Self-similarity hurst parameter estimation with rescaled range method on ip-based campus internet traffic

Murizah Kassim, Noor Laili Ismail, Roslina Mohamad, Saiful Izwan Suliman, Mahamod Ismail

Research output: Contribution to journalArticle

Abstract

Self-similarity network traffic is considered as one of stochastic process studies in telecommunications engineering. In determining self-similarity traffic, Hurst value is an important parameter to be measured. This paper presents self-similarity traffic measurement using Rescaled Range, R/S statistical method in estimating Hurst parameter value. Inbound internet traffics on an IP-based campus network in Malaysia, which implements a 16.0 Mbps speed to internet and supports 10GE bandwidth at switch level, are captured and measured. The objectives of this research are to observe and present the existence level of Hurst parameter value, type of self-similarity and overall percentage of Hurts parameter estimation. The inbound traffic is measured due to its relevancy to next development on policing and shaping algorithm traffic model. Solarwinds Net Flow machine is setup on a campus gateway to its Wide Area Network (WAN). Data of the traffic like in flow, size and speed were taken over 20 days and 14 weeks in different inter-arrival time. These traffics are analysed, which lead to the impacts of packet loss, throughput and speed in network performance. Results present the Hurst parameter value, the existence of Long Range Dependant Self-similarity traffic distribution and percentage level of Hurst parameter value for the three types of captured traffic.

Original languageEnglish
Pages (from-to)287-302
Number of pages16
JournalPertanika Journal of Science and Technology
Volume25
Issue numberS4
Publication statusPublished - 1 Apr 2017

Fingerprint

traffic
Internet
Parameter estimation
Stochastic Processes
Telecommunications
Malaysia
Gateways (computer networks)
Wide area networks
Packet loss
Network performance
Random processes
Telecommunication traffic
Telecommunication
Statistical methods
methodology
Switches
Research
Throughput
Bandwidth
parameter estimation

Keywords

  • Analysis
  • Hurst Parameter Estimation
  • Internet traffic
  • Network performance
  • Self-similarity

ASJC Scopus subject areas

  • Computer Science(all)
  • Chemical Engineering(all)
  • Environmental Science(all)
  • Agricultural and Biological Sciences(all)

Cite this

Self-similarity hurst parameter estimation with rescaled range method on ip-based campus internet traffic. / Kassim, Murizah; Ismail, Noor Laili; Mohamad, Roslina; Suliman, Saiful Izwan; Ismail, Mahamod.

In: Pertanika Journal of Science and Technology, Vol. 25, No. S4, 01.04.2017, p. 287-302.

Research output: Contribution to journalArticle

Kassim, M, Ismail, NL, Mohamad, R, Suliman, SI & Ismail, M 2017, 'Self-similarity hurst parameter estimation with rescaled range method on ip-based campus internet traffic', Pertanika Journal of Science and Technology, vol. 25, no. S4, pp. 287-302.
Kassim, Murizah ; Ismail, Noor Laili ; Mohamad, Roslina ; Suliman, Saiful Izwan ; Ismail, Mahamod. / Self-similarity hurst parameter estimation with rescaled range method on ip-based campus internet traffic. In: Pertanika Journal of Science and Technology. 2017 ; Vol. 25, No. S4. pp. 287-302.
@article{d8f1855d1c3441319f2deae6df9128b9,
title = "Self-similarity hurst parameter estimation with rescaled range method on ip-based campus internet traffic",
abstract = "Self-similarity network traffic is considered as one of stochastic process studies in telecommunications engineering. In determining self-similarity traffic, Hurst value is an important parameter to be measured. This paper presents self-similarity traffic measurement using Rescaled Range, R/S statistical method in estimating Hurst parameter value. Inbound internet traffics on an IP-based campus network in Malaysia, which implements a 16.0 Mbps speed to internet and supports 10GE bandwidth at switch level, are captured and measured. The objectives of this research are to observe and present the existence level of Hurst parameter value, type of self-similarity and overall percentage of Hurts parameter estimation. The inbound traffic is measured due to its relevancy to next development on policing and shaping algorithm traffic model. Solarwinds Net Flow machine is setup on a campus gateway to its Wide Area Network (WAN). Data of the traffic like in flow, size and speed were taken over 20 days and 14 weeks in different inter-arrival time. These traffics are analysed, which lead to the impacts of packet loss, throughput and speed in network performance. Results present the Hurst parameter value, the existence of Long Range Dependant Self-similarity traffic distribution and percentage level of Hurst parameter value for the three types of captured traffic.",
keywords = "Analysis, Hurst Parameter Estimation, Internet traffic, Network performance, Self-similarity",
author = "Murizah Kassim and Ismail, {Noor Laili} and Roslina Mohamad and Suliman, {Saiful Izwan} and Mahamod Ismail",
year = "2017",
month = "4",
day = "1",
language = "English",
volume = "25",
pages = "287--302",
journal = "Pertanika Journal of Science and Technology",
issn = "0128-7680",
publisher = "Universiti Putra Malaysia",
number = "S4",

}

TY - JOUR

T1 - Self-similarity hurst parameter estimation with rescaled range method on ip-based campus internet traffic

AU - Kassim, Murizah

AU - Ismail, Noor Laili

AU - Mohamad, Roslina

AU - Suliman, Saiful Izwan

AU - Ismail, Mahamod

PY - 2017/4/1

Y1 - 2017/4/1

N2 - Self-similarity network traffic is considered as one of stochastic process studies in telecommunications engineering. In determining self-similarity traffic, Hurst value is an important parameter to be measured. This paper presents self-similarity traffic measurement using Rescaled Range, R/S statistical method in estimating Hurst parameter value. Inbound internet traffics on an IP-based campus network in Malaysia, which implements a 16.0 Mbps speed to internet and supports 10GE bandwidth at switch level, are captured and measured. The objectives of this research are to observe and present the existence level of Hurst parameter value, type of self-similarity and overall percentage of Hurts parameter estimation. The inbound traffic is measured due to its relevancy to next development on policing and shaping algorithm traffic model. Solarwinds Net Flow machine is setup on a campus gateway to its Wide Area Network (WAN). Data of the traffic like in flow, size and speed were taken over 20 days and 14 weeks in different inter-arrival time. These traffics are analysed, which lead to the impacts of packet loss, throughput and speed in network performance. Results present the Hurst parameter value, the existence of Long Range Dependant Self-similarity traffic distribution and percentage level of Hurst parameter value for the three types of captured traffic.

AB - Self-similarity network traffic is considered as one of stochastic process studies in telecommunications engineering. In determining self-similarity traffic, Hurst value is an important parameter to be measured. This paper presents self-similarity traffic measurement using Rescaled Range, R/S statistical method in estimating Hurst parameter value. Inbound internet traffics on an IP-based campus network in Malaysia, which implements a 16.0 Mbps speed to internet and supports 10GE bandwidth at switch level, are captured and measured. The objectives of this research are to observe and present the existence level of Hurst parameter value, type of self-similarity and overall percentage of Hurts parameter estimation. The inbound traffic is measured due to its relevancy to next development on policing and shaping algorithm traffic model. Solarwinds Net Flow machine is setup on a campus gateway to its Wide Area Network (WAN). Data of the traffic like in flow, size and speed were taken over 20 days and 14 weeks in different inter-arrival time. These traffics are analysed, which lead to the impacts of packet loss, throughput and speed in network performance. Results present the Hurst parameter value, the existence of Long Range Dependant Self-similarity traffic distribution and percentage level of Hurst parameter value for the three types of captured traffic.

KW - Analysis

KW - Hurst Parameter Estimation

KW - Internet traffic

KW - Network performance

KW - Self-similarity

UR - http://www.scopus.com/inward/record.url?scp=85049122415&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85049122415&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:85049122415

VL - 25

SP - 287

EP - 302

JO - Pertanika Journal of Science and Technology

JF - Pertanika Journal of Science and Technology

SN - 0128-7680

IS - S4

ER -