Use of Bayesian Networks in estimating the reliability of distributed communication systems

Bayesian Network (BN) is a probabilistic methodology used to model and predict the behaviour of a particular system based on its observed stochastic events called information variables. In this paper we show how to use a BN as a multivariate statistical technique to evaluate the reliability of a "k-out-of-n:F" system and to study of its sensitivity with respect to component failure. An example of a communication system is chosen where antennas are arranged in a grid matrix. A BN is used to evaluate the probability of critical failure developing that causes a complete system shutdown. This type of problem is difficult to solve by traditional reliability methods. The solution to this problem allows one to determine the optimum inspection and maintenance period of communication systems in remote geographical locations.