Towards automatic network fault localization in real time using probabilistic inference

This paper describes the foundation of a novel network fault localization algorithm based on active network measurements and probabilistic inference. A fault condition could be an unacceptable large delay or packet loss rate. The solution is computationally efficient, autonomic in nature and provides the operator with a probability mass distribution that indicates the fault location. The probabilistic inference is based on a discrete state-space particle filter. We present results from a first feasibility study performed in a simulated environment. The precise location of single faults is determined rapidly when measurement paths are partly overlapping.