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

Abstract

This terminal device: measures the radio quality of a signal transmitted from a currently connected base station device, the radio quality acquired for the signal transmitted from the base station device being input to a trained model during a training phase; specifies one or more occurrence probabilities respectively corresponding to one or more timings of at least one of a radio link failure (RLF) or a handover failure (HOF), which are obtained by inputting the radio quality measured during an inference phase to the trained model, the trained model being obtained through machine learning using, as training data, a value indicating whether or not at least one of the RLF in the case of handover processing not having been performed or the HOF in the case of the handover processing having been executed at one or more timings after a predetermined period at the timing of acquisition of the radio quality, has occurred; and transmits predetermined information pertaining to the one or more occurrence probabilities to the base station device.

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 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; an identification means for inputting the wireless quality acquired for the signal transmitted from the base station device in a learning phase and identifying one or more occurrence probabilities corresponding to each of one or more timings of at least one of a radio link failure (RLF) when handover processing is not performed and a handover failure (HOF) when handover processing is performed, acquired by inputting the wireless quality measured by the measurement means in an inference phase, for a trained model acquired by machine learning using as training data a value indicating whether or not at least one of an RLF when handover processing is not performed at one or more timings after a predetermined period after the timing at which the wireless quality was acquired; and a transmission means for transmitting predetermined information regarding the one or more occurrence probabilities to the base station device.

[0006] A base station device according to one aspect of the present invention has a receiving means for receiving from a terminal device connected to the base station device, predetermined information regarding one or more occurrence probabilities corresponding to each of one or more timings of at least one of a radio link failure (RLF) and a handover failure (HOF) when handover processing is executed, obtained by inputting the radio quality obtained for a signal transmitted from the base station device in a learning phase and using as training data a value indicating whether or not at least one of a radio link failure (RLF) when handover processing is not performed at one or more timings after the timing at which the radio quality was obtained; and a determining means for determining whether or not to handover the terminal device from a cell provided by the base station device to another cell based on the predetermined information.

[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 for initiating handover processing has occurred based on whether the wireless quality satisfies a predetermined condition. Events are defined in a cellular communication standard. Examples of events include event A2, which is determined to have occurred when the wireless quality of the currently connected cell falls below a predetermined threshold; 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; 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. When the terminal device 111 determines that any of the events set by the base station device 101 has occurred, it transmits a predetermined report to the base station device 101. Then, in response to receiving the predetermined report, the base station device 101 executes processing to hand over the terminal device 111 from the currently connected cell 121 to another cell (for example, 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 a neighboring cell from the base station device 101 to the terminal device 111 before the occurrence of an event, and then transmitting a command (Handover command) from the base station device 101 to the terminal device 111 instructing the handover. Also, after the occurrence of an event, the handover processing can be started by transmitting setting information for communication in a neighboring cell of the handover from the base station device 101 to the terminal device 111 using an RRC Reconfiguration message. Note that RRC is an abbreviation for Radio Resource Control.

[0013] 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.

[0014] The terminal device 111 is supposed to start timer T310 when it is deemed unable to establish downlink synchronization with the base station device 101. More specifically, the terminal device 111 starts timer T310 when it receives N310 consecutive out-of-sync indications from the physical layer in the RRC layer. The terminal device 111 receives information on the number of N310 and the expiration time of T310 in advance as configuration information from the connected base station device 101. When timer T310 expires after being started, the terminal device 111 determines that a radio link failure (RLF) has occurred. Timer T310 is stopped when a handover command is received. However, as described above, if wireless quality deteriorates after an event occurs and the terminal device 111 is unable to receive the command, it cannot stop timer T310. As a result, the terminal device 111 is unable to execute handover processing, resulting in the occurrence of a handover failure (HOF). Furthermore, the terminal device 111 cannot start a connection re-establishment process (RRC Connection Re-establishment process) unless an RLF occurs after waiting until timer T310 expires. For this reason, in order to improve the efficiency of communication in a wireless communication system, it is important to reduce the probability of occurrence of HOF or RLF.

[0015] In recent years, the application of artificial intelligence (AI) / machine learning (ML) to cellular communication systems has been discussed. Using AI / ML, for example, it is possible to predict whether an RLF will occur in the future 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 whether an RLF will occur if a handover does not occur a predetermined period after the wireless quality is acquired as training data. Once 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 obtain an estimated value of the probability that an RLF will occur a predetermined period after the wireless quality is acquired. Furthermore, the terminal device 111 provides the base station device 101 with the output of the trained model, enabling the base station device 101 to make the determination. Furthermore, for example, a trained model can be acquired by machine learning using, as input, the wireless quality of the cell 121 acquired in the learning phase and training data indicating whether or not a HOF occurred when a handover process was performed at a predetermined time after the wireless quality was acquired. When such a trained model is acquired, the terminal device 111 can obtain an estimated value of the probability of a HOF occurring at a predetermined time after the wireless quality was acquired by inputting the results of measuring the wireless quality of a signal transmitted from the cell 121 in the inference phase. Furthermore, the terminal device 111 can provide the base station device 101 with the output of the trained model, thereby enabling the base station device 101 to make this determination. Here, the predetermined time is set arbitrarily, for example, to a period of several seconds. This setting information can be notified in advance from the base station device 101 to the terminal device 111.

[0016] As described above, by using AI / ML, the terminal device 111 can obtain the probability that an RLF or HOF will occur at a predetermined timing in the future (a timing a predetermined period after the measurement value is obtained), but conventional standards do not assume that such probabilities will be obtained, and therefore it is not possible to perform handover processing using these probabilities. In view of this situation, this embodiment provides a technique for performing handover processing based on predicted values ​​of RLF and HOF at appropriate timing.

[0017] In this embodiment, the terminal device 111 identifies one or more occurrence probabilities corresponding to one or more timings of at least one of RLF and HOF, and transmits predetermined information regarding the identified one or more occurrence probabilities to the base station device 101. To identify the one or more occurrence probabilities, the terminal device 111 uses a trained model acquired by machine learning. More specifically, for the cell 121 to which the terminal device 111 is connected in the learning phase, one or more wireless qualities measured in the cell 121 are input, and the trained data may be acquired by machine learning using whether or not at least one of an RLF when a handover process is not performed and an HOF when a handover process is performed has occurred at one or more timings a predetermined period after the timing at which the predetermined one of the one or more wireless qualities is acquired. Note that the predetermined one of the one or more wireless qualities may be, for example, the first acquired wireless quality (the wireless quality acquired earliest among the input wireless qualities) or the last acquired wireless quality (the wireless quality acquired latest among the input wireless qualities). Alternatively, a predetermined one of the one or more wireless qualities may be determined according to another rule. Then, the terminal device 111 acquires, for example, one or more wireless qualities corresponding to one or more timings for the connected cell 121 (and, as necessary, other cells such as neighboring cells (e.g., cell 122 and cell 123)), and inputs the values ​​of the one or more wireless qualities into the trained model. This allows an estimated value of the occurrence probability of at least one of RLF and HOF at one or more timings a predetermined period after (in the future) the timing corresponding to the predetermined one of the one or more wireless qualities identified according to the rule used in the learning phase to be acquired.

[0018] The terminal device 111 may transmit, as predetermined information regarding the probability of occurrence of at least one of RLF and HOF for each of one or more acquired future timings, information indicating the occurrence probabilities of the one or more occurrences to the base station device 101. For example, if the occurrence probabilities of at least one of RLF and HOF at four consecutive timings are values ​​such as 10%, 20%, 40%, and 30%, respectively, information indicating time fluctuations in the occurrence probabilities, such as 10, 20, 40, and 30, may be transmitted to the base station device 101 as predetermined information. Note that if the probability is expressed in 10% units, information such as 1, 2, 4, and 3 may be transmitted to the base station device 101 as predetermined information. Furthermore, a difference value from the occurrence probability at the immediately preceding timing may be transmitted as predetermined information. In this case, information such as 10, 10, 20, and -10 may be transmitted to the base station device 101 as predetermined information indicating values ​​such as 10%, 20%, 40%, and 30%. Furthermore, each value may be expressed, for example, by a reference value and a difference value. For example, by setting the reference value to 20%, information such as -10, 0, 20, and 10 may be transmitted to the base station device 101 as predetermined information indicating values ​​such as 10%, 20%, 40%, and 30%. Note that the timing may be expressed, for example, in units of time slots. In this case, if the first timing is the xth time slot, four consecutive timings may correspond to the xth to x+3rd time slots, respectively. Furthermore, the timing may be expressed in units of the transmission period of a synchronization signal (SS) / physical broadcast channel (PBCH) block (SSB). That is, a value indicating one occurrence probability may be transmitted to the base station device 101 for each SSB transmission period. Alternatively, only information indicating an occurrence probability exceeding a predetermined threshold may be transmitted to the base station device 101. For example, if the predetermined threshold is 30%, then only information such as 40 and 30 may be transmitted to the base station device 101 out of 10%, 20%, 40%, and 30%. In this case, information indicating the timing at which the occurrence probability is due may also be transmitted to the base station device 101. For example, information such as (40, x+2) or (30, x+3) may be transmitted to the base station device 101.This allows the base station device 101 to identify the timing at which RLF or HOF is expected to occur in the terminal device 111, and to perform processing such as handing over the terminal device 111 to another cell before such timing arrives.

[0019] Furthermore, the terminal device 111 may transmit, as predetermined information, to the base station device 101, a statistic of the occurrence probability of at least one of RLF and HOF for each of one or more acquired future timings. The statistic may be, for example, a maximum value. For example, if the occurrence probabilities of at least one of RLF and HOF at four consecutive timings are 10%, 20%, 40%, and 30%, respectively, the value "40%" may be transmitted to the base station device 101. At this time, information on the timing at which the maximum value is obtained may also be transmitted to the base station device 101. For example, information such as (40, x+2) may be transmitted to the base station device 101. The statistic may be, for example, a minimum value. For example, if the occurrence probabilities of at least one of RLF and HOF at four consecutive timings are 10%, 20%, 40%, and 30%, respectively, the value "10%" may be transmitted to the base station device 101. At this time, information about the timing at which the minimum value was obtained may also be transmitted to the base station device 101. For example, information such as (10, x) may be transmitted to the base station device 101. The statistical quantity may also be an average value. For example, if the occurrence probabilities at four consecutive timings for at least one of RLF and HOF are 10%, 20%, 40%, and 30%, respectively, information such as "25%" may be transmitted to the base station device 101.

[0020] Furthermore, the probability of occurrence of HOF may be specified for each of multiple candidate handover destination cells. That is, the probability of occurrence of HOF when a handover process is performed from cell 121 to cell 122 and the probability of occurrence of HOF when a handover process is performed from cell 122 to cell 123 may be estimated. In one example, a separate trained model may be prepared for each candidate handover destination cell. The terminal device 111 can obtain an estimated value of the probability of occurrence of HOF for each of multiple candidate handover destination cells by inputting measured wireless quality values ​​into each of multiple trained models. In this case, the terminal device 111 may, for example, notify the base station device 101 of all of the estimated values ​​of the probability of occurrence of HOF obtained for each of multiple candidate handover destination cells, or may notify the base station device 101 of statistics of the probability of occurrence of HOF (maximum, minimum, average, etc.). That is, the predetermined information as described above may be transmitted for each of multiple candidate handover destination cells. Furthermore, the probability of occurrence of HOF may be output collectively for one or more candidate cells as the handover destination. That is, the trained model may be designed so that the probability of occurrence of HOF is output from the trained model regardless of which cell is selected as the handover destination.

[0021] Note that the above-mentioned predetermined information may be included in, for example, a Measurement Report of Layer 3 and notified from the terminal device 111 to the base station device 101. Alternatively, the above-mentioned predetermined information may be included in a CSI-report of Layer 1 and notified from the terminal device 111 to the base station device 101. Here, the terminal device 111 may transmit information on the radio quality of the measured cell 121 (or other cells such as cell 122 or cell 123 as necessary) along with the predetermined information to the base station device 101. That is, the terminal device 111 may be configured to add the above-mentioned predetermined information to, for example, a conventional Measurement Report or CSI report and transmit the result. For example, the RSRP for each cell and predetermined information on the probability of occurrence of RLF or HOF may be transmitted from the terminal device 111 to the base station device 101 in a single message. Furthermore, the predetermined information may be transmitted in a message separate from the conventional Measurement Report or CSI report. In this case, the separate message used to transmit the predetermined information may be an existing message or a newly defined message.

[0022] Furthermore, all of the wireless quality values ​​output from the trained model may be taken into consideration, or only some of the wireless quality values ​​may be taken into consideration. For example, when n values ​​indicating wireless quality corresponding to n consecutive timings are output from the trained model, m (m<n) values ​​indicating wireless quality among them may be taken into consideration to generate predetermined information to be transmitted to the base station device 101. In this case, setting information indicating the number m of values ​​to be taken into consideration may be notified in advance from the base station device 101 to the terminal device 111.

[0023] Furthermore, machine learning may be performed separately for the probability of RLF occurrence and the probability of HOF occurrence, generating separate trained models. However, these may be combined and machine learning may be performed to generate a single trained model. That is, machine learning may be performed using, as training data, measurement values ​​of the wireless quality of cell 121 (or other cells, such as cell 122 or cell 123, as necessary), and whether or not an RLF has occurred and whether or not an HOF has occurred a predetermined time after the measurement values ​​are obtained. The terminal device 111 may then acquire, as output of the trained model, one or more future occurrence probabilities of RLF and one or more future occurrence probabilities of HOF (at a predetermined time after the wireless quality is obtained).

[0024] Furthermore, as the predetermined information, configuration information indicating which of the above-described information (such as a list of one or more occurrence probabilities of RLF / HOF corresponding to each timing, statistics of the occurrence probabilities) should be transmitted may be notified from the base station device 101 to the terminal device 111, for example, via a radio resource control (RRC) message. In accordance with the notification, the terminal device 111 may generate information regarding the RLF / HOF occurrence probability obtained by estimation and transmit it to the base station device 101 as the predetermined information. Furthermore, information specifying which message (such as a Measurement Report of Layer 3 or a CSI-report of Layer 1) should transmit the predetermined information may be notified from the base station device 101 to the terminal device 111. Note that the content of the predetermined information and the message to be used may be determined in advance (for example, by a standard), and the terminal device 111 may generate the predetermined information based on the predetermined configuration and transmit it to the base station device 101 without receiving any particular configuration information from the base station device 101.

[0025] Based on the reception of the predetermined information, the base station device 101 can determine, for example, whether to execute handover of the terminal device 111. That is, if there is a high probability that an RLF or HOF will occur in the near future, the base station device 101 can decide to handover the terminal device 111 to another cell regardless of the current wireless quality. The base station device 101 starts handover processing in response to the decision.

[0026] Furthermore, the terminal devices present in the cell 121 may include terminal devices that are not capable of estimating at least one of the probability of occurrence of RLF and the probability of occurrence of HOF using a trained model. The terminal devices may notify the base station device 101 in advance (for example, when establishing a connection) capability information indicating whether they are capable of estimating at least one of the probability of occurrence of RLF and HOF using a trained model, and, if capable of estimating, whether they are capable of estimating the RLF or the HOF.

[0027] Note that the performance evaluation of the trained model may be performed periodically, for example. For example, the base station device 101 may collect information on the occurrence probability of at least one of RLF and HOF estimated in some terminal devices, and observe whether or not an RLF or HOF actually occurs at a predetermined timing corresponding to the occurrence probability without transmitting a handover command to the terminal device. The base station device 101 then compares the actual measurement value of the occurrence probability of the RLF or HOF with the notified estimated value of the occurrence probability of the RLF or HOF, and calculates the difference (error) between the actual measurement value and the estimated value. If the error is equal to or greater than a predetermined value, the base station device 101 may evaluate that the trained model is not suitable for the real environment and decide to perform re-learning (additional learning). The base station device 101 may perform re-learning for a certain period of time, for example, and notify the terminal device 111 of the trained model after re-learning. The base station device 101 then receives from the terminal device 111 a notification of an estimated value of the probability of occurrence of RLF or HOF obtained by the trained model, and compares the estimated value with the actual measured value of the probability of occurrence of RLF or HOF again. The base station device 101 may terminate re-learning when the error between the estimated value of the output of the trained model and the actual measured value falls below a predetermined level. Note that, if the terminal device 111 has generated a trained model itself, it may notify the base station device 101 that it will perform this re-learning. Alternatively, the terminal device 111 may notify the base station device 101 that re-learning is necessary, and perform re-learning when it receives a predetermined instruction from the base station device 101. This allows the trained model to be maintained in an appropriate state.

[0028] (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.

[0029] FIG. 3 shows an example of the functional configuration of the terminal device 111. The terminal device 111 includes, for example, a capability information notification unit 301, a setting information receiving unit 302, a quality measurement unit 303, an occurrence probability estimation unit 304, and a reporting unit 305. The terminal device 111 may also include, as an option, a learning unit 306. 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 realized as an integrated unit or may be further subdivided. Furthermore, 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. 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.

[0030] The capability information notifying unit 301 notifies the base station device 101 of capability information possessed by the terminal device 111 as UE Capability. For example, the capability information notifying unit 301 notifies the base station device 101 of information indicating whether the terminal device 111 has the capability to estimate at least one of the probability of RLF occurrence and the probability of HOF occurrence from measured values ​​of wireless quality of the connected cell 121 (and other cells such as neighboring cells (e.g., cell 122 and cell 123) as necessary) using AI / ML. Note that the terminal device 111 may have the capability to estimate only the probability of RLF occurrence, or may have the capability to estimate only the probability of HOF occurrence. The setting information receiving unit 302 receives setting information related to communication from the base station device 101. The setting information may include, for example, information indicating whether the terminal device 111 should estimate and report the probability of RLF or HOF occurrence using a trained model. Furthermore, as described above, the configuration information may include configuration information regarding a report on the probability of RLF / HOF occurrence, such as the format of predetermined information to be transmitted to the base station device 101. Note that both an instruction to estimate and report the probability of RLF or HOF occurrence using a trained model and configuration information regarding a report on the probability of RLF / HOF occurrence may be notified to the terminal device 111 as configuration information, or only one of them may be notified to the terminal device 111. Furthermore, configuration information for causing measurement results of the radio quality of each cell to be reported may be notified to the terminal device 111 along with the report on the probability of RLF / HOF occurrence. The quality measurement unit 303 measures the radio quality of the currently connected cell and, if necessary, other cells such as neighboring cells. The measured radio quality may be information such as reference signal received power (RSRP), reference signal received quality (RSRQ), and signal-to-interference-and-noise ratio (SINR). The occurrence probability estimation unit 304 estimates the occurrence probability of at least one of RLF and HOF at one or more future timings by inputting the wireless quality measured by the quality measurement unit 303 into the trained model. The reporting unit 305 transmits predetermined information related to the occurrence probability estimated by the occurrence probability estimation unit 304 to the base station device 101.The reporting unit 305 generates predetermined information based on the setting information received by the setting information receiving unit 302 and transmits the information to the base station device 101. When a trained model needs to be generated in the terminal device 111, the learning unit 306 generates the trained model by machine learning. Furthermore, the learning unit 306 can re-train the trained model in response to an instruction from the base station device 101, for example.

[0031] FIG. 4 shows an example of the functional configuration of the base station device 101. The base station device 101 includes a capability information receiving unit 401, a setting information notifying unit 402, a report receiving unit 403, and a handover control unit 404. The base station device 101 may also include a learning unit 405 as an option. Note that FIG. 4 only shows 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 realized as an integrated unit or may be 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. 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.

[0032] The capability information receiving unit 401 receives capability information (UE Capability) from the terminal device 111, including information indicating whether the terminal device 111 has the capability to estimate the occurrence probability of at least one of RLF and HOF using AI / ML. The setting information notifying unit 402 can transmit information instructing the terminal device 111, which has the capability to estimate the occurrence probability of at least one of RLF and HOF using AI / ML, whether or not to perform such estimation. The setting information notifying unit 402 also notifies the terminal device 111, which has the capability to estimate the occurrence probability of at least one of RLF and HOF using AI / ML, of setting information for reporting predetermined information regarding the estimation result. The report receiving unit 403 receives predetermined information from the terminal device 111, including a value indicating the occurrence probability itself of at least one of RLF and HOF, a statistic of the occurrence probability, and the like. In response to receiving the predetermined information, the handover control unit 404 determines whether or not to hand over the terminal device 111 to another cell. Then, when the handover control unit 404 determines to hand over the terminal device 111 to another cell, it starts processing for handing over the terminal device 111. This processing can be executed in accordance with existing regulations.

[0033] The learning unit 405 performs machine learning to generate a trained model for estimating the occurrence probability of at least one of RLF and HOF. It is sufficient for either the learning unit 306 of the terminal device 111 or the learning unit 405 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. When the difference between the estimated value and the actual measured value of the occurrence probability of at least one of RLF and HOF exceeds a predetermined value, either the learning unit 306 of the terminal device 111 or the learning unit 405 of the base station device 101 performs re-learning of the trained model. When machine learning is performed in a network node different from either the base station device 101 or the terminal device 111, the base station device 101 may notify the network node that re-learning should be performed.

[0034] (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.

[0035] First, the terminal device 111 notifies the base station device 101 of its own device capability information (S501). Here, the terminal device 111 notifies the base station device 101 of capability information including information indicating that the terminal device 111 is capable of estimating the probability of occurrence of at least one of RLF and HOF by AI / ML. In response to determining from the capability information that the terminal device 111 is capable of estimating the probability of occurrence of at least one of RLF and HOF by AI / ML, the base station device 101 notifies the terminal device 111 of configuration information for reporting estimated values ​​of the occurrence probabilities, for example, by using an RRC Reconfiguration message. Note that the base station device 101 can instruct the terminal device 111 in the configuration information to estimate the probability of occurrence of RLF / HOF by AI / ML and the format of reporting the estimated values ​​(e.g., information indicating each of one or more estimated values, or statistics of one or more estimated values). The terminal device 111 then measures the reference signal transmitted from the base station device 101 (S503, S504) and inputs the measurement value into the trained model to obtain an estimate of the probability of occurrence of at least one of RLF and HOF (S505). The terminal device 111 then transmits predetermined information (an inference result report) indicating the estimate to the base station device 101 (S506). The base station device 101 then determines, for example, based on the predetermined information, whether to hand over the terminal device 111 from the currently connected cell to another cell (S507). The base station device 101 then executes a predetermined handover process (not shown) in response to the determination to hand over the terminal device 111.

[0036] As described above, according to the present embodiment, it is possible to determine whether to hand over the terminal device 111 based on an estimated value of the probability of a future radio link failure (RLF) or handover failure (HOF). This makes it possible to determine whether to hand over the terminal device 111 at the present time, not according to the current wireless quality of the terminal device 111 but according to the probability of a future RLF / HOF, thereby more reliably maintaining the connection of the terminal device 111. This makes it possible to contribute to Goal 9 of the United Nations-led Sustainable Development Goals (SDGs), which is to "build resilient infrastructure, promote sustainable industrialization and foster innovation."

[0037] 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.

[0038] This application claims priority based on Japanese Patent Application No. 2024-131182, 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 wireless quality of a signal transmitted from a base station device to which the terminal device is currently connected; an identification means for inputting the wireless quality acquired for the signal transmitted from the base station device in a learning phase and specifying, as training data, one or more occurrence probabilities corresponding to each of one or more timings of at least one of a radio link failure (RLF) when handover processing is not performed at one or more timings after the timing at which the wireless quality was acquired, and a handover failure (HOF) when handover processing is performed, by inputting the wireless quality measured by the measurement means in an inference phase to a trained model acquired by machine learning using a value indicating whether or not at least one of the RLF and the HOF occurred when handover processing was performed at one or more timings after a predetermined period after the timing at which the wireless quality was acquired; and a transmission means for transmitting predetermined information regarding the one or more occurrence probabilities to the base station device.

2. The terminal device according to claim 1, wherein the predetermined information includes information indicating each of the one or more occurrence probabilities.

3. The terminal device according to claim 1, wherein the predetermined information includes at least one of a maximum value, a minimum value, and an average value of the one or more occurrence probabilities.

4. The terminal device of claim 1, wherein the trained model is prepared for each of a plurality of other cells that are candidate handover destinations for the terminal device from the cell provided by the base station device, the trained model is used to identify the one or more occurrence probabilities of HOF for each of the plurality of other cells, and the specified information includes information indicating each of the one or more occurrence probabilities of HOF for each of the plurality of other cells, or at least one of the maximum, minimum, and average of the one or more occurrence probabilities of HOF for each of the plurality of other cells.

5. The terminal device according to claim 1, wherein the predetermined information is included in a measurement report of layer 3 or a CSI report of layer 1 and transmitted to the base station device.

6. A base station device comprising: a receiving means for receiving from a terminal device connected to the base station device in an inference phase predetermined information regarding one or more occurrence probabilities corresponding to at least one or more timings of at least one of a radio link failure (RLF) and a handover failure (HOF) obtained by inputting wireless quality measured by the terminal device connected to the base station device in a learning phase, the wireless quality being input to the terminal device, and the trained model being obtained by machine learning using as training data a value indicating whether at least one of a radio link failure (RLF) when handover processing is not performed at one or more timings after a predetermined period after the timing at which the wireless quality was acquired, and a determination means for determining whether to handover the terminal device from a cell provided by the base station device to another cell based on the predetermined information.

7. The base station device according to claim 6, wherein the predetermined information includes information indicating each of the one or more occurrence probabilities.

8. The base station device according to claim 6, wherein the predetermined information includes at least one of a maximum value, a minimum value, and an average value of the one or more occurrence probabilities.

9. The base station device of claim 6, wherein the trained model is prepared for each of a plurality of other cells that are candidate handover destinations for the terminal device from the cell provided by the base station device, the trained model is used to identify the one or more occurrence probabilities of HOF for each of the plurality of other cells, and the specified information includes information indicating each of the one or more occurrence probabilities of HOF for each of the plurality of other cells, or at least one of the maximum, minimum, and average of the one or more occurrence probabilities of HOF for each of the plurality of other cells.

10. The base station apparatus according to claim 6, wherein the receiving means receives the predetermined information via a layer 3 measurement report or a layer 1 CSI report.

11. A control method executed by a terminal device, comprising: measuring wireless quality of a signal transmitted from a base station device to which the terminal device is connected; inputting the wireless quality acquired for the signal transmitted from the base station device in a learning phase and using as training data a value indicating whether or not at least one of a radio link failure (RLF) when handover processing is not performed at one or more timings after the timing at which the wireless quality was acquired, and a handover failure (HOF) when handover processing is performed, into a trained model acquired by machine learning; specifying one or more occurrence probabilities corresponding to each of one or more timings of at least one of the RLF and the HOF acquired by inputting the measured wireless quality in an inference phase; and transmitting predetermined information regarding the one or more occurrence probabilities to the base station device.

12. A control method executed by a base station device, comprising: receiving, from a terminal device connected to the base station device in an inference phase, predetermined information regarding one or more occurrence probabilities corresponding to at least one or more timings of at least one of a radio link failure (RLF) and a handover failure (HOF), the information being acquired by inputting wireless quality measured by the terminal device connected to the base station device in the learning phase into a trained model acquired by machine learning using as input wireless quality acquired for a signal transmitted from the base station device in a learning phase and a value indicating whether at least one of a radio link failure (RLF) when handover processing is not performed at one or more timings after a predetermined period after the timing at which the wireless quality was acquired, and a handover failure (HOF) when handover processing is performed, as training data; and determining, based on the predetermined information, whether to handover the terminal device from a cell provided by the base station device to another cell.

13. A program for causing a computer installed in a terminal device to execute the control method according to claim 11.

14. A program for causing a computer installed in a base station device to execute the control method set forth in claim 12.

Images