改进的基于小波变换和FARIMA模型的网络流量预测算法  

Network traffic prediction based on wavelet transformation and FARIIMA

作　　者：陈晓天[1] 刘静娴[1] 

机构地区：[1]南京邮电大学通信与信息工程学院,江苏南京210003

出　　处：《通信学报》2011年第4期153-157,165,共6页Journal on Communications

摘　　要：提出了一种改进的基于小波变换和FARIMA模型的网络流量预测算法,先对经过预处理的流量进行小波分解,再进行Mallat算法单支重构,接着用FARIMA模型分别对重构后的单支进行预测,最后合成流量。该算法较之传统的首先用FARIMA模型对小波系数进行预测再进行小波重构的算法减小了预测误差。仿真实验也验证了改进算法的预测准确性。An advanced network traffic prediction method based on wavelet transformation and FARIMA model was put forward.In the method,the original data was decomposed and reconstructed with Mallat algorithm,then FARIMA model was applied on each branch to predict and integrate the traffic.Simulation is carried out to verify the accuracy of pro-posed algorithm with real network traffic.Compared with the traditional method,the proposed method reduces the pre-diction error.

关 键 词：小波变换 FARIMA 流量预测 

分 类 号：TN915[电子电信—通信与信息系统]