Locating Disruptions on Internet Paths through End-to-End Measurements

摘要

In backbone networks carrying heavy traffic loads, unwanted and unusualend-to-end delay changes can happen, though possibly rarely. In order tounderstand and manage the network to potentially avoid such abrupt changes, itis crucial and challenging to locate where in the network lies the cause ofsuch delays so that some corresponding actions may be taken. To tackle thischallenge, the present paper proposes a simple and novel approach. The proposedapproach relies only on end-to-end measurements, unlike literature approachesthat often require a distributed and possibly complicated monitoring /measurement infrastructure. Here, the key idea of the proposed approach is tomake use of compressed sensing theory to estimate delays on each hop betweenthe two nodes where end-to-end delay measurement is conducted, and infercritical hops that contribute to the abrupt delay increases. To demonstrate itseffectiveness, the proposed approach is applied to a real network. The resultsare encouraging, showing that the proposed approach is able to locate the hopsthat have the most significant impact on or contribute the most to abruptincreases on the end-to-end delay.