DocumentCode :
3465610
Title :
A queueing model for pipelined circuit-switched networks with the MMPP traffic
Author :
Min, Geyong ; Ould-Khaoua, Mohamed
Author_Institution :
Dept. of Comput. Sci., Glasgow Univ., UK
fYear :
2001
fDate :
2001
Firstpage :
259
Lastpage :
266
Abstract :
The Markov-modulated Poisson process (MMPP) has been extensively used for modelling bursty traffic generated by multimedia applications because it is able to model the time-varying arrival rate and capture the important correlation between inter-arrival times. However, interconnection networks used in current multicomputers have been mainly analysed under the assumption of the "non-bursty" Poisson arrival process. This study extends further the application of the MMPP to queueing networks in order to develop a new analytical model for computing message latency in pipelined circuit-switched interconnection networks. Simulation experiments reveal that the model exhibits a good degree of accuracy under various operating conditions
Keywords :
Markov processes; circuit switching; multiprocessor interconnection networks; pipeline processing; queueing theory; stochastic processes; telecommunication traffic; MMPP traffic; Markov-modulated Poisson process; bursty traffic; inter-arrival times; interconnection networks; message latency; multicomputer networks; multimedia applications; pipelined circuit-switched networks; queueing model; queueing networks; simulation experiments; time-varying arrival rate; Analytical models; Circuit analysis computing; Circuit simulation; Computational modeling; Computer networks; Delay; Multiprocessor interconnection networks; Queueing analysis; Telecommunication traffic; Traffic control;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Modeling, Analysis and Simulation of Computer and Telecommunication Systems, 2001. Proceedings. Ninth International Symposium on
Conference_Location :
Cincinnati, OH
ISSN :
1526-7639
Print_ISBN :
0-7695-1315-8
Type :
conf
DOI :
10.1109/MASCOT.2001.948876
Filename :
948876
Link To Document :
بازگشت