Intelligent probing: A cost-effective approach to fault diagnosis in computer networks

We consider the use of probing technology for cost-effective fault diagnosis in computer networks. Probes are test transactions that can be actively selected and sent through the network. This work addresses the probing problem using methods from artificial intelligence. We call the resulting approach intelligent probing. The probes are selected by reasoning about the interactions between the probe paths. Although finding the optimal probe set is prohibitively expensive for large networks, we implement algorithms that find near-optimal probe sets in linear time. In the diagnosis phase, we use a Bayesian network approach and use a local-inference approximation scheme that avoids the intractability of exact inference for large networks. Our results show that the quality of this approximate inference "degrades gracefully" under increasing uncertainty and increases as the quality of the probe set increases.