Mobile traffic prediction method based on space-time attention convolutional network

Abstract

The invention belongs to the technical field of mobile flow prediction, and discloses a mobile flow prediction method based on a space-time attention convolutional network, and the method comprises the steps: enabling the space-time attention convolutional network to carry out the modeling of a mobile flow network in an hour period, a day period and a week period through three time parts, and obtaining three pieces of corresponding mobile flow prediction information; and fusing the three pieces of mobile traffic prediction information with external interference information to obtain a final mobile traffic prediction result. According to the invention, the prediction problem of the mobile flow is effectively solved.

Description

technical field [0001] The invention relates to the technical field of mobile traffic prediction, in particular to a mobile traffic prediction method based on spatio-temporal attention convolutional network. Background technique [0002] According to a new Cisco report, global mobile data traffic is expected to reach 77 exabytes per month by 2022. In order to ensure reliable network management and mobile services, accurate prediction of mobile communication traffic is very necessary. However, due to the highly nonlinear and dynamic spatio-temporal correlation of mobile traffic forecasting, the accuracy of mobile traffic forecasting faces great challenges. [0003] In recent years, a great deal of research has been done on mobile traffic forecasting methods, which are mainly divided into the following two categories: statistics-based methods and machine learning-based methods. In statistics-based methods, the prediction of mobile traffic is based on statistical distribution...

AI Technical Summary

Problems solved by technology

However, capturing the dynamic spatiotemporal correlations of mobile traffic flows using deep learning algorithms remains somewhat challenging.

Images