Time-dependent queueing network approximations as simulation external control variates

Authors:
Bruce W. Schmeiser;Michael R. Taaffe
Affiliations:
School of Industrial Engineering, Purdue University, West Lafayette, IN 47907-1287, USA;Department of Operations and Management Science, University of Minnesota, Minneapolis, MN 55455, USA
Venue:
Operations Research Letters
Year:
1994

Citing 10
Cited 2

Decomposition of some well-known variance reduction techniques

Journal of Statistical Computation and Simulation
On control variate estimators

Computers and Operations Research
Approximating nonstationary Ph(t)/Ph(t)/1/c queueing systems

Mathematics and Computers in Simulation
Control variate remedies

Operations Research
An investigation of phase-distribution moment-matching algorithms for use in queueing models

Queueing Systems: Theory and Applications
Methods for selecting the best system

WSC '91 Proceedings of the 23rd conference on Winter simulation
Use of Polya distributions in approximate solutions to nonstationary M/M/s queues

Communications of the ACM - Special issue on simulation modeling and statistical computing
External control variance reduction for nonstationary simulation

WSC '83 Proceedings of the 15th conference on Winter simulation - Volume 1
Approximating time-dependent non-exponential queues

WSC '84 Proceedings of the 16th conference on Winter simulation
Approximating nonstationary queueing systems

WSC '82 Proceedings of the 14th conference on Winter Simulation - Volume 1

Approximation-assisted point estimation

Operations Research Letters
Decomposition approximations for time-dependent Markovian queueing networks

Operations Research Letters

Quantified Score

Hi-index	0.00

Visualization

Abstract

A strategy for efficient evaluation of a complex stochastic model's performance is to use a simpler model's known performance as an approximation. Another strategy is to simulate using the simpler model's known performance as an external control variate. We combine these two strategies. We also relax the assumption that the simpler model's performance is known exactly by introducing mean-squared-error optimal control variates.