Communication network traffic prediction method and system, storage medium and computer equipment

Abstract

The invention belongs to the technical field of network communication, and discloses a communication network flow prediction method and system, a storage medium and computer equipment, and the communication network flow prediction method comprises the steps: constructing a network flow data set, and constructing a communication network structure topological graph; a network traffic prediction model based on the graph convolutional neural network and the Transform is constructed, and the graph convolutional neural network and the Transform structure are combined; constructing a network traffic prediction model, coding a communication network topology structure and network traffic time sequence information, and learning space and time characteristics of data; and training the constructed network flow prediction model, and testing the model error by adopting three evaluation methods of a root mean square error, a mean absolute error and a mean absolute percentage error. The graph convolutional neural network is adopted, the spatial features of the topological structure of the communication network switching node are extracted, the model is assisted in predicting the future network flow, and the precision and effectiveness of the model are improved.

Description

technical field [0001] The invention belongs to the technical field of network communication, and in particular relates to a communication network flow prediction method, system, storage medium and computer equipment. Background technique [0002] At present, the communication network plays a very important role in people's social activities, enterprise management, and operation and production. As the scale of the communication network continues to expand and the complexity of the network continues to increase, people's requirements for network management continue to increase. Network traffic is an important parameter to evaluate network operation status and network load. Through real-time monitoring and prediction of network traffic, it is helpful to grasp the network operation status in real time, assist traffic load balancing, network congestion control, energy saving control and packet routing and other networks Efficient implementation of management functions. Therefo...

AI Technical Summary

Problems solved by technology

[0006] (1) The existing technology only considers the temporal characteristics of network traffic, ignoring the important spatial characteristics of network traffic, which in turn affects the accuracy and effectiveness of network traffic prediction

[0007] (2) The existing technology is mainly to realize the prediction of network traffic in a short period of time in the future, and lacks the analysis of high-dimensional time series characteristics of network traffic, which leads to the insensitivity of the traffic prediction model to the periodic distribution of network traffic in a long period of time. The poor performance of long-term network traffic prediction limits the scope of application

Images