Assessing the reliability of communication networks through machine learning techniques

The reliability of communication networks is assessed by employing two machine learning algorithms, Support Vector Machines (SVM) and Hamming Clustering (HC), acting on a subset of possible system con- ¯gurations, generated by a Monte Carlo simulation and an appropriate Evaluation Function. The experiments performed with two di®erent re- liability measures show that both methods yield excellent predictions, though the performances of models generated by HC are signi¯cantly better than those of SVM.