Locating disruptions on an Internet path through end-to-end measurements

Unwanted or unusual delay changes on an Internet path can happen, though possibly rarely. In order to understand and manage the network to potentially avoid such abrupt changes, it is crucial and challenging to locate which part of the path has contributed critically to such delay disruptions so that some corresponding actions may be taken. To tackle this challenge, the present paper proposes a simple and novel approach. The proposed approach relies only on end-to-end measurements of the path. Specifically, the end-to-end measurements include end-to-end delay measurement and traceroute measurement.With the former, abrupt delay increases are flagged and a delay disruption matrix is constructed. With the latter, a routing matrix for the end-to-end path is formed. The key idea of the proposed approach is to link the routing matrix to the delay disruption matrix and make use of compressed sensing theory to infer critical hops in the routing matrix which contribute to the abrupt delay increases. To demonstrate its effectiveness, the proposed approach is applied to a real Internet path. The results are encouraging, showing that the proposed approach is able to locate the hops that have the most significant impact on or contribute the most to abrupt increases on the end-to-end delay of the measured Internet path.