Abstract
This paper is a tutorial on RESTART, a widely applicable accelerated simulation technique for estimating rare event probabilities. The method is based on performing a number of simulation retrials when the process enters regions of the state space where the chance of occurrence of the rare event is higher. The paper analyzes its efficiency, showing formulas for the variance of the estimator and for the gain obtained with respect to crude simulation, as well as for the parameter values that maximize this gain. It also provides guidelines for achieving a high efficiency when it is applied. Emphasis is placed on the choice of the importance function, i.e., the function of the system state used for determining when retrials are made. Several examples on queuing networks and ultra reliable systems are exposed to illustrate the application of the guidelines and the efficiency achieved.
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
Rubino, G., Tuffin, B. (eds.): Rare event simulation using Monte Carlo methods. Wiley, Chichester (2009)
Kahn, H., Harris, T.E.: Estimation of Particle Transmission by Random Sampling. National Bureau of Standards Applied Mathematics Series, vol. 12, pp. 27–30 (1951)
Villén-Altamirano, M., Villén-Altamirano, J.: On the Efficiency of RESTART for Multidimensional Systems. ACM T. on Model. and Comput. Simul. 16(3), 251–279 (2006)
Bayes, A.J.: Statistical Techniques for Simulation Models. Australian Computer J. 2, 180–184 (1970)
Villén-Altamirano, M., Villén-Altamirano, J.: RESTART: A Method for Accelerating Rare Event Simulations. In: Cohen, J.W, Pack, C.D. (eds.) 13th International Teletraffic Congress. North Holland Studies in Telecommunication, vol. 15, pp. 71–76 (1991)
Villén-Altamirano, M., Martínez-Marrón, A., Gamo, J.L., Fernández-Cuesta, F.: Enhancement of the Accelerated Simulation Method RESTART by Considering Multiple Thresholds. In: Labetoulle, J., Roberts, J.W. (eds.) 14th International Teletraffic Congress. Teletraffic Science and Engineering, vol. 1a, pp. 797–810. Elsevier, Amsterdam (1994)
Hopmans, A.C.M., Kleijnen, J.P.C.: Importance Sampling in System Simulation: A Practical Failure? In: Mathematics and Computing in Simulation XXI, pp. 209–220 (1979)
Villén-Altamirano, M., Villén-Altamirano, J.: A Straightforward Method for Fast Simulation of Rare Event. In: 1994 Winter Simulation Conference, pp. 282–289. IEEE Press, Los Alamitos (1994)
Görg, C., Schreiber, F.: The RESTART/LRE method for Rare Event Simulation. In: 1996 Winter Simulation Conference, pp. 390–397. IEEE Press, Los Alamitos (1996)
Kelling, C.: A Framework for Rare Event Simulation of Stochastic Petri Net using RESTART. In: 1996 Winter Simulation Conference, pp. 317–324. IEEE Press, Los Alamitos (1996)
Kuhlmann, T., Kelling, C.: Case Studies on Multi-dimensional RESTART Simulations. Int. J. Electron. Commun. 52(3), 190–196 (1998)
Naldi, M., Calonico, F.: A Comparison of the GEVT and RESTART Techniques for the Simulation of Rare Events in ATM Networks. Int. J. of the Federation of Eur. Simul. Societies. 6, 181–186 (1998)
Villén-Altamirano, J.: RESTART Method for the Case where Rare Events Can Occur in Retrials from any Threshold. Int. J. Electron. Commun. 52(3), 183–190 (1998)
Garvels, M.J.J., Kroese, D.P.: A Comparison of RESTART Implementations. In: 1998 Winter Simulation Conference, pp. 601–609. IEEE Press, Los Alamitos (1998)
Görg, C., Fuß, O.: Comparison and Optimization of RESTART Run Time Strategies. Int. J. Electron. Commun. 52(3), 197–204 (1998)
Haraszti, Z., Townsend, J.K.: The Theory of Direct Probability Redistribution and its Application to Rare Event Simulation. ACM T. on Model. and Comput. Simul. 9(2), 105–140 (1999)
Garvels, M.J.J., Kroese, D.P.: On the Entrance Distribution in RESTART Simulation. In: RESIM 1999 Workshop, pp. 65–88. University of Twente, Enschede (1999)
Görg, C., Fuß, O.: Simulating Rare Event Details of ATM Delay-Time Distribution with RESTART-LRE. In: Key, P., Smith, D. (eds.) 16th International Teletraffic Engineering. Teletraffic Science and Engineering, vol. 3b, pp. 777–786. Elsevier, Amsterdam (1999)
Akyamac, A.A., Haraszti, Z., Townsend, J.K.: Efficient Rare Event Simulation using DPR for Multi-dimensional Parameter Spaces. In: 16th International Teletraffic Engineering. Teletraffic Science and Engineering, vol. 3b, pp. 767–776. Elsevier, Amsterdam (1999)
Tuffin, B., Trivedi, K.S.: Implementation of Importance Splitting Techniques in Stochastic Petri Net Package. In: Haverkort, B.R., Bohnenkamp, H.C., Smith, C.U. (eds.) TOOLS 2000. LNCS, vol. 1786, pp. 216–229. Springer, Heidelberg (2000)
Akin, O., Townsed, J.K.: Efficient Simulation of Delay in TCP/IP Networks using DPR-based Splitting. In: IEEE International Conference on Communication 2002, pp. 2619–2624 (2002)
Garvels, M.J.J., Kroese, D.P., Ommeren, J.K.C.W.: On the Importance Function in Splitting Simulation. Eur. T. on Telecom. 13(4), 363–371 (2002)
Radev, D., Iliev, M., Arabadjieva, I.: RESTART Simulation in ATM networks with tandem queue. In: International Conference on Automatics and Informatics, Sofia, pp. 37–40 (2004)
Elayoubi, S.E., Fourestie, B.: On Trajectory Splitting for Accelerating Dynamic Simulations in Mobile Wireless Networks. In: 19th International Teletraffic Congress, Beijing (2005)
Villén-Altamirano, J.: Rare Event RESTART Simulation of Two-Stage Networks. Eur. J. of Oper. Res. 179(1), 148–159 (2007)
Cerou, F., Guyader, A.: Adaptive Multilevel Splitting for Rare Event Analysis. Stoch. Analysis and Applic. 25(2), 417–443 (2007)
Villén-Altamirano, J.: Importance Functions for RESTART Simulation of Highly-Dependable Systems. Simulation 83, 821–828 (2007)
Zimmermann, A.: Stochastic discrete event system. Springer, Berlín (2008)
Lagnoux, A.: Effective Branching Method Splitting under Cost Constraint. Stoch. Processes and their Application 18(10), 1820–1851 (2008)
Mykkeltveit, A., Helvik, B.E.: Application of the RESTART/Splitting Technique to Network Resilience Studies NS2. In: 19th IASTED International Conference (2008)
Dean, T., Dupuis, P.: The design and analysis of a generalized DPR/RESTART algorithm for rare event simulation. Annals of Oper. Res. (2010) (in Press)
Villén-Altamirano, J.: Importance Functions for RESTART Simulation of General Jackson Networks. Eur. J. of Oper. Res. 203(1), 156–165 (2010)
Villén-Altamirano, J.: Dependability Estimation for Non-Markov Consecutive-K-out-of-N: F Repairable Systems by RESTART Simulation. Reliab. Eng. Syst. Saf. 95(3), 247–254 (2010)
Villén-Altamirano, M., Villén-Altamirano, J., Vázquez-Gallo, E.: RESTART Simulation of non-Markovian Queuing Networks. In: RESIM 2010, Isaac Newton Institute, Cambridge (2010)
Villén-Altamirano, M., Villén-Altamirano, J.: Analysis of RESTART Simulation: Theoretical Basis and Sensitivity Study. Eur. T. on Telecom. 13(4), 373–385 (2002)
Villén-Altamirano, J., Villén-Altamirano, M.: Recent Advances in RESTART Simulation. In: RESIM 2008. IRISA - INRIA, Rennes (2008)
Villén-Altamirano, M., Villén-Altamirano, J.: Accelerated Simulation of Rare Event using RESTART Method with Hysteresis. In: ITC Specialists’ Seminar on Telecommunication Services for Developing Economies, pp. 240–251. University of Mining and Metallurgy, Krakow (1991)
Villén-Altamirano, M., Villén-Altamirano, J., González-Rodríguez, J., Río-Martínez, L.: del: Use of Re-Scheduling in Rare Event RESTART Simulation. In: 5th St. Petersburg Workshop on Simulation, pp. 721–728 (2005)
Parekh, S., Walrand, A.: A Quick Simulation Method for Excessive Backlogs in Networks of Queues. IEEE T. on Aut. Control 34, 54–66 (1989)
Glasserman, P., Heidelberger, P., Shahabuddin, P., Zajic, T.: A Large Deviation Perspective on the Efficiency of Multilevel Splitting. IEEE T. on Aut. Control 43(12), 1666–1679 (1998)
Glasserman, P., Heidelberger, P., Shahabuddin, P., Zajic, T.: Multilevel Splitting for Estimating Rare Event Probabilities. Oper. Res. 47, 585–600 (1999)
Kroese, D.P., Nicola, V.F.: Efficient Simulation of a Tandem Jackson Network. ACM T. on Model. and Comput. Simul. 12(2), 119–141 (2002)
L’ecuyer, P., Demers, V., Tuffin, B.: Rare Events, Splitting and Quasi-Monte Carlo. ACM T. on Model. and Comput. Simul. 17 (2), Article 9 (2007)
Villén-Altamirano, J.: RESTART Simulation of Networks of Queues with Erlang Service Times. In: 2009 Winter Simulation Conference, pp. 251–279. IEEE Press, Austin (2009)
Xiao, G., Li, Z., Li, T.: Dependability Estimation for non-Markov Consecutive-k-out- of-n: F Repairable Systems by Fast Simulation. Reliab. Eng. Syst. Saf. 92(3), 293–299 (2007)
Alexopoulos, C., Shultes, B.C.: Estimating Reliability Measures for Highly-Dependable Markov Systems using Balanced Likelihood Ratios. IEEE T. on Reliab. 50(3), 265–280 (2001)
Goyal, A., Shahabuddin, P., Heidelberger, P.: A Unified Framework for Simulating Markovian Models of Highly Dependable Systems. IEEE T. on Comput. 41(1), 36–51 (1992)
Nicola, V., Shahabuddin, P., Nakayama, M.K.: Techniques for Fast Simulation of Models of Highly Dependable Systems. IEEE T. on Reliab. 50(3), 246–264 (2001)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Villén-Altamirano, M., Villén-Altamirano, J. (2011). The Rare Event Simulation Method RESTART: Efficiency Analysis and Guidelines for Its Application. In: Kouvatsos, D.D. (eds) Network Performance Engineering. Lecture Notes in Computer Science, vol 5233. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-02742-0_22
Download citation
DOI: https://doi.org/10.1007/978-3-642-02742-0_22
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-02741-3
Online ISBN: 978-3-642-02742-0
eBook Packages: Computer ScienceComputer Science (R0)