关键词: 混沌理论, 最小二乘支持向量机, 网络流量, 预测模型

Abstract: In order to improve the prediction accuracy of network traffic, this paper proposes a network traffic forecasting method based on chaotic theory and Least Squares Support Vector Machine. Phase space reconstruction is used to reconstruct the network traffic time series and restore the network flow evolution path, and then the network traffic time series are modeled and trained by Least Squares Support Vector Machines which has good nonlinear forecasting ability, and the parameters of Least Squares Support Vector Machine are optimized by chaotic particle swarm algorithm to obtain the optimal network traffic forecasting model. The forecasting method is tested by the network traffic time series data. The results show that the method can well depict the network flow change trend and improves the forecasting accuracy of network traffic whose forecasting performance is superior to the traditional forecasting method.

Key words: chaotic theory, Least Squares Support Vector Machine（LSSVM）, network traffic, forecasting model