一种关于混合模型的实时网络流量预测算法.pdf

计算机研究与发展 ISSN N 111777TP Journal of Computer Research and Development 43 (5) : 806～812 , 2006 一种基于混合模型的实时网络流量预测算法 1 2 1 1 李 　捷 　刘瑞新 　刘先省 　韩志杰 1 (河南大学计算机与信息工程学院 　开封 　475001) 2 (黄河水利职业技术学院信息工程系 　开封 　475004) (jsjt9 @henu educn) A Real Time Net work Traff ic Prediction Al gorithm Based on Hybrid Model 1 2 1 1 Li Jie , Liu Ruixin , Liu Xianxing , and Han Zhijie 1 ( College of Computer and Inf orm ation Engineering , Henan U niversity , Kaif en g 475001) 2 ( ) Depart ment of Inf orm ation Engineering Science , Yellow River Conservancy Technical Institute , Kaif en g 475004 Abstract 　Distributed applications use predictions of network traffic to sustain their performance by adapt ing their behaviors It has been recognized that the network traffic consists of a majorit y of linear part and a small quantity of nonlinear part which can not be neglected However , existent network traffic prediction algorithms only utilize either linear or nonlinear methods to solve the problem and can not provide enough accuracy and realtime due to the isolated adoption A hybrid network traffic prediction algorithm , is provid ed , in which Kalman filter ( KF) and wavelet are combined Thus the linear part can be processed by KF and the nonlinear part can be done by wavelet Simulation results show that the proposed algorithm can guarantee higher accuracy and better realtime than those algorithms based singly on linear or nonlinear method Key words 　traffic ; prediction ; hybrid model ; QoS 摘 　要 　流量预测是流量工程、拥塞控制和网络管理的核心问题 网络流量由大量的非线性变化部分和 少量的但不可忽