Network traffic prediction method and device and computer readable storage medium

Abstract

The invention discloses a network traffic prediction method and device and a computer readable storage medium, and relates to the field of data communication. The network traffic prediction method comprises the following steps: acquiring a related link of a to-be-detected link, wherein the related link is a link of which the traffic correlation with the to-be-detected link is greater than a preset degree in a network; generating a historical traffic sequence according to the traffic of the link to be measured and the related links thereof at one or more historical moments; and inputting the historical traffic sequence into a pre-trained prediction model to obtain the traffic, output by the prediction model, of the to-be-measured link at the future moment. According to the embodiment of the invention, the traffic prediction can be carried out according to the historical traffic data of the associated link, so that the predicted network traffic is more accurate. Therefore, a more accurate reference basis can be provided for network planning, network optimization and network configuration.

Description

technical field [0001] The present invention relates to the field of data communication, in particular to a network traffic prediction method, device and computer-readable storage medium. Background technique [0002] Deep learning is a powerful artificial intelligence technology. With enough samples for training, the trained model can be used to predict unknown samples. The field of data communication can also be combined with deep learning technology to carry out relevant data modeling, which is expected to make data communication more intelligent. [0003] In a communication network, traffic data generally exhibits non-stationary and nonlinear characteristics. For time series data such as flow data, traditional time series processing methods such as ARIMA (Autoregressive Integrated Moving Average model) are difficult to capture its complex laws, resulting in poor prediction results. As a typical time series problem, traffic forecasting can be modeled by applying the LST...

AI Technical Summary

Problems solved by technology

For time series data such as traffic data, traditional time series processing methods such as ARIMA (Autoregressive Integrated Moving Average model, differential integrated moving average autoregressive model) are difficult to capture its complex laws, resulting in poor forecasting effect

Images