Statistical optimization of dynamic importance sampling parameters for efficient simulation of communication networks

Importance sampling (IS) is a powerful method for reducing simulation run times when estimating the probabilities of rare events in communication systems using Monte Carlo simulation and is made feasible and effective for the simulation of networks of queues by regenerative techniques. However, using the most favorable IS settings very often makes the length of regeneration cycles infinite or impractically long. To address this problem, a methodology that uses IS dynamically within each regeneration cycle to drive the system back to the regeneration state after an accurate estimate has been obtained is discussed. A statistically based technique for optimizing IS parameter values for simulations of queueing systems, including complex systems with bursty arrival processes, is formulated. A deterministic variant of stochastic simulated annealing (SA), called mean field annealing (MFA), is used to minimize statistical estimates of the IS estimator variance. The technique is demonstrated by evaluating blocking probabilities. >

[1]  H. Kahn,et al.  Methods of Reducing Sample Size in Monte Carlo Computations , 1953, Oper. Res..

[2]  A. A. Crane,et al.  An introduction to the regenerative method for simulation analysis , 1977 .

[3]  P. Balaban,et al.  A Modified Monte-Carlo Simulation Technique for the Evaluation of Error Rate in Digital Communication Systems , 1980, IEEE Trans. Commun..

[4]  R. Wolff,et al.  The Almost Regenerative Method for Stochastic System Simulations , 1980, Oper. Res..

[5]  Reuven Y. Rubinstein,et al.  Simulation and the Monte Carlo method , 1981, Wiley series in probability and mathematical statistics.

[6]  Scott Kirkpatrick,et al.  Optimization by Simmulated Annealing , 1983, Sci..

[7]  Jeffrey J. Hunter,et al.  Mathematical techniques of applied probability , 1985 .

[8]  C. D. Gelatt,et al.  Optimization by Simulated Annealing , 1983, Science.

[9]  Jeffrey J. Hunter Discrete Time Models : Techniques and Applications , 1983 .

[10]  Michel C. Jeruchim,et al.  Techniques for Estimating the Bit Error Rate in the Simulation of Digital Communication Systems , 1984, IEEE J. Sel. Areas Commun..

[11]  M. Metivier,et al.  Applications of a Kushner and Clark lemma to general classes of stochastic algorithms , 1984, IEEE Trans. Inf. Theory.

[12]  S. Asmussen Conjugate processes and the silumation of ruin problems , 1985 .

[13]  Peter W. Glynn,et al.  Proceedings of Ihe 1986 Winter Simulation , 2022 .

[14]  Philip Heidelberger,et al.  Measure specific dynamic importance sampling for availability simulations , 1987, WSC '87.

[15]  Wesley E. Snyder,et al.  Optimization by Mean Field Annealing , 1988, NIPS.

[16]  Kung Yao,et al.  Improved importance sampling technique for efficient simulation of digital communication systems , 1988, IEEE J. Sel. Areas Commun..

[17]  J. Bucklew,et al.  On large deviations theory and asymptotically efficient Monte Carlo estimation , 1989, Proceedings of the 32nd Midwest Symposium on Circuits and Systems,.

[18]  S. Asmussen Risk theory in a Markovian environment , 1989 .

[19]  Donald L. Iglehart,et al.  Importance sampling for stochastic simulations , 1989 .

[20]  Jean Walrand,et al.  A quick simulation method for excessive backlogs in networks of queues , 1989 .

[21]  Michel C. Jeruchim,et al.  On optimum and suboptimum biasing procedures for importance sampling in communication simulation , 1990, IEEE Trans. Commun..

[22]  J. Keith Townsend,et al.  Optimization of Transmitter and Receiver Filters for Digital Communication Systems Using Mean Field Annealing , 1990, IEEE J. Sel. Areas Commun..

[23]  H.-J. Schlebusch Nonlinear importance sampling techniques for efficient simulation of communication systems , 1990, IEEE International Conference on Communications, Including Supercomm Technical Sessions.

[24]  Michael Devetsikiotis,et al.  A useful and general technique for improving the efficiency of Monte Carlo simulation of digital communication systems , 1990, [Proceedings] GLOBECOM '90: IEEE Global Telecommunications Conference and Exhibition.

[25]  Harry G. Perros,et al.  An approximate analysis of a bufferless NxN synchronous Clos ATM switch , 1990 .

[26]  Victor S. Frost,et al.  Efficient estimation of cell blocking probability for ATM systems , 1991, ICC 91 International Conference on Communications Conference Record.

[27]  Michael R. Frater,et al.  Optimally efficient estimation of the statistics of rare events in queueing networks , 1991 .

[28]  Michael Devetsikiotis,et al.  A dynamic importance sampling methodology for the efficient estimation of rare event probabilities in regenerative simulations of queueing systems , 1992, [Conference Record] SUPERCOMM/ICC '92 Discovering a New World of Communications.

[29]  Michael Devetsikiotis,et al.  Optimization of importance sampling parameters for the efficient simulation of communication networks and ATM switches using mean field annealing , 1992, ACM-SE 30.

[30]  Harry G. Perros,et al.  A Queueing Model of a Bufferless Synchronous Clos ATM Switch with Head-of-Line Priority and Push-Out , 1992, J. High Speed Networks.

[31]  Philip Heidelberger,et al.  A Unified Framework for Simulating Markovian Models of Highly Dependable Systems , 1992, IEEE Trans. Computers.

[32]  Michael Devetsikiotis,et al.  An algorithmic approach to the optimization of importance sampling parameters in digital communication system simulation , 1993, IEEE Trans. Commun..

[33]  Victor S. Frost,et al.  Efficient estimation of cell blocking probability for ATM systems , 1993, TNET.