基于加权支持向量回归的网络流量预测

被引:4
作者
赵云
肖嵬
陈阿林
机构
[1] 重庆师范大学信息技术中心
关键词
网络流量; 预测; 支持向量机; 网络安全;
D O I
暂无
中图分类号
TP393.06 []; TP18 [人工智能理论];
学科分类号
081201 ; 1201 ; 081104 ; 0812 ; 0835 ; 1405 ;
摘要
网络流量预测对于网络的安全和可用性至关重要,但是,传统的网络流量预测方法使用平均时间加权的方法进行预测,缺泛化能力导致预测精度低。基于每一个网络流量历史数据到预测点的时间间隔计算其时间权重,使用带时间权重的加权支持向量回归模型w-SVR预测网络流量。该模型因为其泛化能力和为每个训练数据设置单独的权重而提高了网络流量预测的准确性。模拟实验显示w-SVR模型相对于ANN和AR模型,预测错误率分别降低了37.4%和65.6%,而标准误差降低了46.2%和53.3%。
引用
收藏
页码:103 / 106
页数:4
相关论文
共 8 条
[1]  
Cheng Guang,Gong Jian,Ding Wei.Nonlinear-periodical network traffic behavioral forecast based on seasonal neu-ral network model. International Conference on Com-munications,Circuits and Systems . 2004
[2]  
Wen Yong,Zhu Guangxi,Xie Changsheng.A novel BP neural network model for traffic prediction of next gen-eration network. 4th IEEE International Conference on Circuits and Systems for Communications . 2008
[3]  
Shevade S K,Keerthi S S,Bhattacharyya C,et al.Improvements to the SMO algorithm for SVM regression. IEEE Transactions on Neural Networks . 2000
[4]  
Li Jingfei,Shen Lei,Tong Yong’’an.Prediction of network flow based on wavelet analysis and ARIMA model. International Conference on Wireless Networks and In-formation Systems . 2009
[5]  
Lv Jun,Li Tong,Li Xing.Network traffic prediction al-gorithm and its practical application in real network. International Conference on Network and Parallel Com-puting . 2007
[6]  
Zhaoxia Wang,Tingzhu Hao,Zengqiang Chen,etc all.Predicting nonlinear network traffic using fuzzy neural network. Information, Communications and Signal Processing, 2003 and the Fourth Pacific Rim Conference on Multimedia . 2003
[7]  
Mitchell T.Machine Learning. . 1997
[8]  
Xu Na,Zhang Xinrui.Traffic volume prediction based on improved grey self-adaptable prediction formula. 2010International Conference on Machine Learning and Cy-bernetics . 2010