Communication control device, communication control method, and communication control program

Abstract

A communication control device (100) according to the present application comprises an acquisition unit (132), a prediction unit (134), and a communication control unit (135). The acquisition unit (132) acquires, as result information pertaining to communication between a terminal device and a communication destination base station with which the terminal device communicates or a neighboring base station which neighbors the communication destination base station, measurement result information obtained by measuring a prescribed communication parameter and failure information pertaining to a communication failure. The prediction unit (134) predicts, on the basis of the result information, whether a prescribed communication failure will occur in a target terminal device. When it is predicted that the prescribed communication failure will occur in the target terminal device, the communication control unit (135) hands over the target terminal device from the communication destination base station to the neighboring base station before the timing at which the prescribed communication failure can occur.

Description

Communication control device, communication control method, and communication control program 【0001】 The present invention relates to a communication control device, a communication control method, and a communication control program. 【0002】 Patent Document 1 describes that a source RAN node determines a target RAN node for handover among cells around a UE based on measurements on neighboring cells (for example, cell quality, signal quality, signal strength, reference signal received power (RSRP), reference signal received quality (RSRQ), channel state, channel quality, signal-to-interference-plus-noise ratio (SINR)). 【0003】 Japanese Patent Application Laid-Open No. 2022-531419 【0004】 When handing over a mobile communication terminal (User Equipment, UE), communication may be disconnected depending on the communication environment of the UE, and seamless handover may not be achieved. The above prior art only determines a target RAN node for handover among cells around the UE based on measurements on neighboring cells, leaving a risk that communication will be disconnected when handing over the UE to the determined target RAN node. Therefore, seamless handover cannot always be achieved with the above prior art. 【0005】 Therefore, the communication control device according to the present application includes an acquisition unit that acquires measurement result information in which a predetermined communication parameter is measured and failure information regarding a communication failure, as performance information regarding communication between a base station with which a terminal device communicates or an adjacent base station adjacent to the base station of the communication destination and the terminal device; a prediction unit that predicts whether or not a predetermined communication failure will occur in a target terminal device based on the performance information; and a communication control unit that, when it is predicted that the predetermined communication failure will occur in the target terminal device, hands over the target terminal device from the base station of the communication destination to the adjacent base station before the timing when the predetermined communication failure can occur. 【0006】Figure 1 is a diagram comparing the conventional technology with the proposed method. Figure 2 is a diagram showing an example of a RAN architecture according to the embodiment. Figure 3 is a diagram showing an example of the configuration of a communication control device according to the embodiment. Figure 4 is a diagram showing an example of information collection in the learning phase according to the embodiment. Figure 5 is a diagram showing an example of a learning method in the learning phase according to the embodiment. Figure 6 is a diagram showing an example of an inference phase according to the embodiment. Figure 7 is a hardware configuration diagram showing an example of a computer that realizes the functions of the communication control device according to the embodiment. 【0007】 Embodiments of the present invention will be described in detail below with reference to the attached drawings. In this specification and the drawings, components having substantially the same functional configuration are denoted by the same reference numerals, and redundant explanations will be omitted. 【0008】 The one or more embodiments (including examples, modifications, and applications) described below can each be implemented independently. On the other hand, at least some of the embodiments described below may be implemented in appropriate combination with at least some of the other embodiments. These embodiments may contain novel features that differ from each other. Therefore, these embodiments may contribute to solving different objectives or problems and may produce different effects. 【0009】 [1. Introduction] The proposed method of this application relates to a technology for controlling UE handover. Therefore, we will first explain the difference between the conventional handover control technology and the proposed technology of this application. Figure 1 is a diagram comparing the conventional technology and the proposed method. 【0010】Figure 1 illustrates a handover (switching of cell C) between a gNB (gangline base station), which is a fifth-generation (5G) wireless base station of the 3GPP (3rd Generation Partnership Project), and a UE (user's mobile communication terminal). According to Figure 1, the gNB to which the UE is currently communicating (connected) is "gNB1," and the cell C formed by gNB1 is "C1." On the other hand, the gNB adjacent to gNB1, to which the UE is currently communicating, is "gNB2," and the cell C formed by gNB2 is "C2." In the example in Figure 1, the UE, currently in cell C1, is moving towards cell C2 formed by gNB2. The UE is also measuring the radio wave conditions of the surrounding gNBs. 【0011】 The situation described above is common to both Figure 1(a) and Figure 1(b). 【0012】 First, we will explain the handover process in the conventional method using Figure 1(a). In the example in Figure 1(a), the handover process progresses from the top diagram to the middle diagram and then to the bottom diagram. 【0013】 In the upper diagram of Figure 1(a), the UE currently communicating with gNB1 is moving towards cell C2 while measuring not only the radio wave conditions of gNB1 but also those of gNB2, with which it is not currently communicating. In this situation, the connection between the UE and gNB1 is good, while the connection between the UE and gNB2 is poor. 【0014】 Now, let's assume that, as shown in the middle section of Figure 1(a), the UE has moved and the radio signal conditions with gNB2 have improved compared to those with gNB1. In this case, the UE reports a handover request to gNB1 indicating that the radio signal conditions with gNB2 have improved compared to those with gNB1. 【0015】Upon receiving a handover request containing the measurement results, gNB1 instructs UE to perform a handover, as shown in the lower part of Figure 1(a). In response to the handover instruction from gNB1, UE switches the communication destination gNB from gNB1 to gNB2. In other words, in response to the handover instruction, UE disconnects from gNB1 and connects to the adjacent gNB2, completing the handover. 【0016】 A problem with these conventional methods is that they do not always guarantee a seamless handover. Figure 1(a) shows area AR where cells C1 and C2 overlap, and area AR is called the cell edge at the edge of cell C. 【0017】 Wireless quality is prone to change in areas near Area A and in locations with obstacles (e.g., underground, inside tunnels, near buildings). For example, in the example in Figure 1(a), if a UE communicating with gNB1 is placed in an environment where wireless quality is prone to change during movement (e.g., near Area AR), the UE may lose communication with gNB1 and be unable to perform a proper handover. For example, if communication with gNB1 is lost before the UE sends a handover request, the UE will have to send the handover request again. Therefore, with conventional methods, communication interruptions may occur before the handover is completed, and a seamless handover may not be achievable. 【0018】 The proposed method is a solution that addresses the above-mentioned problems of conventional methods. The proposed method predicts the deterioration of the UE's communication quality (e.g., communication disconnection) and, if deterioration of communication quality is predicted, forcibly hands over the UE to the destination gNB before a normal handover event. In other words, the proposed method predicts environments where wireless quality is likely to change and, based on the prediction result, maintains communication quality by delaying the handover to the destination gNB of the UE. A normal handover event refers to the series of handover processes explained in Figure 1(a). 【0019】The proposed method will be explained using Figure 1(b). In the example in Figure 1(b), if the UE communicating with gNB1 continues to move toward gNB2, the handover event described in Figure 1(a) will occur. The proposed method predicts whether a communication disconnection will occur at a timing related to the handover event (before the handover event occurs or during the handover event), and if a communication disconnection is predicted, it hands over the UE from gNB1 to gNB2 before the communication disconnection occurs. 【0020】 For example, according to the upper diagram in Figure 1(b), the UE sends a handover request to the gNB1 near Area AR. However, it is predicted that the UE will continue moving toward Area AR, and that a communication interruption will occur between the UE and the gNB1 when it is located near Area AR. 【0021】 In this case, the proposed method executes handover control on gNB1 before a communication interruption occurs between the UE and gNB1. As a result, as shown in the middle of Figure 1(b), gNB1 instructs the UE to hand over. In response to the handover instruction from gNB1, the UE switches the communication destination gNB from gNB1 to gNB2. In other words, in response to the handover instruction, the UE disconnects from gNB1 and connects with the adjacent gNB2, completing the handover. 【0022】 As explained in Figure 1, the proposed method is advantageous compared to conventional methods in that it achieves seamless handover. Furthermore, although the proposed method is conceptually shown in Figure 1, the information processing related to the proposed method may actually be performed not by a gNB itself, but by a network device with gNB functionality. This point will be explained in Figure 2. 【0023】 Furthermore, this proposed method can improve communication quality and operational efficiency through the use of AI, and will serve as an innovative technological foundation in the telecommunications business, thereby contributing to the achievement of Sustainable Development Goal (SDG) 9, "Build resilient infrastructure, promote inclusive and sustainable industrialization and foster innovation." 【0024】[2. RAN Architecture and Virtualization] Figure 2 shows an example of a RAN architecture according to the embodiment. For example, in order to respond to the diversification of demands for mobile networks, progress is being made in commonizing interfaces between network devices within a Radio Access Network (RAN), virtualizing network devices, and promoting the use of general-purpose servers (minimizing dedicated hardware). 【0025】 For example, with NFV (Network Functions Virtualization), network functions that were previously implemented with dedicated hardware can now be implemented as software functions, allowing them to run as virtualized workloads on inexpensive general-purpose servers. Therefore, vRAN (virtual Radio Access Network) is a virtualization system that implements the gNB (gangline network) components of a RAN, with the gNB functions being implemented as software on a general-purpose server. 【0026】 As shown in Figure 2, vRAN is based on the idea of ​​dividing the gNB, which was previously composed of dedicated hardware, into three components: CU (Central Unit), DU (Distributed Unit), and RU (Radio Unit). In this example, the RU corresponds to a slave station, and the DU and CU correspond to master stations. 【0027】 In vRAN, the DU and CU are expected to be provided as virtualized applications (vDU and vCU) that run on a virtualization infrastructure composed of general-purpose servers. Furthermore, as shown in Figure 2, the RIC (RAN Intelligent Controller) is defined as a platform that optimizes wireless resource management and automates operations, and the SMO (Service Management and Orchestration) is defined as a framework for RAN maintenance and orchestration. 【0028】The communication control device 100 according to this embodiment may be implemented as part of a function such as an SMO or RIC. Also, although RU10-1 and RU10-2 are shown as examples of multiple RU10s (RUs), the number of RU10s accommodated in the virtualization infrastructure is not limited to two. For example, Figure 2 shows an example in which one DU accommodates (manages) two RU10s, RU10-1 and RU10-2, but the number of RU10s accommodated by the DU is not limited to two. 【0029】 Furthermore, in the following embodiment, RU10-1 corresponds to gNB1 in Figure 1, and RU10-2 corresponds to gNB2 in Figure 1. Therefore, RU10-1 forms cell C1, and RU10-2 forms cell C2. For example, if a UE is located in cell C1 under RU10-1, RU10-1 corresponds to the gNB with which the UE is currently communicating. In this example, RU10-2 corresponds to an adjacent gNB with which the UE is not currently communicating. 【0030】 Furthermore, vRAN enables autonomous and automated operations utilizing artificial intelligence (AI) and machine learning (ML). AI-RAN is a technology that allows vRAN applications and AI applications to run on the same virtualization platform. As mentioned above, as RAN is increasingly software-based, general-purpose servers can use not only software to implement RAN control functions but also other software. For example, since the amount of wireless communication traffic by UE fluctuates greatly depending on the time of day, there is surplus resources (computing power) on general-purpose servers during off-peak hours such as late at night and early in the morning. The AI-RAN concept utilizes these surplus resources for AI applications. 【0031】[3. Configuration of the Communication Control Device] The communication control device 100 according to the embodiment will be described using Figure 3. Figure 3 is a diagram showing an example of the configuration of the communication control device 100 according to the embodiment. As shown in Figure 3, the communication control device 100 has a communication unit 110, a storage unit 120, and a control unit 130. The communication control device 100 may be configured as an AI-RAN in which both the vRAN application and the AI ​​application are realized by software on the same virtualization infrastructure on a general-purpose server. 【0032】 (Communication Unit 110) The communication unit 110 is implemented by, for example, a NIC (Network Interface Card). For example, it transmits and receives information with the outside world. 【0033】 (Storage Unit 120) The storage unit 120 is implemented by, for example, a semiconductor memory element such as RAM (Random Access Memory) or flash memory, or a storage device such as a hard disk or optical disc. The storage unit 120 may store, for example, data and programs related to information processing according to the embodiment. Also, as shown in Figure 3, the storage unit 120 may have a measurement result information storage unit 121, a failure information storage unit 122, and a model storage unit 123. 【0034】 (Control Unit 130) The control unit 130 is implemented by a CPU (Central Processing Unit) or MPU (Micro Processing Unit), etc., which executes various programs (for example, information processing programs according to the embodiment) stored in the storage device inside the communication control device 100 using RAM as the working area. The control unit 130 is also implemented by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or FPGA (Field Programmable Gate Array). 【0035】As shown in Figure 3, the control unit 130 includes a receiving unit 131, an acquisition unit 132, a generation unit 133, a prediction unit 134, and a communication control unit 135, and realizes or executes the information processing functions and operations described below. Note that the internal configuration of the control unit 130 is not limited to the configuration shown in Figure 3, and other configurations are also possible as long as they perform the information processing described later. Also, the connection relationships of the various processing units in the control unit 130 are not limited to the connection relationships shown in Figure 3, and other connection relationships are also possible. 【0036】 (Reception Unit 131) The reception unit 131 receives measurement result information DA1, which is measured for predetermined communication parameters, as actual communication information between the UE and the gNB that the UE communicates with (RU10-1 in the example in Figure 2), or a gNB adjacent to the base station gNB that the UE communicates with (RU10-2 in the example in Figure 2). The reception unit 131 also receives fault information DA2 regarding a communication fault that occurred between the base station gNB and the UE. The reception unit 131 stores the measurement result information DA1 in the measurement result information storage unit 121 and the fault information DA2 in the fault information storage unit 122. 【0037】 The measurement result information DA1 may include, at a minimum, information regarding the communication quality between the UE and the gNB with which it communicates, information regarding the communication quality between the UE and the adjacent gNB adjacent to the base station gNB with which it communicates, and information regarding the UE's communication attitude. The UE's communication attitude includes the concepts of the UE's position and orientation. 【0038】 (Acquisition Unit 132) The acquisition unit 132 acquires information necessary for the information processing according to the embodiment. For example, the acquisition unit 132 acquires measurement result information DA1 from the measurement result information storage unit 121 and outputs it to the generation unit 133. The acquisition unit 132 also acquires fault information DA2 from the fault information storage unit 122 and outputs it to the generation unit 133. 【0039】(Generation Unit 133) Based on the measurement result information DA1 and the fault information DA2, the generation unit 133 generates a model M1 that has been trained to output a prediction of the occurrence of a predetermined communication fault, taking predetermined communication parameters as input. For example, the generation unit 133 may generate model M1 by training the model on the relationship between the content of the communication fault, the timing at which the communication fault occurred, and the measurement result corresponding to the timing at which the communication fault occurred. The generation unit 133 may also store model M1 in the model storage unit 123. 【0040】 (Prediction Unit 134) The prediction unit 134 inputs the current communication parameters of the target UE into model M1 and predicts whether a predetermined communication failure will occur in the target UE based on the output result of model M1. For example, the prediction unit 134 may use model M1 to predict the direction of movement of the target UE and, if the target UE moves in the predicted direction, predict whether a communication disconnection will occur at the timing related to the handover event (before the handover event occurs, or during the handover event). The generation unit 133 may generate a model M1 capable of such predictions based on measurement result information DA1 and failure information DA2. 【0041】 (Communication Control Unit 135) The communication control unit 135 performs handover control. Specifically, if the communication control unit 135 predicts that a predetermined communication failure will occur in the target UE, it performs control to hand over the target UE to the adjacent gNB before the timing at which the predetermined communication failure is likely to occur. 【0042】 [4. Learning Phase] (Information Gathering) The information processing according to this embodiment may be divided into a learning phase for generating model M1 and an inference phase for performing handover control based on the inference results inferred using model M1. Therefore, Figures 4 and 5 will explain the learning phase. First, Figure 4 will be explained. Figure 4 is a diagram showing an example of information gathering in the learning phase according to this embodiment. 【0043】Note that FIG. 4 shows an example in which the communication control device 100 collects information necessary for the learning data LD from one UE. In reality, however, information is collected from an unspecified number of UEs within the cell C. 【0044】 As shown in FIG. 4, every time the UE measures a predetermined communication parameter, it sequentially transmits measurement result information DA1 including the measurement result to the communication destination RU10. For example, the UE may receive radio waves from each of RU10-1 (communication destination gNB) and RU10-2 (adjacent gNB) and measure the communication quality (e.g., radio wave intensity). Then, the UE may sequentially transmit a measurement result report RP1 indicating the measurement result of the radio wave intensity (Reference Signal Received Power, RSRP) to the communication destination RU10. As shown in FIG. 4, the measurement result report RP1 may include communication destination RU information (a pair of the base station ID indicating the communication destination gNB and the radio wave intensity received from the communication destination gNB) and adjacent RU information (a pair of the base station ID indicating the adjacent gNB and the radio wave intensity received from the adjacent gNB). 【0045】 Note that the UE may include, in the measurement result report RP1, information on its current position and the direction in which it is moving as its own terminal information when measuring the RSRP. In addition, as a predetermined communication parameter, the UE may measure not only the RPSP but also the Signal to Inter-ference plus Noise Ratio (SINR) and the Received Signal Quality (Reference Signal Received Quality, RSRQ), and transmit a measurement result report RP1 further including the measurement results. 【0046】 The communication destination RU10 transmits the measurement result report RP1 received from the UE to the communication control device 100. As a result, the communication control device 100 can collect measurement result information from various UEs. 【0047】Also, as shown in FIG. 4, when a communication failure occurs, the UE transmits failure information DA2 including the details of the communication failure to the destination RU10. For example, when the UE detects a Radio Link Failure (RLF) as a connection failure, it may transmit a radio link failure report RP2 reporting the RLF information to the destination RU10. Also, when the UE detects a Handover Failure (HOF) as a connection failure, it may transmit a radio link failure report RP2 reporting the HOF information to the destination RU10. The destination RU10 transmits the radio link failure report RP2 received from the UE to the communication control device 100. As a result, the communication control device 100 can collect connection failure information from various UEs. 【0048】 As another example, when the UE fails to establish a Radio Resource Control (RRC) connection as a connection failure, it may transmit a connection establishment failure report RP3 reporting the RRC connection establishment failure information to the destination RU10. The destination RU10 transmits the connection establishment failure report RP3 received from the UE to the communication control device 100. As a result, the communication control device 100 can collect connection failure information from various UEs. 【0049】 (Learning method) Next, FIG. 5 will be described. FIG. 5 is a diagram showing an example of a learning method in the learning phase according to the embodiment. 【0050】 The generation unit 133 combines the measurement result information DA1 and the failure information DA2 to generate learning data LD. For example, the generation unit 133 may generate a learning data set in which a set of the details of the communication failure, the timing at which the communication failure occurred, and the measurement result corresponding to the timing at which the communication failure occurred is one piece of learning data LD. 【0051】The generation unit 133 then takes predetermined communication parameters as input and trains a model to output a prediction of the occurrence of a predetermined communication failure, thereby generating a model M1 for predicting the occurrence of a predetermined communication failure. For example, the generation unit 133 may generate a model M1 that predicts the direction of movement of the UE and, if the UE moves in the predicted direction, predicts whether or not a communication disconnection will occur at the timing related to the handover event (before the handover event occurs, or during the handover event). 【0052】 [5. Inference Phase] Figure 6 is a diagram showing an example of the inference phase according to the embodiment. Figure 6 shows a scene in which a handover control is performed on a target UE1 located in cell C1 of RU10-1 and communicating with RU10-1. 【0053】 In the example shown in Figure 1, the target UE1 transmits a measurement result report RP1_U1, which measures radio wave strength as a communication parameter, to RU10-1 (step S61), and RU10-1 transmits the measurement result report RP1 received from the target UE1 to the communication control device 100 (step S62). 【0054】 The measurement result report RP1_U1 includes communication destination RU information (a pair of the base station ID indicating the communication destination RU10-1 and the radio wave strength received from the communication destination RU10-1) and adjacent RU information (a pair of the base station ID indicating the adjacent RU10-2 and the radio wave strength received from the adjacent gNB). The measurement result report RP1_U1 also includes local terminal information indicating the position and direction of movement of the target UE1. Although not shown in Figure 6, the measurement result report RP1_U1 may include not only RSRP (radio wave strength) but also RSRQ (reception quality) and SINR (signal-to-interference noise ratio). Furthermore, the target UE1 may transmit the measurement result report RP1_U1 each time it is measured in response to periodic measurements of its communication parameters. Therefore, the communication control device 100 may perform a prediction using Model M1 each time it receives the measurement result report RP1_U1. 【0055】The measurement result report RP1_U1 is received by the reception unit 131. The acquisition unit 132 acquires the received measurement result report RP1_U1 and transmits the acquired measurement result report RP1_U1 to the prediction unit 134 (step S63). 【0056】 The prediction unit 134 inputs the measurement result information contained in the measurement result report RP1_U1 to the model M1 and predicts whether or not a communication failure will occur in the target UE1 based on the output result of the model M1 (step S64). Based on the output result of the model M1, the prediction unit 134 predicts whether or not a communication disconnection will occur between the target UE1 and the RU10-1 if the target UE1 continues to move in its current direction. For example, based on the output result of the model M1, the prediction unit 134 predicts whether or not a communication disconnection will occur at a timing related to the handover event (before or during the handover event) if the target UE1 continues to move in its current direction. 【0057】 If the communication control unit 135 predicts that no communication failure will occur at the target UE1, it does not need to perform the handover control according to the embodiment so that the normal handover event proceeds. 【0058】 On the other hand, if the communication control unit 135 predicts that a communication failure will occur in the target UE1, it performs handover control to hand over the target UE1 from RU10-1 to RU10-2 before the communication failure occurs (step S65). For example, the communication control unit 135 controls RU10-1 to issue a handover instruction to the target UE1. 【0059】 RU10-1 instructs target UE1 to perform a handover in response to handover control from communication control unit 135 (step S66). Target UE1 switches the communication destination RU10 from RU10-1 to RU10-2 in response to the handover instruction from RU10-1 (step S67). In other words, in response to the handover instruction, target UE1 disconnects from RU10-1 and connects with the adjacent RU10-2, completing the handover. 【0060】Thus, according to the information processing of this embodiment, a deterioration in the communication quality of the target UE1 (for example, a communication disconnection) is predicted, and if a deterioration in communication quality is predicted, the target UE1 is forcibly handed over to the adjacent RU10-2 before a normal handover event occurs. Therefore, according to the information processing of this embodiment, a seamless handover can be achieved. 【0061】 [6. Hardware Configuration] The communication control device 100 according to the embodiment may be implemented by a computer 1000 having the configuration shown in Figure 7. Figure 7 is a hardware configuration diagram showing an example of a computer that implements the functions of the communication control device 100 according to the embodiment. The computer 1000 has a CPU 1100, RAM 1200, ROM 1300, HDD 1400, communication interface (I / F) 1500, input / output interface (I / F) 1600, and media interface (I / F) 1700. 【0062】 The CPU 1100 operates based on programs stored in the ROM 1300 or HDD 1400, and controls various parts. The ROM 1300 stores boot programs executed by the CPU 1100 when the computer 1000 starts up, as well as programs that depend on the computer 1000's hardware. 【0063】 The HDD 1400 stores programs executed by the CPU 1100, and data used by such programs. The communication interface 1500 receives data from other devices via a predetermined communication network and sends it to the CPU 1100, and transmits data generated by the CPU 1100 to other devices via the predetermined communication network. 【0064】 The CPU 1100 controls output devices such as displays and input devices such as keyboards via the input / output interface 1600. The CPU 1100 acquires data from input devices via the input / output interface 1600. The CPU 1100 also outputs the generated data to output devices via the input / output interface 1600. 【0065】The media interface 1700 reads a program or data stored in the recording medium 1800 and provides it to the CPU 1100 via the RAM 1200. The CPU 1100 loads the program from the recording medium 1800 onto the RAM 1200 via the media interface 1700 and executes the loaded program. The recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or PD (Phase Change Rewritable Disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory. 【0066】 For example, when the computer 1000 functions as a communication control device 100 according to the embodiment, the CPU 1100 of the computer 1000 realizes the functions of the control unit 130 by executing a program loaded on the RAM 1200. The CPU 1100 of the computer 1000 reads and executes these programs from the recording medium 1800, but as another example, these programs may be obtained from other devices via a predetermined communication network. 【0067】 [7. Others] Furthermore, all or part of the processes described as being performed automatically in each of the above embodiments may be performed manually, or all or part of the processes described as being performed manually may be performed automatically by known methods. In addition, the processing procedures, specific names, and information including various data and parameters shown in the above documents and drawings may be changed at will unless otherwise specified. For example, the various information shown in each figure is not limited to the information shown. 【0068】 Furthermore, the components of each illustrated device are functionally conceptual and do not necessarily need to be physically configured as shown. In other words, the specific forms of distribution and integration of each device are not limited to those shown, and all or part of them can be functionally or physically distributed and integrated in any unit according to various loads and usage conditions. 【0069】Furthermore, the above embodiments can be combined as appropriate, provided that the processing content is not contradictory. 【0070】 Although some embodiments of the present invention have been described in detail above with reference to the drawings, these are illustrative examples, and the present invention can be implemented in various other forms with modifications and improvements based on the knowledge of those skilled in the art, including the embodiments described in the section on the present invention. 【0071】 100 Communication control device 120 Storage unit 121 Measurement result information storage unit 122 Fault information storage unit 123 Model storage unit 130 Control unit 131 Reception unit 132 Acquisition unit 133 Generation unit 134 Prediction unit 135 Communication control unit

Claims

1. A communication control device comprising: an acquisition unit that acquires measurement result information in which predetermined communication parameters have been measured and fault information regarding communication failures as actual communication information between the terminal device and a base station to which the terminal device communicates, or an adjacent base station adjacent to the base station to which the terminal device communicates; a prediction unit that predicts whether or not a predetermined communication failure will occur in the target terminal device based on the actual information; and a communication control unit that, if it is predicted that the predetermined communication failure will occur in the target terminal device, hands over the target terminal device from the base station to which the terminal device communicates to the adjacent base station before the timing at which the predetermined communication failure may occur.

2. The communication control device according to claim 1, wherein the acquisition unit acquires measurement result information which includes at least the communication quality between the terminal device and the base station to which the terminal device communicates, the communication quality between the terminal device and an adjacent base station adjacent to the base station to which the terminal device communicates, and the communication attitude of the terminal device as measurement results, and acquires fault information relating to a communication fault that occurred between the terminal device and the base station to which the terminal device communicates.

3. The communication control device according to claim 2, wherein the fault information includes a wireless link failure report transmitted from the terminal device, or a connection establishment failure report transmitted from the terminal device, the wireless link failure report includes at least information indicating a wireless link failure (RLF) or a handover failure (HOF) by the terminal device, and the connection establishment failure report includes at least information indicating a wireless resource (RRC) connection establishment failure.

4. The communication control device according to claim 1, further comprising: a generation unit that generates a model trained to output a prediction of the occurrence of a predetermined communication failure, taking predetermined communication parameters as input based on the measurement result information and the failure information, wherein the prediction unit inputs the current communication parameters of the target terminal device to the model and predicts whether or not the predetermined communication failure will occur in the target terminal device based on the output result of the model.

5. The communication control device according to claim 4, wherein the generation unit causes the model to learn the relationship between the content of the communication failure, the timing at which the communication failure occurred, and the measurement result corresponding to the timing at which the communication failure occurred.

6. A communication control device according to claim 1, wherein both a RAN control function for controlling a wireless access network (RAN) and an AI function having artificial intelligence (AI) are implemented on a server by software.

7. A communication control method executed by a computer, comprising: an acquisition step of acquiring measurement result information in which predetermined communication parameters have been measured and fault information regarding communication failures as actual communication information between the terminal device and a base station to which the terminal device communicates, or an adjacent base station adjacent to the base station to which the terminal device communicates; a prediction step of predicting whether or not a predetermined communication failure will occur in the target terminal device based on the actual information; and a communication control step of, if it is predicted that the target terminal device will experience the predetermined communication failure, handing over the target terminal device from the base station to which the terminal device communicates to the adjacent base station before the timing at which the predetermined communication failure may occur.

8. A communication control program that causes a computer to execute the following: an acquisition procedure for acquiring measurement result information in which predetermined communication parameters have been measured and fault information regarding communication failures, as actual communication information between the terminal device and a base station to which the terminal device communicates, or an adjacent base station adjacent to the base station to which the terminal device communicates; a prediction procedure for predicting whether or not a predetermined communication failure will occur in the target terminal device based on the actual communication information; and a communication control procedure for handing over the target terminal device from the base station to which the terminal device communicates to the adjacent base station before the timing at which the predetermined communication failure may occur, if it is predicted that the target terminal device will occur.

Images