Presentation 2004/2/27
A Parameter Estimation of MMPP Based on Covariance Structure for Internet Traffic : Performance Prediction for a Single-Server Queueing System
akayuki ARAI, Shoji KASAHARA, Kenji SUGIMOTO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) It is well known that the Internet traffic exhibits a long-range correlation and that it is difficult to model the Internet traffic with a Markovian arrival process such as a Poisson one. In this paper, we propose a parameter estimation of two-state Markov-modulated Poisson process (MMPP), in which the parameters of the two-state MMPP are determined so as to match the covariance of the number of arriving packets in some interval. In numerical examples, we compare estimated MMPPs with original ones in terms of the covariance of the number of arriving pachets arid the mean delay of a single-server queueing system with MMPP input. It is shown that our estimation is useful when the correlation of an original MMPP is moderate.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) MMPP / correlation / covariance / traffic modeling
Paper # NS2003-352,IN2003-307
Date of Issue

Conference Information
Committee NS
Conference Date 2004/2/27(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Network Systems(NS)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A Parameter Estimation of MMPP Based on Covariance Structure for Internet Traffic : Performance Prediction for a Single-Server Queueing System
Sub Title (in English)
Keyword(1) MMPP
Keyword(2) correlation
Keyword(3) covariance
Keyword(4) traffic modeling
1st Author's Name akayuki ARAI
1st Author's Affiliation Granduate School of Information Science Nara Institue of Science and Technology()
2nd Author's Name Shoji KASAHARA
2nd Author's Affiliation Granduate School of Information Science Nara Institue of Science and Technology
3rd Author's Name Kenji SUGIMOTO
3rd Author's Affiliation Granduate School of Information Science Nara Institue of Science and Technology
Date 2004/2/27
Paper # NS2003-352,IN2003-307
Volume (vol) vol.103
Number (no) 690
Page pp.pp.-
#Pages 4
Date of Issue