A refined version of M/G/∞ processes for modelling VBR video traffic

Wai Chung Poon; Kwok Tung Lo

doi:10.1016/S0140-3664(00)00325-X

A refined version of M/G/∞ processes for modelling VBR video traffic

Wai Chung Poon, Kwok Tung Lo

The Hong Kong Polytechnic University

Research output: Journal article publication › Journal article › Academic research › peer-review

17 Citations (Scopus)

Abstract

This paper presents a refined version of the M/G/∞ busy-server process described in IEEE J. Select. Areas Commun., 16(5) (1998) 733-748 for VBR video modelling, with emphasis on a refined fitting approach of marginal distribution. First we suggest using normal mixture distribution instead of Gamma-Pareto distribution to model the marginal distribution for greater flexibility and accuracy. Second, we retune the parameter value of the Poisson input process to ensure smooth distribution transformation. Experimental results indicate that our model gives closer estimate to the empirical cell loss behaviour than the original model. Also, its performance is more consistent than other uni-distribution models like Gamma and lognormal, when fitting a wide variety of video sequences.

Original language	English
Pages (from-to)	1105-1114
Number of pages	10
Journal	Computer Communications
Volume	24
Issue number	11
DOIs	https://doi.org/10.1016/S0140-3664(00)00325-X
Publication status	Published - 15 Jun 2001

Keywords

EM algorithm
Normal mixture distribution
Traffic model
VBR video
Video model

ASJC Scopus subject areas

Computer Networks and Communications

More information

10.1016/S0140-3664(00)00325-X

Cite this

@article{5171efe9926342ec92a621aa11de1461,

title = "A refined version of M/G/∞ processes for modelling VBR video traffic",

abstract = "This paper presents a refined version of the M/G/∞ busy-server process described in IEEE J. Select. Areas Commun., 16(5) (1998) 733-748 for VBR video modelling, with emphasis on a refined fitting approach of marginal distribution. First we suggest using normal mixture distribution instead of Gamma-Pareto distribution to model the marginal distribution for greater flexibility and accuracy. Second, we retune the parameter value of the Poisson input process to ensure smooth distribution transformation. Experimental results indicate that our model gives closer estimate to the empirical cell loss behaviour than the original model. Also, its performance is more consistent than other uni-distribution models like Gamma and lognormal, when fitting a wide variety of video sequences.",

keywords = "EM algorithm, Normal mixture distribution, Traffic model, VBR video, Video model",

author = "Poon, {Wai Chung} and Lo, {Kwok Tung}",

year = "2001",

month = jun,

day = "15",

doi = "10.1016/S0140-3664(00)00325-X",

language = "English",

volume = "24",

pages = "1105--1114",

journal = "Computer Communications",

issn = "0140-3664",

publisher = "Elsevier B.V.",

number = "11",

}

TY - JOUR

T1 - A refined version of M/G/∞ processes for modelling VBR video traffic

AU - Poon, Wai Chung

AU - Lo, Kwok Tung

PY - 2001/6/15

Y1 - 2001/6/15

N2 - This paper presents a refined version of the M/G/∞ busy-server process described in IEEE J. Select. Areas Commun., 16(5) (1998) 733-748 for VBR video modelling, with emphasis on a refined fitting approach of marginal distribution. First we suggest using normal mixture distribution instead of Gamma-Pareto distribution to model the marginal distribution for greater flexibility and accuracy. Second, we retune the parameter value of the Poisson input process to ensure smooth distribution transformation. Experimental results indicate that our model gives closer estimate to the empirical cell loss behaviour than the original model. Also, its performance is more consistent than other uni-distribution models like Gamma and lognormal, when fitting a wide variety of video sequences.

AB - This paper presents a refined version of the M/G/∞ busy-server process described in IEEE J. Select. Areas Commun., 16(5) (1998) 733-748 for VBR video modelling, with emphasis on a refined fitting approach of marginal distribution. First we suggest using normal mixture distribution instead of Gamma-Pareto distribution to model the marginal distribution for greater flexibility and accuracy. Second, we retune the parameter value of the Poisson input process to ensure smooth distribution transformation. Experimental results indicate that our model gives closer estimate to the empirical cell loss behaviour than the original model. Also, its performance is more consistent than other uni-distribution models like Gamma and lognormal, when fitting a wide variety of video sequences.

KW - EM algorithm

KW - Normal mixture distribution

KW - Traffic model

KW - VBR video

KW - Video model

UR - http://www.scopus.com/inward/record.url?scp=0035875946&partnerID=8YFLogxK

U2 - 10.1016/S0140-3664(00)00325-X

DO - 10.1016/S0140-3664(00)00325-X

M3 - Journal article

SN - 0140-3664

VL - 24

SP - 1105

EP - 1114

JO - Computer Communications

JF - Computer Communications

IS - 11

ER -

A refined version of M/G/∞ processes for modelling VBR video traffic

Abstract

Keywords

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this