Bound-Based Network Tomography for Inferring Interesting Path Metrics

Abstract

In the &#x201C;network-as-a-service&#x201D; paradigm, network operators have a strong need to know the performance of critical paths running services to the users. Network tomography is an attractive methodology for inferring internal network characteristics from end-to-end measurements between monitors. Motivated by previous results that uniquely identifying the path metrics can require a large number of monitors, we focus on calculating the performance bounds of a set of interesting paths, i.e., bound-based network tomography for interesting paths. We present an efficient solution to obtain the tightest upper and lower bounds of all interesting paths in an arbitrary network with a given set of end-to-end measurements. Based on this solution, we further develop an algorithm to place new monitors over existing ones such that the bounds of interesting paths can be maximally tightened. We formally prove the effectiveness of the proposed algorithms. We implement the algorithms and conduct extensive experiments on real ISP topologies. Compared with state-of-the-art approaches, our algorithms achieve up to 1.2<inline-formula> <tex-math notation="LaTeX">$\sim$</tex-math> </inline-formula>1.9 times more reduction on the bound interval lengths of all interesting paths and use up to 50.4%<inline-formula> <tex-math notation="LaTeX">$\sim$</tex-math> </inline-formula>62.5% fewer monitors in various network settings.