Abstract
This paper defines a hybrid simulation model to be a computer system model which uses discrete-event simulation to model allocation and use of long-term resources (e.g., main memory) and mathematical modeling to approximate the use of short-term resources (e.g., the CPU and I/O processors.) This combination yields system models whose accuracy can approach that of an equivalent simulation-only model at a significant reduction in operating costs.
This paper describes the hybrid technique and illustrates its use to study the effects of variations in the amount of main memory on system performance. The mathematical portion is based on a central server model extended to accomodate jobs of two classes. The accuracy and operating costs of the hybrid version of this model are seen to compare favorably with the equivalent simulation-only version.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Avi-Itzak, B. and D. P. Heyman, “Approximate Queueing Models for Multiprogramming Computer Systems”, Operations Research, (21,6), November-December, 1973, pp. 1212–1230.
Balbo, G., Bruell, S. C. and H. D. Schwetman, “Computational Aspects of Closed Queueing Networks with Different Customer Classes”, Computer Sciences Department, Purdue University, CSD-TR-210, November, 1976.
Baskett, F., Chandy, K. M., Müntz, R. R., and F. Palacios, “Open, Closed, and Mixed Networks of Queues with Different Customer Classes”, Journal ACM (22,2), April, 1975, pp. 248–260.
Buzen, J., “Computational Algorithms for Closed Queueing Networks with Exponential Servers”, Communications ACM (16,9), September, 1973, pp. 527–531.
Buzen, J., “Cost-Effective Analytic Tools for Computer Performance Evaluation”, Proceedings IEEE Compcon, September, 1975.
Chandy, K. M., Herzog, U. and L. Woo, “Parametric Analysis of Queueing Networks”, IBM Journal of Research and Development, January, 1975, pp. 36–42.
Courtois, P., “Decomposability, Instabilities and Saturation in Multiprogramming Systems”, Communications ACM (18,7), July, 1975, pp. 371–377.
MacDougall, M. H. and J. S. McAlpine, “Computer System Simulation with ASPOL”, Proceedings Symposium on the Simulation of Computer Systems, ACM/SIGSIM, June, 1973, pp. 93–104.
Reiser, M. and H. Kobayashi, “Queueing Networks with Multiple Closed Chains: Theory and Computational Algorithms”, IBM Journal of Research and Development, May, 1975, pp. 283–294.
Schwetman, H., “Hybrid Simulation Models of Computer Systems,” submitted for publication. May, 1976.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1977 Springer-Verlag Berlin · Heidelberg
About this chapter
Cite this chapter
Schwetman, H.D. (1977). Hybrid Simulation Models: A Speed-Up Technique Combining Analytic and Discrete-Event Modeling. In: Spies, P.P. (eds) Modelle für Rechensysteme. Informatik — Fachberichte, vol 9. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-45499-8_16
Download citation
DOI: https://doi.org/10.1007/978-3-642-45499-8_16
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-08206-4
Online ISBN: 978-3-642-45499-8
eBook Packages: Springer Book Archive