Bayesian network loss inference

In large-scale dynamic communication networks, endsystems can not rely on the network itself to cooperate in characterizing its own behavior. This has prompted research activities on methods for inferring internal network behavior based on the external end-to-end network measurements. In particular, knowledge of the link losses inside the network is important for network management. However it is impractical to directly measure packet losses or delays at every router. On the other hand, measuring end-to-end (from sources to receivers) losses is relatively easy. We formulate the problems of link in a network as Bayesian inference problems and develop several Markov chain Monte Carlo (MCMC) algorithms to solve them. We then apply the proposed link loss algorithms to data generated by the Network Simulator (NS2) software, and obtain good agreements between the theoretical results and the actual measurements.