Inferring Link Loss Rates from Unicast-Based End-to-End Measurement

Masato TSURU  Tetsuya TAKINE  Yuji OIE  

IEICE TRANSACTIONS on Communications   Vol.E85-B   No.1   pp.70-78
Publication Date: 2002/01/01
Online ISSN: 
Print ISSN: 0916-8516
Type of Manuscript: Special Section PAPER (Special Issue on Internet Technology II -- Traffic Control and Performance Evaluation in the Internet)
link loss rate,  end-to-end measurement,  statistical inference,  

Full Text: PDF>>
Buy this Article

In the Internet, because of huge scale and distributed administration, it is of practical importance to infer network-internal characteristics that cannot be measured directly. In this paper, based on a general framework we proposed previously, we present a feasible method of inferring packet loss rates of individual links from end-to-end measurement of unicast probe packets. Compared with methods using multicast probes, unicast-based inference methods are more flexible and widely applicable, whereas they have a problem with imperfect correlation in concurrent events on paths. Our method can infer link loss rates under this problem, and is applicable to various path-topologies including trees, inverse trees and their combinations. We also show simulation results which indicate potential of our unicast-based method.