if a conventional event has not occurred in the terminal device 111 (S506).This allows the base station device 101 to quickly hand over the terminal device 111 that is expected to require handover in the near future to another cell, thereby preventing future handover failures in the terminal device 111.

[0041] The above-mentioned "cell" may be read as "beam." That is, the terminal device 111 may measure the wireless quality of at least one of a beam used for communication and a beam not used. In this case, machine learning is performed based on the wireless quality of each beam, and, for example, when it is predicted that the wireless quality will deteriorate in all of multiple cells of a specific cell, control may be performed to execute handover.

[0042] As described above, in this embodiment, by determining whether an event requiring handover will occur in the future based on the current wireless quality measured in the terminal device 111, it becomes possible to start handover processing before the wireless quality deteriorates. This improves the stability of communication in the terminal device 111 and improves communication efficiency in the entire system. Therefore, it becomes possible to contribute to Goal 9 of the Sustainable Development Goals (SDGs) led by the United Nations, which is to "Develop resilient infrastructure, promote sustainable industrialization and foster innovation."

[0043] The invention is not limited to the above-described embodiment, and various modifications and variations are possible within the scope of the gist of the invention.

[0044] This application claims priority based on Japanese Patent Application No. 2024-131178, filed August 7, 2024, the entire contents of which are incorporated herein by reference.

Claims

1. A terminal device comprising: a measurement means for measuring the wireless quality of a signal transmitted from a base station device to which the terminal device is currently connected; a determination means for inputting the wireless quality acquired in a learning phase into a trained model acquired by machine learning using as training data a predetermined value for determining whether an event related to a handover from a cell provided by the base station device to another cell is predicted to occur within a predetermined period from the time the wireless quality was acquired, and for determining whether the event is predicted to occur within the predetermined period from the time the wireless quality was acquired; and a transmission means for transmitting a predetermined report to the base station device if it is predicted that the event will occur within the predetermined period.

2. The terminal device described in claim 1, wherein the predetermined value is a value indicating whether the event has occurred after the predetermined period from the timing when the wireless quality was acquired in the learning phase, the trained model is configured to input the wireless quality acquired by the terminal device in the inference phase and output the probability of the event occurring, and the determination means determines that the event is estimated to occur after the predetermined period based on the fact that the probability obtained by inputting the wireless quality acquired by the terminal device in the inference phase into the trained model is greater than or equal to a predetermined value.

3. The terminal device described in claim 1, wherein the predetermined value is a second wireless quality of a signal transmitted in a cell provided by the base station device after the predetermined period from the timing at which a first wireless quality of a signal transmitted in the cell is acquired in the learning phase, the first wireless quality is used as input in the learning phase, and the determination means determines that the event is estimated to occur after the predetermined period based on the wireless quality output by inputting the wireless quality acquired by the terminal device in the inference phase into the trained model falling below a predetermined level.

4. The terminal device according to claim 2 or 3, further comprising an execution means for executing the machine learning to obtain the trained model.

5. The terminal device according to claim 2 or 3, further comprising an acquisition means for acquiring the trained model from the base station device.

6. A terminal device as described in claim 2 or 3, wherein the trained model is obtained in the learning phase by performing machine learning using as input a predetermined number of the wireless qualities obtained at a predetermined time interval, and the determination means determines in the inference phase whether the event is estimated to occur after the predetermined period by inputting the predetermined number of the wireless qualities obtained at the predetermined time interval into the trained model.

7. The terminal device of claim 3, wherein the trained model is acquired in the learning phase by machine learning using as training data the second wireless quality acquired at multiple times during a predetermined period from the predetermined period after the time when the first wireless quality is acquired, and the determination means determines that the event is estimated to occur after the predetermined period based on the fact that the estimated value of wireless quality output from the trained model continues to be below a predetermined level during the predetermined period from the predetermined period after the time when the wireless quality is acquired in the inference phase.

8. The terminal device according to claim 1, wherein the measurement means further measures a third wireless quality of the signal transmitted in the other cell, the trained model is acquired by machine learning using the wireless quality and the third wireless quality acquired in the learning phase as input and a predetermined value as training data for determining whether a second event related to handover from the cell to the other cell is estimated to occur after the predetermined period from the time when the wireless quality and the third wireless quality are acquired, the determination means inputs the wireless quality and the third wireless quality acquired by the terminal device in the inference phase into the trained model, and determines whether the second event is estimated to occur after the predetermined period from the time when the wireless quality and the third wireless quality are acquired, and the transmission means transmits a predetermined report to the base station device when it is estimated that the second event will occur after the predetermined period.

9. The terminal device according to claim 1, further comprising receiving means for receiving information specifying the event from the base station device.

10. The terminal device according to claim 1, wherein the determination means is capable of using a plurality of the trained models, and the terminal device further has a receiving means for receiving information from the base station device specifying which of the plurality of the trained models to use.

11. A base station device comprising: a receiving means for receiving a predetermined report indicating that the terminal device has determined that the event is estimated to occur within a predetermined period from the time when the measurement result is acquired, from a terminal device connected to a cell provided by the base station device, by inputting the measurement result of the wireless quality of the cell in a learning phase and using as training data a predetermined value for determining whether an event related to a handover from the cell to another cell is estimated to occur within a predetermined period from the time when the wireless quality is acquired; and an instruction means for instructing the terminal device to perform a handover based on the receipt of the predetermined report.

12. The base station device according to claim 11, further comprising notification means for notifying said terminal device of information specifying said event.

13. The base station device according to claim 11, wherein the terminal device is capable of using a plurality of the trained models, and the base station device further comprises a notification means for notifying the terminal device of information specifying which of the plurality of the trained models to use.

14. A control method executed by a terminal device, comprising: measuring the wireless quality of a signal transmitted from a base station device to which the terminal device is connected; inputting the wireless quality acquired in a learning phase into a trained model acquired by machine learning using as training data a predetermined value for determining whether an event related to a handover from a cell provided by the base station device to another cell is predicted to occur within a predetermined period from the time when the wireless quality was acquired, thereby determining whether the event is predicted to occur within the predetermined period from the time when the wireless quality was acquired; and transmitting a predetermined report to the base station device if it is predicted that the event will occur within the predetermined period.

15. A control method executed by a base station device, comprising: receiving, from a terminal device connected to a cell provided by the base station device, a predetermined report indicating that the terminal device has determined that the event is estimated to occur within a predetermined period of time from the time the measurement result is acquired, by inputting, in an inference phase, the measurement result of the wireless quality of the cell by the terminal device into a trained model obtained by machine learning, which inputs, in a learning phase, the measurement result of the wireless quality of the cell and uses, as training data, predetermined values ​​for determining whether an event related to a handover from the cell to another cell is estimated to occur within a predetermined period of time from the time the measurement result is acquired; and instructing the terminal device to perform a handover based on the receipt of the predetermined report.

Images