A new approach for parallel steady-state simulations
Abstract
We propose a new procedure for building confidence interval estimators of steady-state parameters in discrete event simulations. The procedure uses parallel processors to generate independent replications and constructs the confidence interval estimator by solving a generalized least square problem. The most appealing theoretical feature of the proposed procedure is that the precision of the resulted estimator can be improved by simply increasing the number of processors (or independent replications) while the simulated time length is fixed on an appropriate level on each processor. Experiments conducted on M/M/1 queue waiting time processes in heavy traffic confirm this theoretical property.
References
[1]
Cash, C. R., B. L. Nelson, D. G. Dippold, J. M. Long, and W. P. Pollard. 1992. Evaluation of tests for initial-condition bias. In Proceedings of the 24th Winter Simulation Conference (WSC'92), 577--585.
[2]
Glynn, P. W. 1984. Some asymptotic formulas for markov chain with applications to simulation. Journal of Statistical Computation and Simulation 19:97--112.
[3]
Glynn, P. W. 1995. Some new results on the initial transient problem. In Proceedings of the 27th Winter Simulation Conference (WSC'95), 165--170.
[4]
Glynn, P. W., and P. Heidelberger. 1991a. Analysis of initial transient deletion for replicated steady-state simulations. Operations Research Letters 10:437--443.
[5]
Glynn, P. W., and P. Heidelberger. 1991b. Analysis of parallel, replicated simulations under a completion time constraint. ACM Transations on Modeling and Computer Simulation 1:3--23.
[6]
Glynn, P. W., and P. Heidelberger. 1992a. Analysis of initial transient deletion for parallel steady-state simulations. SIAM Journal on Scientific and Statistical Computing 13:909--922.
[7]
Glynn, P. W., and P. Heidelberger. 1992b. Experiments with initial transient deletion for parallel, replicated steady-state simulations. Management Science 38:400--418.
[8]
Goldsman, D., L. W. Schruben, and J. Swain. 1994. Tests for transient means in simulated time series. Naval Research Logistics Quarterly 41:171--187.
[9]
Heidelberger, P. 1988. Discrete event simulations and parallel processing: statistical properties. SIAM Journal on Scientific and Statistical Computing 9:1114--1132.
[10]
Hsieh, M.-H., D. L. Iglehart, and P. W. Glynn. 2004. Empirical performance of bias-reducing estimators for regenerative steady-state simulations. ACM Transations on Modeling and Computer Simulation 14:325--343.
[11]
Schruben, L. W. 1982. Detecting initialization bias in simulation output. Opertions Research 30 (3): 151--153.
[12]
Schruben, L. W., H. Singh, and L. Tierney. 1983. Optimal tests for initialization bais in simulation output. Opertions Research 31 (6): 1167--1178.
[13]
Steiger, N. M., E. K. Lada, J. R. Wilson, J. A. Joines, C. Alexopoulos, and D. Goldsman. 2005. ASAP3: a batch means procedure for steady-state simulation analysis. ACM Transations on Modeling and Computer Simulation 15 (1): 39--73.
[14]
White, K. P. 1997. An effective truncation heuristic for bias reduction in simulation output. Simulation 69 (6): 323--334.
[15]
White, K. P., M. J. Cobb, and S. C. Spratt. 2000. A comparison of five steady-state truncation heuristics for simulation. In Proceedings of the 32nd Winter Simulation Conference (WSC'00), 755--760.
Recommendations
How Hard are Steady-State Queueing Simulations?
Special Issue on Don IglehartSome queueing systems require tremendously long simulation runlengths to obtain accurate estimators of certain steady-state performance measures when the servers are heavily utilized. However, this is not uniformly the case. We analyze a number of ...
Experiments with Initial Transient Deletion for Parallel, Replicated Steady-State Simulations
A simple and effective way to exploit parallel processors in discrete event simulations is to run multiple independent replications, in parallel, on multiple processors and to average the results at the end of the runs. We call this the method of ...
Steady-state analysis of a discrete-time batch arrival queue with working vacations
This paper analyzes a discrete-time batch arrival queue with working vacations. In a Geo^X/G/1 system, the server works at a lower speed during the vacation period which becomes a lower speed operation period. This model is more appropriate for the ...
Comments
Information & Contributors
Information
Published In
December 2006
2429 pages
ISBN:1424405017
- Editors:
- L. Felipe Perrone,
- Barry G. Lawson,
- Jason Liu,
- Frederick P. Wieland,
- General Chair:
- David Nicol,
- Program Chair:
- Richard Fujimoto
Sponsors
- IIE: Institute of Industrial Engineers
- ASA: American Statistical Association
- IEICE ESS: Institute of Electronics, Information and Communication Engineers, Engineering Sciences Society
- IEEE-CS\DATC: The IEEE Computer Society
- SIGSIM: ACM Special Interest Group on Simulation and Modeling
- NIST: National Institute of Standards and Technology
- (SCS): The Society for Modeling and Simulation International
- INFORMS-CS: Institute for Operations Research and the Management Sciences-College on Simulation
Publisher
Winter Simulation Conference
Publication History
Published: 03 December 2006
Check for updates
Qualifiers
- Article
Conference
WSC06
Sponsor:
- IIE
- ASA
- IEICE ESS
- IEEE-CS\DATC
- SIGSIM
- NIST
- (SCS)
- INFORMS-CS
Acceptance Rates
WSC '06 Paper Acceptance Rate 177 of 252 submissions, 70%;
Overall Acceptance Rate 3,413 of 5,075 submissions, 67%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 80Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 07 Mar 2025
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in