The Pseudo-Self-Similar Traffic Model: Application and Validation

Rachid El Abdouni Khayari, Boudewijn R.H.M. Haverkort, R. Sadre, Alexander Ost

Research output: Contribution to journalArticleScientificpeer-review

15 Citations (Scopus)

Abstract

Since the early 1990s, a variety of studies have shown that network traffic, both for local- and wide-area networks, has self-similar properties. This led to new approaches in network traffic modelling because most traditional traffic approaches result in the underestimation of performance measures of interest. Instead of developing completely new traffic models, a number of researchers have proposed to adapt traditional traffic modelling approaches to incorporate aspects of self-similarity. The motivation for doing so is the hope to be able to reuse techniques and tools that have been developed in the past and with which experience has been gained. One such approach is the so-called pseudo-self-similar traffic (PSST) model. This model is appealing, as it is easy to understand and easily embedded in Markovian performance evaluation studies. In applying this model in a number of cases, we have perceived various problems which we initially thought were particular to these specific cases. However, we recently have been able to show that these problems are fundamental to the PSST model. In this paper we review the PSST model, validate it experimentally and discuss its shortcomings. As far as we know, this is the first paper that discusses these shortcomings formally. We also report on ongoing work to overcome some of these problems.
Original languageEnglish
Pages (from-to)3-22
Number of pages20
JournalPerformance Evaluation
Volume56
Issue number1-4
DOIs
Publication statusPublished - 2004
Externally publishedYes

Keywords

  • IR-47888
  • Trace-driven simulations
  • Markovian traffic models
  • matrix-geometric methods
  • Queueing
  • METIS-218877
  • EWI-7872
  • Parameter fitting
  • Self-similarity

Fingerprint

Dive into the research topics of 'The Pseudo-Self-Similar Traffic Model: Application and Validation'. Together they form a unique fingerprint.

Cite this