Wavelet multifractal modeling for network traffic and queuing analysis

被引：2

作者：

Lu, X ^{[1
]}

Wang, K ^{[1
]}

Dou, HJ ^{[1
]}

机构：

[1] Jilin Univ, Coll Commun Engn, Changchun 130025, Jilin, Peoples R China

来源：

2001 INTERNATIONAL CONFERENCE ON COMPUTER NETWORKS AND MOBILE COMPUTING, PROCEEDINGS | 2001年

关键词：

computer network traffic; multifractal; wavelet; modeling; self-similarity;

D O I：

10.1109/ICCNMC.2001.962606

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

In this paper, we give a wavelet-based model of network traffic, which exhibits multifractal character The discovery of the multifractal nature of traffic has made new models and analysis tools for traffic essential, since self-similar or long-range Dependence (LRD) models are far too optimistic in their predictions of performance. Short-range Dependence (SRD) is must be considered especially in flow control (FC) and CRC design. We find that the wavelet-based model can capture important fractal properties like multi-scale variability and bursting that deleteriously affect performance. Experiments and queuing analysis is performed and the results show that the model is matched well with the real data.

引用

页码：260 / 265

页数：4