Heterogeneous bursty traffic dispersion over multiple server clusters

Author

Elhanany, Itamar ; Kahane, Michael

Author_Institution

Dept. of Electr. & Comput. Eng., Tennessee Univ., Knoxville, TN, USA

Volume

9

Issue

3

fYear

2005

fDate

3/1/2005 12:00:00 AM

Firstpage

261

Lastpage

263

Abstract

This letter presents performance analysis of multiple subnets, each representing a cluster of computing server nodes, that are introduced with non-uniformly distributed bursty packet arrivals. In particular, we study the case of a multi-state Markov-modulated arrival process, heterogeneously dispersed among designated queues. Cluster processing is modeled by employing a batch service discipline. The probability generating functions of the interarrival times distributions are utilized to derive closed-form expressions for each of the queue size distributions.

Keywords

Markov processes; computer network management; network servers; packet switching; queueing theory; telecommunication congestion control; telecommunication traffic; workstation clusters; batch service discipline; closed-form expressions; cluster processing model; computing server nodes; designated queues; heterogeneous bursty traffic dispersion; heterogeneously dispersed arrival; interarrival times distributions; multi-state Markov-modulated arrival process; multiple server clusters; multiple subnets; nonuniformly distributed bursty packet arrivals; performance analysis; probability generating functions; queue size distributions; traffic modeling; Closed-form solution; Computer networks; Distributed computing; Network servers; Network topology; Performance analysis; Power engineering and energy; Telecommunication traffic; Traffic control; Wide area networks;

fLanguage

English

Journal_Title

Communications Letters, IEEE

Publisher

ieee

ISSN

1089-7798

Type

jour

DOI

10.1109/LCOMM.2005.03026

Filename

1411026