Server System

Abstract

Reduce overhead associated with data collection. [Solution] The server system comprises a plurality of prediction servers and an intermediary server that mediates the exchange of data between the plurality of prediction servers. One prediction server comprises an acquisition means for acquiring communication service logs relating to one partial communication area, a prediction means for predicting the future communication service quality of one partial communication area based on the communication service logs, and a communication means for transmitting the first prediction result by the prediction means to the intermediary server and selectively receiving the second prediction result by other prediction servers from the intermediary server. The prediction means uses the first and second prediction results to predict the communication service quality between one node in one partial communication area and other nodes in other partial communication areas. The server system comprises an instruction means for instructing one node to change its communication settings if the predicted communication service quality is lower than a predetermined quality.

Description

Technical Field

[0001] The present invention relates to the technical field of a server system for predicting communication quality.

Background Art

[0002] As this type of system, for example, a system has been proposed that estimates the radio quality in a service target area using a radio wave propagation simulator and predicts the deterioration of radio quality at the future position of a wireless terminal (see Patent Document 1).

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] A digital twin has been proposed in which AI (Artificial Intelligence) performs analysis and simulation on a virtual space using data collected in the real space and provides feedback to the real space. In order to realize a digital twin in the technical field of communication services, for example, it is necessary to collect, store, and analyze a huge amount of communication service logs. For this reason, the overhead related to data collection becomes a problem.

[0005] The present invention has been made in view of the above problems, and an object thereof is to provide a server system capable of suppressing the overhead related to data collection.

Means for Solving the Problems

[0006] A server system according to one aspect of the present invention is a server system comprising a plurality of prediction servers that predict the communication service quality of a partial communication area each is responsible for, and an intermediary server that mediates the exchange of data between the plurality of prediction servers, wherein one of the plurality of prediction servers includes an acquisition means for acquiring a communication service log relating to a partial communication area that the prediction server is responsible for, a prediction means for predicting a first communication service quality, which is the future communication service quality of the partial communication area, based on the communication service log, and a transmission of a first prediction result indicating the first communication service quality to the intermediary server. The server system further includes a communication means for selectively receiving a second prediction result predicted by another prediction server from the intermediary server, wherein the prediction means uses at least one of the first prediction result and the second prediction result to predict a second communication service quality, which is the future communication service quality between one node in one partial communication area and another node in another partial communication area handled by the other prediction server, and the server system further includes an instruction means for instructing the one node to change its communication settings if the second communication service quality is lower than a predetermined quality. [Brief explanation of the drawing]

[0007] [Figure 1] This is a conceptual diagram illustrating the server system according to the embodiment. [Figure 2] This is a block diagram showing the configuration of the server system according to the embodiment. [Modes for carrying out the invention]

[0008] An embodiment of the server system will be described with reference to Figures 1 and 2.

[0009] In Figure 1, server system 1 comprises servers 10a, 10b, and 10c, and server 20. Servers 10a, 10b, and 10c are configured to communicate with each other. For example, MQTT (Message Queue Telemetry Transport) may be used as the communication protocol between servers 10a, 10b, and 10c and server 20. In other words, server system 1 may be a publish-subscribe type system. Note that the number of servers comprising server system 1 is an example and is not limited to this.

[0010] Server 10a may acquire communication service logs from each node included in communication area Ar1. Server 10a may use the acquired communication service logs to recreate the communication environment of communication area Ar1 in a virtual space. Server 10b may acquire communication service logs from each node included in communication area Ar2. Server 10b may use the acquired communication service logs to recreate the communication environment of communication area Ar2 in a virtual space. Server 10c may acquire communication service logs from each node included in communication area Ar3. Server 10c may use the acquired communication service logs to recreate the communication environment of communication area Ar3 in a virtual space. Servers 10a, 10b, and 10c may be referred to as "digital twin servers".

[0011] For example, a node may be a vehicle with communication capabilities, a relay device, a server device, etc. A vehicle with communication capabilities may be a connected car. For example, a communication service log for a vehicle acting as a node may include at least one of the following: the vehicle's location, communication history, communication quality, and server response delay. The vehicle's location may be rephrased as the location of the communication equipment. Communication areas Ar1, Ar2, and Ar3 may each be defined based on at least one of the cells covered by a single radio base station and the area under the jurisdiction of a central office located upstream of each radio base station.

[0012] Server 20 mediates the exchange of data between servers 10a, 10b, and 10c. For example, server 20 may transmit data acquired from server 10a to at least one of servers 10b and 10c. Server 20 may transmit data acquired from server 10b to at least one of servers 10a and 10c. Server 20 may transmit data acquired from server 10c to at least one of servers 10a and 10b. Server 20 may be referred to as a "digital twin broker".

[0013] Next, the operation of server system 1 will be explained with reference to Figure 2 in addition to Figure 1. In Figure 2, server 10a includes a log processing unit 11, a log database 12, a communication environment prediction unit 13, a network setting formulation unit 14, and a communication device 15. Server 20 includes a prediction result distribution unit 21. Servers 10b and 10c may have the same configuration as server 10a. Vehicle 100, acting as a node, includes a log collection unit 110 and a network setting update unit 120.

[0014] The log collection unit 110 of vehicle 100 may send the communication service log to the server 10a responsible for the communication area Ar1 where vehicle 100 is located. The communication service log related to vehicle 100 as a node may include, for example, the history of vehicle 100's location information, the amount of communication data sent and received by vehicle 100, the throughput and latency at that time, the signal strength and S / N ratio (Signal-to-Noise ratio) of the signal received by vehicle 100 from the wireless base station, the server's data processing delay and load level, etc. The log collection unit 110 may also periodically send the communication service log to the server 10a.

[0015] The log processing unit 11 of server 10a may acquire communication service logs transmitted from vehicle 100. The log processing unit 11 may further acquire communication service logs transmitted from nodes other than vehicle 100 that are included in communication area Ar1. The log processing unit 11 may perform predetermined processing or aggregation on the communication service logs acquired from multiple nodes included in communication area Ar1. The log processing unit 11 may store the aggregation results in the log database 12. In addition to the latest aggregation results, the log database 12 may also store past aggregation results.

[0016] The communication environment prediction unit 13 of server 10a may predict, for example, the future behavior of vehicle 100 as a node and the communication performance between nodes within communication area Ar1 (for example, between vehicle 100 and vehicle 101) based on the aggregated results of communication service logs stored in the log database 12. In other words, the communication environment prediction unit 13 may predict the future communication service quality of communication area Ar1. In this case, the communication environment prediction unit 13 may use AI that, upon input of the aggregated results of communication service logs, outputs the future behavior of vehicle 100 and the communication performance between nodes within communication area Ar1.

[0017] Furthermore, the future behavior of vehicle 100 may include the vehicle's movement trajectory, communication volume, communication timing, etc. For predicting the position of vehicle 100 (for example, the vehicle's movement trajectory), the prediction algorithm described in Nachiket Deo, Mohan M. Trivedi; Convolutional Social Pooling for Vehicle Trajectory Prediction, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2018, pp. 1468-1476 may be used. For predicting communication quality, a wireless propagation simulator, a communication simulator, etc., or regression analysis or machine learning may be used.

[0018] The communication device 15 may transmit the first prediction result, which is the prediction result of the communication environment prediction unit 13, to the server 20. The server 20 may store the first prediction result transmitted from server 10a in a storage device (not shown). The prediction result distribution unit 21 of server 20 may transmit the first prediction result to at least one of servers 10b and 10c. For example, the first prediction result may be associated with a topic related to the first prediction result. Based on the topic associated with the first prediction result, the prediction result distribution unit 21 may transmit the first prediction result to the server among servers 10b and 10c that has registered the topic associated with the first prediction result. If there is no server that has registered the topic associated with the first prediction result, the prediction result distribution unit 21 may discard the first prediction result.

[0019] Server 10b may predict the future quality of communication services in communication area Ar2 based on communication service logs (e.g., aggregated results of communication service logs). Server 10b may send a second prediction result indicating the predicted communication service quality to Server 20. The prediction result distribution unit 21 of Server 20 may send the second prediction result to at least one of Servers 10a and 10c.

[0020] Server 10c may predict the future quality of communication services in communication area Ar3 based on communication service logs (e.g., aggregated results of communication service logs). Server 10c may send a third prediction result indicating the predicted communication service quality to server 20. The prediction result distribution unit 21 of server 20 may send the third prediction result to at least one of servers 10a and 10b.

[0021] For example, the communication environment prediction unit 13 of server 10a may predict the future communication service quality between the vehicle 100 as a node within the communication area Ar1 and the server 200 (see FIG. 1) as a node within the communication area Ar2. In this case, the communication device 15 of server 10a may receive the prediction result (for example, the above-described second prediction result) of server 10b responsible for the communication area Ar2 from server 20. Note that, in addition to the prediction result of server 10b, the communication device 15 may receive the prediction results of the communication service quality of one or more servers responsible for each node on the communication path between the vehicle 100 and the server 200 from server 20.

[0022] For example, the communication environment prediction unit 13 of server 10a may predict the future communication service quality between the vehicle 100 and the server 200 by using at least one of the future communication service quality of the communication area Ar1 (for example, the above-described first prediction result) and the prediction result of server 10b (for example, the above-described second prediction result). The communication service quality may include an End-to-End delay. The communication environment prediction unit 13 may input a fourth prediction result indicating the future communication service quality between the vehicle 100 and the server 200 to the network configuration determination unit 14.

[0023] The network configuration determination unit 14 may determine whether the communication service quality indicated by the fourth prediction result satisfies a predetermined required quality. If the communication service quality indicated by the fourth prediction result is lower than the predetermined quality, the network configuration determination unit 14 may transmit a network configuration instruction to the vehicle 100 via the communication device 15. Note that if the communication service quality indicated by the fourth prediction result satisfies the predetermined quality, the network configuration determination unit 14 may not output a network configuration instruction. For example, the network configuration instruction may include at least one of an update of a routing table, a change of a communication destination application server, a change of a communication means, and a change of the data transmission frequency, the detail level of transmitted data, and the compression ratio.

[0024] For example, by updating the routing table, it can be expected that communication traffic is transferred so as to avoid congested network sections. For example, by changing the destination application server, it can be expected that a server with a lower assumed End-to-End delay is selected. For example, changes to the communication means may include at least one of switching and combined use between different cellular lines, and at least one of switching and combined use between different types of communication networks (such as Wi-Fi (registered trademark) / satellite communication, etc.).

[0025] The network setting update unit 120 of the vehicle 100 as a node that has received a network setting instruction may reflect the network setting instruction in communication control.

[0026] In addition, each time the communication environment prediction unit 13 of the server 10a predicts the future communication service quality of the communication area Ar1, the server 10a may transmit a prediction result indicating the newly predicted communication service quality to the server 20 via the communication device 15. When the server 10a transmits a new prediction result to the server 20, the server 10a may delete the past prediction result related to the communication area Ar1 from the server 20.

[0027] For example, when the server system 1 is a Publish-Subscribe type system, the server 10a may selectively receive from the server 20 only the prediction results that the server 10a uses among a plurality of prediction results indicating the quality of communication services predicted by other servers (for example, at least one of the servers 10b and 10c). Thereby, communication overhead can be reduced.

[0028] (Technical effect) In the server system 1, the servers 10a, 10b, and 10c collect communication service logs related to the communication areas Ar1, Ar2, and Ar3 that they are respectively in charge of. For example, compared with a server system in which only one server collects communication service logs, the server system 1 according to the present embodiment can suppress the overhead related to data collection.

[0029] In other words, in order to accurately predict communication service quality such as radio wave reception quality, network congestion, and server processing load, it is necessary to collect a huge amount of communication service logs from each node on the network without delay. In the server system 1 according to this embodiment, multiple servers 10a, 10b, and 10c distribute the communication service quality prediction processing, so that the range over which each of the servers 10a, 10b, and 10c collects communication service logs can be narrowed. As a result, the server system 1 can suppress overhead related to data collection.

[0030] The embodiments of the invention derived from the above-described embodiments are described below.

[0031] A server system according to one aspect of the invention comprises a plurality of prediction servers that predict the communication service quality of a partial communication area each is responsible for, and an intermediary server that mediates the exchange of data between the plurality of prediction servers, wherein one of the plurality of prediction servers includes an acquisition means for acquiring a communication service log relating to a partial communication area that the prediction server is responsible for, a prediction means for predicting a first communication service quality, which is the future communication service quality of the partial communication area, based on the communication service log, and a transmission of a first prediction result indicating the first communication quality service to the intermediary server. The server system further includes a communication means for selectively receiving a second prediction result predicted by another prediction server from the intermediary server, wherein the prediction means uses at least one of the first prediction result and the second prediction result to predict a second communication service quality, which is the future communication service quality between one node in one partial communication area and another node in another partial communication area handled by the other prediction server, and the server system further includes an instruction means for instructing the one node to change its communication settings if the second communication service quality is lower than a predetermined quality.

[0032] In the above-described embodiment, "servers 10a, 10b, and 10c" correspond to an example of a "prediction server," "server 10b" corresponds to an example of an "intermediary server," "log processing unit 11" corresponds to an example of an "acquisition means," "communication environment prediction unit 13" corresponds to an example of a "prediction means," "communication device 15" corresponds to an example of a "communication means," and "network setting formulation unit 14" corresponds to an example of an "instruction means."

[0033] In one example of the server system, the first node may be a vehicle with communication capabilities.

[0034] The present invention is not limited to the embodiments described above, and can be modified as appropriate without contradicting the gist or idea of ​​the invention as can be read from the claims and specification as a whole. Server systems with such modifications are also included within the technical scope of the present invention. [Explanation of Symbols]

[0035] 1…Server system, 10a, 10b, 10c, 20…Server, 11…Log processing unit, 12…Log database, 13…Communication environment prediction unit, 14…Network configuration formulation unit, 15…Communication device, 21…Prediction result distribution unit, 110…Log collection unit, 120…Network configuration update unit

Claims

1. A server system comprising multiple prediction servers that predict the quality of communication services in the respective partial communication areas they are responsible for, and an intermediary server that mediates the exchange of data between the multiple prediction servers, Of the aforementioned multiple prediction servers, one prediction server is: A means for acquiring communication service logs relating to a partial communication area handled by the aforementioned prediction server, A prediction means that predicts a first communication service quality, which is the future communication service quality of one partial communication area, based on the aforementioned communication service log, A communication means for transmitting a first prediction result indicating the first communication quality service to the intermediary server, and selectively receiving a second prediction result predicted by another prediction server among the plurality of prediction servers from the intermediary server, Equipped with, The prediction means uses at least one of the first prediction result and the second prediction result to predict a second communication service quality, which is the future communication service quality between one node in one partial communication area and another node in another partial communication area handled by the other prediction server. The server system further includes an instruction means for instructing one node to change its communication settings when the second communication service quality is lower than a predetermined quality. Server system.

2. The aforementioned node is a vehicle with communication capabilities. The server system according to claim 1.

Images