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

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

Fingerprint

Traffic Model
Traffic Modeling
Network Traffic
Network Modeling
Self-similarity
Performance Measures
Reuse
Performance Evaluation
Wide area networks
Traffic
Local area networks
Model

Keywords

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

Cite this

El Abdouni Khayari, Rachid ; Haverkort, Boudewijn R.H.M. ; Sadre, R. ; Ost, Alexander. / The Pseudo-Self-Similar Traffic Model: Application and Validation. In: Performance Evaluation. 2004 ; Vol. 56, No. 1-4. pp. 3-22.
@article{d84fa425c6f7457ca039c6af3093b513,
title = "The Pseudo-Self-Similar Traffic Model: Application and Validation",
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.",
keywords = "IR-47888, Trace-driven simulations, Markovian traffic models, matrix-geometric methods, Queueing, METIS-218877, EWI-7872, Parameter fitting, Self-similarity",
author = "{El Abdouni Khayari}, Rachid and Haverkort, {Boudewijn R.H.M.} and R. Sadre and Alexander Ost",
note = "Imported from research group DACS (ID number 434)",
year = "2004",
doi = "10.1016/j.peva.2003.07.010",
language = "English",
volume = "56",
pages = "3--22",
journal = "Performance Evaluation",
issn = "0166-5316",
publisher = "Elsevier",
number = "1-4",

}

The Pseudo-Self-Similar Traffic Model: Application and Validation. / El Abdouni Khayari, Rachid; Haverkort, Boudewijn R.H.M.; Sadre, R.; Ost, Alexander.

In: Performance Evaluation, Vol. 56, No. 1-4, 2004, p. 3-22.

Research output: Contribution to journalArticleScientificpeer-review

TY - JOUR

T1 - The Pseudo-Self-Similar Traffic Model: Application and Validation

AU - El Abdouni Khayari, Rachid

AU - Haverkort, Boudewijn R.H.M.

AU - Sadre, R.

AU - Ost, Alexander

N1 - Imported from research group DACS (ID number 434)

PY - 2004

Y1 - 2004

N2 - 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.

AB - 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.

KW - IR-47888

KW - Trace-driven simulations

KW - Markovian traffic models

KW - matrix-geometric methods

KW - Queueing

KW - METIS-218877

KW - EWI-7872

KW - Parameter fitting

KW - Self-similarity

U2 - 10.1016/j.peva.2003.07.010

DO - 10.1016/j.peva.2003.07.010

M3 - Article

VL - 56

SP - 3

EP - 22

JO - Performance Evaluation

JF - Performance Evaluation

SN - 0166-5316

IS - 1-4

ER -