Title :
Conservative parallel simulation of continuous time Markov chains using uniformization
Author :
Heidelberger, Philip ; Nicol, David M.
Author_Institution :
IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
fDate :
8/1/1993 12:00:00 AM
Abstract :
The authors describe parallel algorithms for simulating certain continuous time Markov chains, such as those arising in queueing network models of distributed computing systems or communications systems. The algorithms are based on the technique of uniformization. Two variations of a conservative parallel simulation algorithm are presented. In each algorithm, a relatively short presimulation is performed to identify those times, and only those times, at which the simulation algorithm requires processor pairs to synchronize. Speedup studies of the algorithms, performed on a 16-node Intel iPSC/2 hypercube, are presented and discussed
Keywords :
Markov processes; discrete event simulation; parallel algorithms; queueing theory; Intel iPSC/2 hypercube; communications systems; conservative parallel simulation algorithm; continuous time Markov chains; distributed computing systems; parallel algorithms; queueing network models; uniformization; Clustering algorithms; Computational modeling; Computer aided manufacturing; Discrete event simulation; Distributed computing; Hypercubes; Parallel algorithms; Predictive models; Time warp simulation; Virtual manufacturing;
Journal_Title :
Parallel and Distributed Systems, IEEE Transactions on