Abstract
In this article, a novel approach is presented for the determination of reliability importance measures in electric transmission systems implementing the Bayesian network. By this method, the Bayesian network associated with a given power system is first constructed where the generation units are assumed fully reliable and the required training data is provided by using the state sampling method of Monte Carlo simulation. When the Bayesian network is constructed, it is readily used to determine the various reliability importance measures and to investigate their physical interpretations for the proposed transmission system.