基于小波分析的网络流量随机模拟  

Stochastic Simulation of Network Traffic Based on Wavelet Analysis

作　　者：魏恒义[1] 程竹林[1] 刘伟娜[1] 曹雪[1] 

机构地区：[1]西安交通大学电子与信息工程学院,西安710049

出　　处：《西安交通大学学报》2003年第2期188-191,共4页Journal of Xi'an Jiaotong University

基　　金：国家“八六三”计划资助项目(2001AA1121l1)

摘　　要：为了快速生成具有自相似特性的模拟网络流量,应用小波变换将实际测量到的网络流量分解成不同尺度下的小波系数(细节信号)和尺度系数(背景信号),并把这些系数分割成长度相等的很多个小段.然后从每个尺度下的细节信号中和背景信号中分别随机抽取一个小段进行叠加,多次重复该操作,就可以得到较长时间范围内的模拟网络流量.采用方差时间曲线图对模拟生成的网络流量的自相似特性进行了分析,结果表明:用该方法模拟的网络流量具有较好的自相似性,而且简单、速度快.In order to rapidly generate the simulated network traffic with self-similarity, the traffic collected from a real network is decomposed into wavelet coefficients (detailed signals) and scale coefficients (background signals) with different scales based on the wavelet analysis, and these coefficients are divided into many parts with the same length. The parts randomly selected from each group of coefficients respectively are then added up. The stochastic network traffic is obtained by repeating this operation. The statistic analysis shows that the network traffic generated by this way possesses a high degree of self-similarity, and the high velocity and simplicity of this method are confirmed.

关 键 词：随机模拟 小波分析 自相似性 网络流量 自相似参数 小波系数 尺度系数 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]