Comparison of internet Traffic Models: On-Off Self Similar Model Versus Fractional Gaussian Noise Model

Comu, K. and Gavrilovska, L. (2003) Comparison of internet Traffic Models: On-Off Self Similar Model Versus Fractional Gaussian Noise Model. In: Proceedings of the Fourth Conference on Informatics and Information Technology. Institute of Informatics, Faculty of Natural Sciences and Mathematics, Ss. Cyril and Methodius University in Skopje, Macedonia, Skopje, Macedonia, pp. 244-254. ISBN 9989-668-45-0

[img]
Preview
Text
9989-668-45-0_pp244-254.pdf

Download (637kB) | Preview
Official URL: http://ciit.finki.ukim.mk

Abstract

This paper focuses on investigation which model is propriety for generation of artificial Internet traffic streams depending on number of sources n. Two major models applicable to capture the specifics of the Internet traffic are: ON-OFF self-similar model and Fractional Gaussian Noise (FGN) model. ON-OFF series are generated using Pareto distribution and FGN series are generated using spatial renewal process (SRP). The relevant analysis parameters are mean, Hurst parameter, variance and the probability density function (PDF). The result shows that for small n ON-OFF is more appropriate, and for large n the better solution is FGN.

Item Type: Book Section
Uncontrolled Keywords: Internet traffic model, self-similar, fractal, ON-OFF, Pareto, FGN, SRP, PDF
Subjects: International Conference on Informatics and Information Technologies > Wireless and Mobile Computing
Depositing User: Vangel Ajanovski
Date Deposited: 28 Oct 2016 00:15
Last Modified: 28 Oct 2016 00:15
URI: http://eprints.finki.ukim.mk/id/eprint/11146

Actions (login required)

View Item View Item