A multinomial formulation for efficient simulation of periodic on/off sources

Author

Freebersyser, James A. ; Townsend, J. Keith

Author_Institution

Center for Adv. Comput. & Commun., North Carolina State Univ., Raleigh, NC, USA

fYear

1996

Firstpage

75

Lastpage

81

Abstract

We develop a system model for estimating the cell loss probability utilizing a traffic source derived from the connection traffic descriptors rather than a stochastic model. We use a multinomial formulation for the Monte Carlo simulation to remove the correlation associated with estimating bursty events. We use importance sampling to increase the efficiency of the simulation. For the experimental examples considered here, the improvement in simulation efficiency compared to conventional Monte Carlo simulation is inversely proportional to the estimate

Keywords

Monte Carlo methods; asynchronous transfer mode; probability; simulation; telecommunication networks; telecommunication traffic; Monte Carlo simulation; bursty event estimation; cell loss probability estimation; connection traffic descriptors; efficient simulation; importance sampling; multinomial formulation; periodic on/off sources; simulation efficiency; system model; traffic source; Analysis of variance; Asynchronous transfer mode; Buffer overflow; Computational modeling; Discrete event simulation; Information analysis; Monte Carlo methods; Stochastic systems; Telecommunication traffic; Traffic control;

fLanguage

English

Publisher

ieee

Conference_Titel

Modeling, Analysis, and Simulation of Computer and Telecommunication Systems, 1996. MASCOTS '96., Proceedings of the Fourth International Workshop on

Conference_Location

San Jose, CA

Print_ISBN

0-8186-7235-8

Type

conf

DOI

10.1109/MASCOT.1996.500997

Filename

500997