Network Traffic Forecast Based on Weighted Support Vector Regression

摘要：

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％.

关键词： support vector regression prediction network traffic network security

作者: Yun ZHAO Wei XIAO Alin CHEN

作者单位: Information Technology Center Chongqing Normal University Chongqing,China

会议类型: 国际会议

会议名称: 2011 3rd International Conference on Computer and Network Technology(ICCNT 2011)(2011第三届IEEE计算机与网络技术国际会议)

会议地点: 太原

会议语种:英文

页码: 532-535

在线出版日期: 2011-02-26（万方平台首次上网日期，不代表论文的发表时间）