A computational study on the design of overall reliability measures of optimized ANN for computer networks with fixed and varying link reliabilities

Abstract

This paper presents a computational study on the performance of reliability measures by using optimized ANN for computer networks with fixed and varying link reliabilities. This objective of this paper is to focus on the design of minimum cost reliable computer networks when a set of nodes, their topology, and links are given to connect them. A comparative study of various approaches for evaluating reliabilities has been studied such as Monte Carlo simulation methods and upper and lower bounds to bound reliability. The network design problem is difficult when overall reliability measure is considered through these methods. For optimal network design, an optimized ANN is used. ANN is constructed, trained and validated using topologies, with fixed and varying links, and upper-bound on reliability as inputs to produce overall reliability as output. The optimal design of ANN shows that the reliability of growing networks can be measured efficiently.