Characterization and control of highly correlated traffic in high speed networks

Ying-Dar Lin; Tian Ren Huang; Yuan Cheng Lai

doi:10.1109/LCN.1996.558127

Characterization and control of highly correlated traffic in high speed networks

Ying-Dar Lin^*, Tian Ren Huang, Yuan Cheng Lai

^*Corresponding author for this work

Department of Computer Science

Research output: Contribution to journal › Conference article › peer-review

2 Scopus citations

Abstract

By assuming network traffic to be independent from each other, the analysis of network performance can be simplified. However, the real traffic sources may have some correlation which makes their behavior tends to converge or diverge. This phenomenon has tremendous influence on the congestion control. In this paper, we explain the possible reasons of the correlated behavior, namely, top-down and client-server correlation, and analyze their impacts. We also use the rapid matrix-geometric solution to investigate the cost to pay when applying the Leaky Bucket input control scheme on the independent, such as Poisson, traffic sources and the correlated, such as ON-OFF and HAP (Hierarchical Arrival Process), traffic sources.

Original language	English
Article number	558127
Pages (from-to)	19-27
Number of pages	9
Journal	Conference on Local Computer Networks
DOIs	https://doi.org/10.1109/LCN.1996.558127
State	Published - 13 Oct 1996
Event	Proceedings of the 1996 21st Conference on Local Computer Networks - Minneapolis, MN, USA Duration: 13 Oct 1996 → 16 Oct 1996

Access to Document

10.1109/LCN.1996.558127

Cite this

@article{2393622ad09847e1a980aee6808fd8e4,

title = "Characterization and control of highly correlated traffic in high speed networks",

abstract = "By assuming network traffic to be independent from each other, the analysis of network performance can be simplified. However, the real traffic sources may have some correlation which makes their behavior tends to converge or diverge. This phenomenon has tremendous influence on the congestion control. In this paper, we explain the possible reasons of the correlated behavior, namely, top-down and client-server correlation, and analyze their impacts. We also use the rapid matrix-geometric solution to investigate the cost to pay when applying the Leaky Bucket input control scheme on the independent, such as Poisson, traffic sources and the correlated, such as ON-OFF and HAP (Hierarchical Arrival Process), traffic sources.",

author = "Ying-Dar Lin and Huang, {Tian Ren} and Lai, {Yuan Cheng}",

year = "1996",

month = oct,

day = "13",

doi = "10.1109/LCN.1996.558127",

language = "English",

pages = "19--27",

journal = "Conference on Local Computer Networks",

issn = "0742-1303",

note = "Proceedings of the 1996 21st Conference on Local Computer Networks ; Conference date: 13-10-1996 Through 16-10-1996",

}

TY - JOUR

T1 - Characterization and control of highly correlated traffic in high speed networks

AU - Lin, Ying-Dar

AU - Huang, Tian Ren

AU - Lai, Yuan Cheng

PY - 1996/10/13

Y1 - 1996/10/13

N2 - By assuming network traffic to be independent from each other, the analysis of network performance can be simplified. However, the real traffic sources may have some correlation which makes their behavior tends to converge or diverge. This phenomenon has tremendous influence on the congestion control. In this paper, we explain the possible reasons of the correlated behavior, namely, top-down and client-server correlation, and analyze their impacts. We also use the rapid matrix-geometric solution to investigate the cost to pay when applying the Leaky Bucket input control scheme on the independent, such as Poisson, traffic sources and the correlated, such as ON-OFF and HAP (Hierarchical Arrival Process), traffic sources.

AB - By assuming network traffic to be independent from each other, the analysis of network performance can be simplified. However, the real traffic sources may have some correlation which makes their behavior tends to converge or diverge. This phenomenon has tremendous influence on the congestion control. In this paper, we explain the possible reasons of the correlated behavior, namely, top-down and client-server correlation, and analyze their impacts. We also use the rapid matrix-geometric solution to investigate the cost to pay when applying the Leaky Bucket input control scheme on the independent, such as Poisson, traffic sources and the correlated, such as ON-OFF and HAP (Hierarchical Arrival Process), traffic sources.

UR - http://www.scopus.com/inward/record.url?scp=0030395379&partnerID=8YFLogxK

U2 - 10.1109/LCN.1996.558127

DO - 10.1109/LCN.1996.558127

M3 - Conference article

AN - SCOPUS:0030395379

SN - 0742-1303

SP - 19

EP - 27

JO - Conference on Local Computer Networks

JF - Conference on Local Computer Networks

M1 - 558127

T2 - Proceedings of the 1996 21st Conference on Local Computer Networks

Y2 - 13 October 1996 through 16 October 1996

ER -

Characterization and control of highly correlated traffic in high speed networks

Abstract

Access to Document

Other files and links

Fingerprint

Cite this