论文信息 - A conditional Monte Carlo with intermediate estimations for c omputing MTTF of Markovian systems

A conditional Monte Carlo with intermediate estimations for c omputing MTTF of Markovian systems

Conditional Monte Carlo with intermediate estimations is a proposal for applying Conditional Monte Carlo to the estimation of the failure probability of a multicomponent system modeled by a Markov chain. Through this probability it is possible to compute the MTTF. This article introduces the basis of this method, proves that it is unbiased, that its variance is less than the standard simulation and mentions some lines of ongoing work for extending the idea and applying it to systems with large number of states.

Gerardo Rubino | Héctor Cancela | Leslie Murray

[1] Gerardo Rubino,et al. MTTF Estimation using importance sampling on Markov models , 2002, Monte Carlo Methods Appl..

[2] Gerardo Rubino,et al. Rare Event Simulation using Monte Carlo Methods , 2009 .

[3] Sandeep Juneja,et al. Fast Simulation of Markov Chains with Small Transition Probabilities , 2001, Manag. Sci..

[4] Sheldon M. Ross,et al. Simulation, Fourth Edition , 2006 .