000150640 001__ 150640
000150640 005__ 20190316234843.0
000150640 037__ $$aCONF 000150640 245__$$aNetwork Tomography on Correlated Links
000150640 269__ $$a2010 000150640 260__$$c2010
000150640 336__ $$aConference Papers 000150640 520__$$aNetwork tomography establishes linear relationships between the characteristics of individual links and those of end-to-end paths. It has been proved that these relationships can be used to infer the characteristics of links from end-to-end measurements, provided that links are not correlated, i.e., the status of one link is independent from the status of other links. In this paper, we consider the problem of identifying link characteristics from end-to-end measurements when links are "correlated," i.e., the status of one link may depend on the status of other links. There are several practical scenarios in which this can happen; for instance, if we know the network topology at the IP-link or at the domain-link level, then links from the same local-area network or the same administrative domain are potentially correlated, since they may be sharing physical links, network equipment, even management processes. We formally prove that, under certain well defined conditions, network tomography works when links are correlated, in particular, it is possible to identify the probability that each link is congested from end-to-end measurements. We also present a practical algorithm that computes these probabilities. We evaluate our algorithm through extensive simulations and show that it is accurate in a variety of realistic congestion scenarios.
000150640 6531_ $$aNetwork Performance Tomography 000150640 6531_$$aLink Correlation
000150640 700__ $$0242764$$g173437$$aGhita, Denisa 000150640 700__$$0243542$$g176638$$aArgyraki, Katerina
000150640 700__ $$aThiran, Patrick$$g103925$$0240373 000150640 7112_$$dNovember 1-3, 2010$$cMelbourne, Australia$$aACM Internet Measurement Conference (IMC)
000150640 773__ $$tProceedings of the ACM Internet Measurement Conference (IMC) 000150640 8564_$$uhttps://infoscience.epfl.ch/record/150640/files/imc046-ghita.pdf$$zn/a$$s491351$$yn/a 000150640 909C0$$xU12550$$0252412$$pNAL
000150640 909C0 $$pLCA3$$xU10431$$0252454 000150640 909CO$$qGLOBAL_SET$$pconf$$pIC$$ooai:infoscience.tind.io:150640 000150640 917Z8$$x173437
000150640 917Z8 $$x176638 000150640 917Z8$$x176638
000150640 917Z8 $$x176638 000150640 917Z8$$x176638
000150640 917Z8 $$x176638 000150640 917Z8$$x176638
000150640 917Z8 $$x176638 000150640 937__$$aEPFL-CONF-150640
000150640 973__ $$rREVIEWED$$sPUBLISHED$$aEPFL 000150640 980__$$aCONF