HTTP Traffic Modeling and Analysis with Statistical Process

Jun Uie-Soo; Lee Kwang-Hui

HTTP Traffic Modeling and Analysis with Statistical Process

Jun Uie-Soo, Lee Kwang-Hui, Journal of Internet Computing and Services, Vol. 5, No. 4, pp. 63-76, Aug. 2004
Full Text:

Keywords: HTTP, Traffic Engineering, Network Simulator

Abstract

For efficient design and operation of a communication network, precise simulation of network characteristics is essential. This issue has been the focus of research by several groups. In this study, we first modeled the HTTP traffic which would be employed on simulation on the level of application using the real collected traffic data. There are two different viewpoints on the characteristics of web traffic pattern, Poisson distribution and self-similar characteristics. In our study, the results show that web traffic characteristics do not depend on only one type of distribution, but the traffic can be modeled as composition of these depending on the size of response of Web server. This implicates that the web traffic can be modeled as the combination of two characteristics. We also found that the characteristics of Web traffic rely on the properties of web servers. This result was deployed as a traffic generator in implementing the network simulator (NetDAS).

Statistics

Show / Hide Statistics

Statistics (Cumulative Counts from November 1st, 2017)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.

Cite this article

[APA Style]

Uie-Soo, J. & Kwang-Hui, L. (2004). HTTP Traffic Modeling and Analysis with Statistical Process. Journal of Internet Computing and Services, 5(4), 63-76.

[IEEE Style]

J. Uie-Soo and L. Kwang-Hui, "HTTP Traffic Modeling and Analysis with Statistical Process," Journal of Internet Computing and Services, vol. 5, no. 4, pp. 63-76, 2004.

[ACM Style]

Jun Uie-Soo and Lee Kwang-Hui. 2004. HTTP Traffic Modeling and Analysis with Statistical Process. Journal of Internet Computing and Services, 5, 4, (2004), 63-76.