Network Traffic Forecast Based on Weighted Support Vector Regression
The forecast of network traffic is important to the network security and availability.However,the traditional prediction methods use uniform time weight and are lack of generalizing ability which results in the low prediction accuracy.In this article,we calculate the time weight of each history traffic data by its time interval to the prediction point.To incorporate the time weight into the prediction model,we employ the weighted support vector regression model to predict the network traffic.The prediction accuracy could be raised attributes to the generalizing ability of w-SVR and the unique weight of each training data.The simulated results show that the prediction errors ration of wSVR is decreased by 37.4% and 65.6% compared with ANN and AR model while the standard deviation is decreased by 46.2% and 53.3%.
support vector regression prediction network traffic network security
Yun ZHAO Wei XIAO Alin CHEN
Information Technology Center Chongqing Normal University Chongqing,China
国际会议
太原
英文
532-535
2011-02-26(万方平台首次上网日期,不代表论文的发表时间)