Additive and multiplicative mixture trees for network traffic modeling

Shriram Sarvotham; Xin Wang; Rudolf H. Riedi; Richard G. Baraniuk

Additive and multiplicative mixture trees for network traffic modeling

Shriram Sarvotham, Xin Wang, Rudolf H. Riedi, Richard G. Baraniuk

Houston Methodist

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

2 Scopus citations

Abstract

Network traffic exhibits drastically different statistics, ranging from nearly Gaussian marginals and Long range dependence at very large time scales to highly non-Gaussian marginals and multifractal scaling on small scales. This behavior can be explained by forming two components of the traffic according to the speed of connections, one component absorbing most traffic and being mostly Gaussian, the other constituting virtually all the small scale bursts. Towards a better understanding of this phenomenon, we propose a novel tree-based model which is flexible enough to accommodate Gaussian as well as bursty behavior on different scales in a parsimonious way.

Original language	English (US)
Title of host publication	ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume	4
State	Published - 2002
Event	2002 IEEE International Conference on Acoustic, Speech, and Signal Processing - Orlando, FL, United States Duration: May 13 2002 → May 17 2002

Other

Other	2002 IEEE International Conference on Acoustic, Speech, and Signal Processing
Country/Territory	United States
City	Orlando, FL
Period	5/13/02 → 5/17/02

Keywords

Fractional Brownian motion
Haar wavelet
Lévy stable motion
Long range dependence
Multifractals
Network traffic modeling

ASJC Scopus subject areas

Electrical and Electronic Engineering
Signal Processing
Acoustics and Ultrasonics

Cite this

@inproceedings{93a170892d7b4096b03a5ba75c58403d,

title = "Additive and multiplicative mixture trees for network traffic modeling",

abstract = "Network traffic exhibits drastically different statistics, ranging from nearly Gaussian marginals and Long range dependence at very large time scales to highly non-Gaussian marginals and multifractal scaling on small scales. This behavior can be explained by forming two components of the traffic according to the speed of connections, one component absorbing most traffic and being mostly Gaussian, the other constituting virtually all the small scale bursts. Towards a better understanding of this phenomenon, we propose a novel tree-based model which is flexible enough to accommodate Gaussian as well as bursty behavior on different scales in a parsimonious way.",

keywords = "Fractional Brownian motion, Haar wavelet, L{\'e}vy stable motion, Long range dependence, Multifractals, Network traffic modeling",

author = "Shriram Sarvotham and Xin Wang and Riedi, {Rudolf H.} and Baraniuk, {Richard G.}",

year = "2002",

language = "English (US)",

volume = "4",

booktitle = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",

note = "2002 IEEE International Conference on Acoustic, Speech, and Signal Processing ; Conference date: 13-05-2002 Through 17-05-2002",

}

TY - GEN

T1 - Additive and multiplicative mixture trees for network traffic modeling

AU - Sarvotham, Shriram

AU - Wang, Xin

AU - Riedi, Rudolf H.

AU - Baraniuk, Richard G.

PY - 2002

Y1 - 2002

N2 - Network traffic exhibits drastically different statistics, ranging from nearly Gaussian marginals and Long range dependence at very large time scales to highly non-Gaussian marginals and multifractal scaling on small scales. This behavior can be explained by forming two components of the traffic according to the speed of connections, one component absorbing most traffic and being mostly Gaussian, the other constituting virtually all the small scale bursts. Towards a better understanding of this phenomenon, we propose a novel tree-based model which is flexible enough to accommodate Gaussian as well as bursty behavior on different scales in a parsimonious way.

AB - Network traffic exhibits drastically different statistics, ranging from nearly Gaussian marginals and Long range dependence at very large time scales to highly non-Gaussian marginals and multifractal scaling on small scales. This behavior can be explained by forming two components of the traffic according to the speed of connections, one component absorbing most traffic and being mostly Gaussian, the other constituting virtually all the small scale bursts. Towards a better understanding of this phenomenon, we propose a novel tree-based model which is flexible enough to accommodate Gaussian as well as bursty behavior on different scales in a parsimonious way.

KW - Fractional Brownian motion

KW - Haar wavelet

KW - Lévy stable motion

KW - Long range dependence

KW - Multifractals

KW - Network traffic modeling

UR - http://www.scopus.com/inward/record.url?scp=17944397650&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=17944397650&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:17944397650

VL - 4

BT - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

T2 - 2002 IEEE International Conference on Acoustic, Speech, and Signal Processing

Y2 - 13 May 2002 through 17 May 2002

ER -

Additive and multiplicative mixture trees for network traffic modeling

Abstract

Other

Keywords

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this