Passive localizing lossy links in sensor network using max-product algorithm

Faulty components in a wireless sensor network need to be localized and repaired to sustain the normal operation of the network. Due to the inherent stringent bandwidth and energy constraints, we consider only use end-to-end measurement to infer lossy links in sensor network. In this paper, we formulate the problem of lossy links localization as a Bayesian inference problem, and use max-product algorithm to solve it. Finally, we evaluate the performance of our approach through simulation and it shows good performance and stability.