Communication quality prediction system, communication quality prediction method, and program

Abstract

This communication quality prediction system predicts the communication quality of wireless communication, and comprises: a parameter acquisition unit that acquires one or more wireless communication parameters of the wireless communication; a parameter prediction unit that uses the time-series data of the one or more wireless communication parameters to predict the one or more wireless communication parameters after the lapse of a prescribed time; and a communication quality prediction unit that uses the prediction results of the one or more wireless parameters predicted by the parameter prediction unit to predict the communication quality of the wireless communication after the lapse of the prescribed time.

Description

Communication quality prediction system, communication quality prediction method, and program

[0001] The present invention relates to a communication quality prediction system, a communication quality prediction method, and a program.

[0002] There are techniques for predicting communication quality in a wireless communication system. For example, a technique is known for predicting the communication quality of wireless communication of a terminal from a current terminal position, movement information, etc., based on a previously acquired actual value of communication quality at the terminal position (see, for example, Non-Patent Document 1).

[0003] Also, a received power prediction technique is known that predicts future received power using time series data of the most recent received power by a time series prediction method such as a recurrent neural network (RNN) (see, for example, Non-Patent Document 2).

[0004] Keisuke Wakao, Kenichi Kawamura, Takatsugu Moriyama, "Quality Prediction Technology for Optimal Use of Multiple Wireless Accesses," NTT Technical Journal, April 2020, pp. 11-13. <https: / / www.ntt.co.jp / journal / 2004 / JN20200411_h.html?_ga=2.187750880.999492446.1632821976-1982013439.1586410872> Motoharu Sasaki et al., "Prediction of Radio Wave Propagation Loss Fluctuations in the 2-26 GHz Band Using LSTM," IEICE Technical Report, vol. 120, no. 325, AP2020-112, pp. 50-55, January 2021.

[0005] In the technology disclosed in Non-Patent Document 1, throughput is predicted based on actual values ​​obtained in advance. However, because the occurrence of degradation in communication quality such as throughput varies depending on time, location, etc., this method makes it difficult to predict communication quality such as throughput that changes depending on the surrounding situation or the usage status of the wireless communication system.

[0006] On the other hand, the technology disclosed in Non-Patent Document 2 uses the most recent received power data to make predictions according to the surrounding conditions, and therefore it is possible to predict changes in received power that differ depending on time, location, etc. However, this method cannot predict communication quality such as throughput that is required when using an actual application.

[0007] As described above, conventional technology has a problem in that a communication quality prediction system that predicts the communication quality of a wireless communication system is unable to predict communication quality such as throughput, which changes depending on the surrounding conditions or the usage status of the wireless communication system.

[0008] One embodiment of the present invention has been made in consideration of the above-mentioned problems, and in a communication quality prediction system that predicts the communication quality of a wireless communication system, it is possible to predict communication quality such as throughput that changes depending on the surrounding conditions or the usage status of the wireless communication system.

[0009] In order to solve the above problems, a communication quality prediction system according to an embodiment of the present invention is a communication quality prediction system that predicts the communication quality of wireless communication, and includes a parameter acquisition unit that acquires one or more wireless communication parameters of the wireless communication, a parameter prediction unit that predicts the one or more wireless communication parameters after a predetermined time has elapsed using time series data of the one or more wireless communication parameters, and a communication quality prediction unit that predicts the communication quality of the wireless communication after the predetermined time has elapsed using the prediction results of the one or more wireless parameters predicted by the parameter prediction unit.

[0010] According to one embodiment of the present invention, in a communication quality prediction system that predicts the communication quality of a wireless communication system, it is possible to predict communication quality such as throughput that changes depending on the surrounding conditions or the usage status of the wireless communication system.

[0011] FIG. 1 is a diagram illustrating an example of a system configuration of a communication quality prediction system according to Example 1. FIG. 2 is a diagram illustrating an overview of a communication quality prediction process according to Example 1. FIG. 3 is a flowchart illustrating an example of a communication quality prediction process according to Example 1. FIG. 4 is a diagram illustrating an example of a communication quality prediction model according to Example 1. FIG. 5 is a diagram illustrating an example of a communication quality prediction result according to Example 1. FIG. 6 is a diagram illustrating an example of a system configuration of a communication quality prediction system according to Example 2. FIG. 7 is a diagram illustrating an overview of the process of the communication quality prediction system according to Example 2. FIG. 8 is a flowchart illustrating an example of a communication quality prediction process according to Example 2. FIG. 9 is a diagram illustrating an example of a hardware configuration of a computer. FIG. 10 is a diagram illustrating a problem of the present embodiment. FIG. 11 is a diagram illustrating a problem of the present embodiment.

[0012] Hereinafter, an embodiment of the present invention will be described with reference to the drawings. The embodiment described below is merely an example, and the embodiment to which the present invention is applied is not limited to the following embodiment.

[0013] <Communication Quality Prediction System> The communication quality prediction system is a system that predicts the communication quality of wireless communication in a wireless communication network. Here, before describing the communication quality prediction system according to this embodiment, an overview of the communication quality prediction system will be described.

[0014] 10 shows an overview of a communication quality prediction system 1000 disclosed in Non-Patent Document 1. A wireless quality prediction engine 1001 is, for example, a server device on a network installed on a cloud or within a management network.

[0015] The terminal 1002 periodically uploads information such as location information, terminal type, wireless access type, scan data of the wireless environment, and communication quality information to the wireless quality prediction engine 1001, and accumulates historical information in a database 1003. Based on this database 1003, the wireless quality prediction engine 1001 performs machine learning on a learning algorithm 1004.

[0016] A terminal 1002 using a wireless communication network adds, for example, wireless environment information, terminal information, and location information, and makes an inquiry to the wireless quality prediction engine 1001. As a result, the terminal 1002 can acquire a future predicted value (predicted quality m minutes from now) of communication quality (for example, throughput, delay, jitter, or packet loss) that will be obtained when connected to a wireless base station 1005 that is visible in the surrounding area and is a target of estimation.

[0017] In the technology disclosed in Non-Patent Document 1, a wireless quality prediction engine 1001 predicts the communication quality of wireless communication after a predetermined time has elapsed from the current terminal position, movement information, etc., based on the actual value of communication quality at the terminal position obtained in advance.

[0018] However, since the occurrence of degradation in communication quality such as throughput varies depending on the time, location, etc., this method makes it difficult to predict communication quality such as throughput, which changes depending on the surrounding conditions or the usage status of the wireless communication system.

[0019] On the other hand, in the technology disclosed in Non-Patent Document 2, as shown in Fig. 11, the most recent data 1102 of time-series data 1101 of received power is used to predict future received power 1103 by a time-series prediction method such as a recurrent neural network (RNN). With this method, by using the most recent time-series data, it becomes possible to predict fluctuations that change moment by moment due to the surrounding dynamic environment.

[0020] However, this method cannot predict the communication quality, such as the throughput, required for actual application use.

[0021] As described above, conventional technology has a problem in that a communication quality prediction system that predicts the communication quality of a wireless communication system is unable to predict communication quality such as throughput, which changes depending on the surrounding conditions or the usage status of the wireless communication system.

[0022] Therefore, the communication quality prediction system according to this embodiment has a system configuration as shown in FIG. 1 as an example, so that it can predict communication quality such as throughput that changes depending on the surrounding conditions or the usage status of the wireless communication system.

[0023] 1 is a diagram illustrating an example of a system configuration of a communication quality prediction system according to Example 1. In the example of FIG.

[0024] The communication quality prediction device 100 is an information processing device having a computer configuration or a system including multiple computers. The communication quality prediction device 100 realizes, for example, each functional configuration shown in Fig. 1 by executing a predetermined program stored in a storage medium or the like on the computer included in the communication quality prediction device 100. In the example of Fig. 1, the communication quality prediction device 100 has functional configurations such as a parameter acquisition unit 101, a parameter prediction unit 102, a communication quality prediction unit 103, and a parameter storage unit 111.

[0025] The communication quality prediction device 100 may be a communication terminal connected to a wireless communication network, or a communication quality prediction server capable of communicating with the communication terminal via a wireless base station and the network. Furthermore, the communication quality prediction device 100 may be a communication quality prediction server on a multi-access edge computing (MEC) system.

[0026] The parameter acquisition unit 101 executes a parameter acquisition process to acquire one or more radio parameters for wireless communication and store the acquired radio parameters in the parameter storage unit 111. The radio parameters acquired by the parameter acquisition unit 101 include, for example, parameters such as the received power of the communication terminal, an MCS (Modulation and Coding Scheme) indicating a combination of a modulation method and a coding rate, and a resource block (RB) which is the smallest unit of a radio resource. However, the radio parameters acquired by the parameter acquisition unit 101 are not limited to these.

[0027] The parameter prediction unit 102 executes a parameter prediction process for predicting one or more wireless communication parameters after a predetermined time has elapsed, using time-series data of the one or more wireless communication parameters stored in the parameter storage unit 111. For example, the parameter prediction unit 102 uses the time-series data of the one or more wireless communication parameters to predict the one or more wireless communication parameters after a predetermined time has elapsed, by a time-series prediction method such as an RNN (Recurrent Neural Network).

[0028] The communication quality prediction unit 103 executes a communication quality prediction process for predicting the communication quality of wireless communication after a predetermined time has elapsed, using the prediction results of one or more wireless communication parameters predicted by the parameter prediction unit 102. For example, the communication quality prediction unit 103 predicts the throughput (an example of communication quality) of a communication terminal performing wireless communication from the prediction results of one or more wireless communication parameters using deep learning, machine learning, an estimation formula, or the like.

[0029] The parameter storage unit 111 is a storage unit that stores one or more wireless communication parameters acquired by the parameter acquisition unit 101 in chronological order.

[0030] 1 is an example. For example, the functional components of the communication quality prediction device 100 shown in FIG. 1 may be distributed across multiple devices.

[0031] (Processing Overview) FIG. 2 is a diagram illustrating an overview of a communication quality prediction process according to the first embodiment.

[0032] For example, as shown in FIG. 2 , the parameter prediction unit 102 inputs time-series data 201 of predetermined wireless communication parameters A, B, ..., X to an RNN (Recurrent Neural Network) 202, and obtains prediction results of the wireless communication parameters A, B, ..., X after a predetermined time has elapsed.

[0033] Here, the RNN 202 is a neural network (NN) that can handle time-series data as input data. The RNN 202 has been machine-trained in advance using, for example, time-series data 201 of wireless communication parameters A, B, ..., X as input data and wireless communication parameters A, B, ..., X actually measured after a predetermined time has elapsed as correct answer data.

[0034] The parameter prediction unit 102 inputs time series data 201 of wireless communication parameters A, B, ..., X into this trained RNN 202, thereby obtaining prediction results of the wireless communication parameters A, B, ..., X after a predetermined time has elapsed.

[0035] The communication quality prediction unit 103 uses the prediction results of the wireless communication parameters A, B, ..., X after a predetermined time has elapsed, predicted by the parameter prediction unit 102, to obtain a prediction result of the communication quality (e.g., throughput) after a predetermined time has elapsed, for example, by deep learning, machine learning, an estimation formula, or the like.

[0036] In this way, the communication quality prediction system 1 has a two-stage configuration in which, in addition to time series prediction using the most recent wireless communication parameters, wireless communication quality at the predicted time is estimated from the predicted wireless communication parameters.

[0037] As a result, according to this embodiment, the communication quality prediction system 1 that predicts the communication quality of a wireless communication system can predict communication quality such as throughput that changes depending on the surrounding conditions or the usage status of the wireless communication system.

[0038] <Processing Flow> Next, a description will be given of the processing flow of the communication quality prediction method according to Example 1. Fig. 3 is a flowchart showing an example of the communication quality prediction processing according to Example 1. This processing shows an example of the communication quality prediction processing executed by the communication quality prediction system 1 described with reference to Figs.

[0039] In step S301, the parameter acquisition unit 101 acquires predetermined wireless communication parameters A, B, ..., X, and stores the acquired wireless communication parameters A, B, ..., X in the parameter storage unit 111. The communication quality prediction system 1 can acquire time-series data of the wireless communication parameters A, B, ..., X by repeatedly executing this process.

[0040] In step S302, the communication quality prediction system 1 determines whether an inquiry about communication quality has been received. If an inquiry about communication quality has been received, the communication quality prediction system 1 proceeds to step S303. On the other hand, if an inquiry about communication quality has not been received, the communication quality prediction system 1 returns to step S301.

[0041] In step S303, the parameter prediction unit 102 predicts the wireless communication parameters A, B, ..., X after a predetermined time has elapsed, using the time-series data of the wireless communication parameters A, B, ..., X. For example, as described in FIG. 2 , the parameter prediction unit 102 inputs the time-series data 201 of the wireless communication parameters A, B, ..., X to the trained RNN 202, thereby obtaining the prediction results of the wireless communication parameters A, B, ..., X after a predetermined time has elapsed.

[0042] In step S304, the communication quality prediction unit 103 predicts communication quality after a predetermined time has elapsed, using the prediction results of the wireless communication parameters A, B, ..., X by the parameter prediction unit 102. For example, the communication quality prediction unit 103 predicts communication quality such as throughput after a predetermined time has elapsed, from the prediction results of the wireless communication parameters A, B, ..., X, using deep learning, machine learning, an estimation formula, or the like.

[0043] In step S305, the communication quality prediction unit 103 provides the communication quality prediction result to the source of the communication quality inquiry (for example, a communication terminal, etc.).

[0044] By the process of FIG. 3, the communication quality prediction system 1 can predict communication quality such as throughput that changes depending on the surrounding conditions or the usage status of the wireless communication system, and provide the predicted communication quality result.

[0045] <Example of Communication Quality Prediction Model> Fig. 4 is a diagram illustrating an example of a communication quality prediction model according to Example 1. This diagram illustrates a specific example of a communication quality prediction model 400 that performs the process of predicting the communication quality described in Fig. 2 .

[0046] In the example of FIG. 4, the predetermined wireless communication parameter is p ｔ , m which is the MCS (Modulation and Coding Scheme) at time t ｔ , and r is the resource block at time t ｔ The three wireless communication parameters are: ｔ , m ｔ , r ｔ The time series data of the most recent 50 time steps is used as input data 401.

[0047] In the example of Fig. 4, the parameter prediction unit 102 is configured with a GRU (Gated Recurrent Unit) layer 402 with 30 nodes, a fully connected layer 403 with two layers with 30 nodes, and a fully connected layer 404 with three nodes. Here, the GRU layer 402 is an RNN layer that learns the dependency between time steps of time series data. In addition, the fully connected layer 404 learns the wireless communication parameter p after 5 seconds. ｔ＋５ , m ｔ＋５ , r ｔ＋５ The output layer outputs the prediction result 411. Note that "5 seconds" is an example of a predetermined time.

[0048] In the example of FIG. 4, the communication quality prediction unit 103 predicts the wireless communication parameter p ｔ＋５ , m ｔ＋５ , r ｔ＋５ Using the prediction result 411, the throughput after 5 seconds is predicted by a decision tree 405. Note that "throughput" is an example of communication quality that changes depending on the surrounding conditions, the usage status of the wireless communication system, etc.

[0049] Here, the decision tree is a machine learning technique that uses a tree structure to find explanatory variables that affect a target variable. The communication quality prediction unit 103 may predict the throughput after a predetermined time has elapsed using a technique other than the decision tree.

[0050] 5 is a diagram showing an example of a communication quality prediction result according to Example 1. This diagram shows an example of a prediction result of throughput after 5 seconds, predicted using the communication quality prediction model 400 of FIG. 4. In FIG. 5, the horizontal axis represents time (number of samples) and the vertical axis represents throughput (UL Throughput), and the predicted value of throughput after 5 seconds and the actual value of throughput after 5 seconds are shown. In this way, it was confirmed that the communication quality prediction system 1 according to this embodiment can predict the throughput after 5 seconds, which changes depending on the surrounding conditions, the usage status of the wireless communication system, etc.

[0051] [Example 2] In Example 1, the input data input to the parameter prediction unit 102 is described as being wireless communication parameters. However, the input data input to the parameter prediction unit 102 may include information other than wireless communication parameters.

[0052] <System Configuration> Fig. 6 is a diagram showing an example of the system configuration of a communication quality prediction system according to the second embodiment. As shown in Fig. 6, the communication quality prediction system 1 according to the second embodiment has functional configurations such as a parameter acquisition unit 101, a parameter prediction unit 102, a communication quality prediction unit 103, a parameter storage unit 111, a map and building data acquisition unit 601, a people flow data acquisition unit 602, a device information acquisition unit 603, a map and building data storage unit 611, a people flow data storage unit 612, and a device information storage unit 613.

[0053] As in the first embodiment, the parameter acquisition unit 101 executes a parameter acquisition process of acquiring one or more wireless parameters for wireless communication and storing the acquired wireless parameters in the parameter storage unit 111. As in the first embodiment, the parameter storage unit 111 stores the one or more wireless communication parameters acquired by the parameter acquisition unit 101 in chronological order.

[0054] As in Example 1, the communication quality prediction unit 103 executes a communication quality prediction process to predict the communication quality of wireless communication after a predetermined time has elapsed, using the prediction results of one or more wireless communication parameters predicted by the parameter prediction unit 102.

[0055] The map and building data acquisition unit 601 is realized by, for example, a program executed by a computer included in the communication quality prediction device 100, and acquires map data, building data, and the like of the communication area of ​​the wireless communication system. The map and building data acquisition unit 601 also stores the acquired map data, building data, and the like in the map and building data storage unit 611. Here, the map data and building data include, for example, data such as average building height or road width. The map data and building data are examples of environmental data of the communication area of ​​the wireless communication system.

[0056] The people flow data acquisition unit 602 is realized, for example, by a program executed by a computer included in the communication quality prediction device 100, and acquires people flow data in the communication area of ​​the wireless communication system and stores the acquired people flow data in the people flow data storage unit 612. Here, the people flow data includes, for example, information such as the number of people in the communication area of ​​the wireless communication system. Note that the people flow data is another example of environmental data for the communication area of ​​the wireless communication system.

[0057] The device information acquisition unit 603 is realized by, for example, a program executed by a computer included in the communication quality prediction device 100, acquires device information of the communication terminal, and stores the acquired device information in the device information storage unit 613. Here, the device information includes, for example, information such as location information of the communication terminal, supported wireless standards, and transmission power.

[0058] The map and building data acquisition unit 601, the people flow data acquisition unit 602, and the device information acquisition unit 603 are included in the information acquisition unit 600, which acquires, for example, environmental data of the communication area of ​​wireless communication or device information of the communication terminal performing wireless communication.

[0059] The map and building data storage unit 611 is a storage unit that stores the map and building data acquired by the map and building data acquisition unit 601. The people flow data storage unit 612 is a storage unit that stores the people flow data acquired by the people flow data acquisition unit 602. The device information storage unit 613 is a storage unit that stores the device information acquired by the device information acquisition unit 603.

[0060] The parameter prediction unit 102 according to the second embodiment predicts one or more wireless communication parameters after a predetermined time has elapsed, using the information acquired by the information acquisition unit 600 in addition to one or more wireless communication parameters.

[0061] (Processing Overview) FIG. 7 is a diagram illustrating an overview of a communication quality prediction process according to the second embodiment.

[0062] As shown in FIG. 7 , for example, the parameter prediction unit 102 inputs time-series data 201 of a predetermined wireless communication parameter and information 701 acquired by the information acquisition unit 600 into an NN (Neural Network) 702, and obtains a prediction result of the wireless communication parameter after a predetermined time has elapsed.

[0063] Here, the NN 702 has been machine-learned in advance using, for example, the time-series data 201 of the wireless communication parameters and the information 701 acquired by the information acquisition unit 600 as input data, and the wireless communication parameters A, B, ..., X actually measured after a predetermined time has elapsed as correct answer data.

[0064] The parameter prediction unit 102 can obtain prediction results of the wireless communication parameters A, B, ..., X after a predetermined time has elapsed by inputting the time-series data 201 of the wireless communication parameters and the information 701 acquired by the information acquisition unit 600 into this trained NN 702. With this method, the parameter prediction unit 102 can improve the prediction accuracy of the wireless communication parameters after a predetermined time has elapsed.

[0065] <Processing Flow> Next, a description will be given of the processing flow of the communication quality prediction method according to Example 2. Fig. 8 is a flowchart showing an example of the communication quality prediction processing according to Example 2. This processing shows an example of the communication quality prediction processing executed by the communication quality prediction system 1 described with reference to Figs.

[0066] In step S801, the parameter acquisition unit 101 acquires predetermined wireless communication parameters A, B, . . . , X, and stores the acquired wireless communication parameters A, B, .

[0067] In step S802, the communication quality prediction system 1 determines whether an inquiry about communication quality has been received from, for example, a communication terminal, etc. If an inquiry about communication quality has been received, the communication quality prediction system 1 proceeds to step S803. On the other hand, if an inquiry about communication quality has not been received, the communication quality prediction system 1 returns the process to step S801.

[0068] In step S803, the information acquisition unit 600 acquires device information of the communication terminal and environmental data of the wireless communication area. For example, the information acquisition unit 600 acquires device information including information such as the location information of the communication terminal, the supported wireless standard, and transmission power from the device information storage unit 613 or the communication terminal, etc. In addition, the information acquisition unit 600 acquires, for example, a map, building data, and people flow data corresponding to the location of the communication terminal from the map, building data storage unit 611, the people flow data storage unit 612, an external server, etc.

[0069] In step S804, the parameter prediction unit 102 predicts the wireless communication parameters A, B, ..., X after a predetermined time has elapsed, using the time-series data of the wireless communication parameters A, B, ..., X and the information acquired by the information acquisition unit 600. For example, as described in Fig. 7 , the parameter prediction unit 102 inputs the time-series data 201 of the wireless communication parameters and the information 701 acquired by the information acquisition unit 600 to the trained NN 702, and obtains the prediction results of the wireless communication parameters A, B, ..., X after a predetermined time has elapsed.

[0070] In step S805, the communication quality prediction unit 103 predicts the communication quality after a predetermined time has elapsed, using the prediction results of the wireless communication parameters A, B, . . . , X by the parameter prediction unit 102, in the same manner as in the first embodiment.

[0071] In step S806, the communication quality prediction unit 103 provides the communication quality prediction result to the communication terminal that has made the inquiry about the communication quality.

[0072] By the process of FIG. 8, the communication quality prediction system 1 can improve the accuracy of prediction of communication quality by using environmental information of the communication area of ​​wireless communication, device information of the communication terminal, and the like.

[0073] <Hardware Configuration Example> (Hardware Configuration of Communication Quality Prediction Device) Fig. 9 is a diagram showing an example of the hardware configuration of a computer. The communication quality prediction device 100 has, for example, the hardware configuration of a computer 900 as shown in Fig. 9. Alternatively, the communication quality prediction device 100 is configured by a plurality of computers 900.

[0074] In the example of FIG. 9, a computer 900 includes a processor 901, a memory 902, a storage device 903, a communication device 904, an input device 905, an output device 906, a bus B, and the like.

[0075] The processor 901 is, for example, an arithmetic unit such as a CPU (Central Processing Unit) that executes predetermined programs to realize various functions. The memory 902 is a storage medium readable by the computer 900, and includes, for example, a RAM (Random Access Memory) and a ROM (Read Only Memory). The storage device 903 is a computer-readable storage medium, and may include, for example, a HDD (Hard Disk Drive), an SSD (Solid State Drive), various optical disks, and magneto-optical disks.

[0076] The communication device 904 includes one or more pieces of hardware (communication devices) for communicating with other devices via a wireless or wired network. The input device 905 is an input device (e.g., a keyboard, a mouse, a microphone, a switch, a button, a sensor, etc.) that accepts input from the outside. The output device 906 is an output device (e.g., a display, a speaker, an LED lamp, etc.) that outputs to the outside. Note that the input device 905 and the output device 906 may be integrated into one device (e.g., an input / output device such as a touch panel display).

[0077] The bus B is commonly connected to the above components and transmits, for example, address signals, data signals, and various control signals. The processor 901 is not limited to a CPU, and may be, for example, a DSP (Digital Signal Processor), a PLD (Programmable Logic Device), or an FPGA (Field Programmable Gate Array).

[0078] (Supplementary Note) The communication quality prediction device 100 in this embodiment is not limited to being realized by a dedicated device, but may also be realized by a general-purpose computer. In this case, a program for realizing this function may be recorded on a computer-readable recording medium, and the program recorded on this recording medium may be read into a computer system and executed to realize the function. Note that the term "computer system" here includes hardware such as an OS and peripheral devices.

[0079] Furthermore, "computer-readable recording medium" includes various storage devices such as portable media such as flexible disks, optical magnetic disks, ROMs, CD-ROMs, and storage devices built into computer systems. Furthermore, "computer-readable recording medium" may also include devices that dynamically store a program for a short period of time, such as a communication line when transmitting a program via a network such as the Internet or a communication line such as a telephone line, and devices that store a program for a certain period of time, such as volatile memory within a computer system that serves as a server or client in such cases.

[0080] Furthermore, the above program may be one that realizes part of the above-mentioned functions, or may be one that can realize the above-mentioned functions in combination with a program already recorded in a computer system, or may be one that is realized using hardware such as a PLD or FPGA.

[0081] <Effects of the embodiment> According to the present embodiment, the communication quality prediction system 1 that predicts the communication quality of a wireless communication system can predict communication quality such as throughput that changes depending on the surrounding conditions or the usage status of the wireless communication system.

[0082] This will enable stable use of wireless communications and applications, such as switching the connection of terminals (wireless base stations) in response to deterioration in communication quality, or changing the driving route of self-driving cars.

[0083] Summary of Embodiments This specification discloses at least the following communication quality prediction systems, communication quality prediction methods, and programs. (Item 1) A communication quality prediction system for predicting communication quality of wireless communication, comprising: a parameter acquisition unit for acquiring one or more wireless communication parameters of the wireless communication; a parameter prediction unit for predicting the one or more wireless communication parameters after a predetermined time has elapsed using time-series data of the one or more wireless communication parameters; and a communication quality prediction unit for predicting the communication quality of the wireless communication after the predetermined time has elapsed using a prediction result of the one or more wireless parameters predicted by the parameter prediction unit. (Item 2) The communication quality prediction system according to Item 1, wherein the communication quality of the wireless communication includes a throughput of a communication terminal performing the wireless communication. (Item 3) The communication quality prediction system according to Item 1 or 2, wherein the one or more wireless communication parameters include one or more parameters of received power, MCS, and resource blocks. (4) The communication quality prediction system according to any one of paragraphs 1 to 3, further comprising an information acquisition unit that acquires environmental data of a communication area of ​​the wireless communication or device information of a communication terminal that performs the wireless communication, and the parameter prediction unit predicts the one or more wireless communication parameters after the predetermined time has elapsed by further using the information acquired by the information acquisition unit. (5) A communication quality prediction method, wherein a communication quality prediction system that predicts the communication quality of wireless communication executes: an acquisition process that acquires one or more wireless communication parameters of the wireless communication; a parameter prediction process that predicts the one or more wireless communication parameters after the predetermined time has elapsed by using time-series data of the one or more wireless communication parameters; and a communication quality prediction process that predicts the communication quality of the wireless communication after the predetermined time has elapsed by using a prediction result of the one or more wireless parameters predicted by the parameter prediction process.(Clause 6) A program, or a storage medium storing a program, that causes a computer that predicts communication quality of wireless communication to execute: an acquisition process that acquires one or more wireless communication parameters of the wireless communication; a parameter prediction process that predicts the one or more wireless communication parameters after a predetermined time has elapsed using time series data of the one or more wireless communication parameters; and a communication quality prediction process that predicts the communication quality of the wireless communication after the predetermined time has elapsed using the prediction results of the one or more wireless parameters predicted by the parameter prediction process.

[0084] Although the present embodiment has been described above, the present invention is not limited to such a specific embodiment, and various modifications and changes are possible within the scope of the gist of the present invention described in the claims.

[0085] REFERENCE SIGNS LIST 1 Communication quality prediction system 100 Communication quality prediction device 101 Parameter acquisition unit 102 Parameter prediction unit 103 Communication quality prediction unit 600 Information acquisition unit 601 Map and building data acquisition unit 602 People flow data acquisition unit 603 Device information acquisition unit 900 Computer

Claims

1. A communication quality prediction system for predicting communication quality of wireless communication, comprising: a parameter acquisition unit for acquiring one or more wireless communication parameters of the wireless communication; a parameter prediction unit for predicting the one or more wireless communication parameters after a predetermined time has elapsed using time series data of the one or more wireless communication parameters; and a communication quality prediction unit for predicting the communication quality of the wireless communication after the predetermined time has elapsed using the prediction results of the one or more wireless parameters predicted by the parameter prediction unit.

2. The communication quality prediction system according to claim 1, wherein the communication quality predicted by said communication quality prediction unit includes a throughput of a communication terminal performing said wireless communication.

3. The communication quality prediction system according to claim 1, wherein the one or more wireless communication parameters include one or more of received power, MCS, and resource blocks.

4. A communication quality prediction system as described in claim 1 or 3, further comprising an information acquisition unit that acquires environmental data of the communication area of ​​the wireless communication or device information of the communication terminal performing the wireless communication, and the parameter prediction unit further uses the information acquired by the information acquisition unit to predict the one or more wireless communication parameters after the specified time has elapsed.

5. A communication quality prediction method, comprising: a communication quality prediction system for predicting the communication quality of wireless communication, performing an acquisition process for acquiring one or more wireless communication parameters of the wireless communication; a parameter prediction process for predicting the one or more wireless communication parameters after a predetermined time has elapsed using time series data of the one or more wireless communication parameters; and a communication quality prediction process for predicting the communication quality of the wireless communication after the predetermined time has elapsed using the prediction results of the one or more wireless parameters predicted by the parameter prediction process.

6. A program causing a computer to execute the following steps for predicting communication quality of wireless communication: an acquisition process for acquiring one or more wireless communication parameters of the wireless communication; a parameter prediction process for predicting the one or more wireless communication parameters after a predetermined time has elapsed using time series data of the one or more wireless communication parameters; and a communication quality prediction process for predicting the communication quality of the wireless communication after the predetermined time has elapsed using the prediction results of the one or more wireless parameters predicted by the parameter prediction process.

Images