A fast Monte Carlo method for evaluating reliability indexes

This paper presents a fast Monte Carlo method, based on importance sampling (IS) distribution, for estimation of reliability indexes in hydroelectric systems. More precisely, it considers the case where the IS distribution comes from the same parametric family as the original (true) one and proposes a simulation-based optimization algorithm for selecting the parameters of the IS in an optimal way. The superiority of this method, relative to the usual Monte Carlo one, is shown for the well-known test problem: IEEE Reliability Test System.