Inferring Invisible Internet Traffic

Abstract

The Internet is at once an immense engineering artifact, a pervasive social force, and a fascinating object of study. Unfortunately many natural questions about the Internet cannot be answered by direct measurement, requiring us to turn instead to the tools of statistical inference. As a detailed example I'll describe a current project in traffic measurement. We are asking the question: using traffic measurements taken at one location in the Internet, can we estimate how much traffic is flowing in a different part of the Internet? Surprisingly, the answer is yes. I'll explain why this is possible (with a connection to problems like the Netflix Prize), how it can be done, and how this result could be used to give a network operator an edge over its competitors.

Bio:

Mark Crovella is Professor and Chair of the Department of Computer Science at Boston University. His research interests center on improving the understanding, design, and performance of parallel and networked computer systems, mainly through the application of data mining, statistics, and performance evaluation. In the networking arena, he has worked on characterizing the Internet and the World Wide Web. He has explored the presence and implications of self- similarity and heavy-tailed distributions in network traffic and Web workloads. He has also investigated the implications of Web workloads for the design of scalable and cost-effective Web servers. In addition he has made numerous contributions to Internet measurement and modeling; and he has examined the impact of network properties on the design of protocols and the construction of statistical models.

Professor Crovella is co-author of "Internet Measurement: Infrastructure, Traffic, and Applications" (Wiley Press, 2006) and is the author of over one hundred and fifty papers, with over 19,000 citations (Google Scholar). Between 2007 and 2009 he was Chair of ACM SIGCOMM. In 2010 his paper "Self-Similarity in World Wide Web Traffic: Evidence and Possible Causes" received the SIGMETRICS Test of Time Award, and in 2013 his paper "Routing State Distance: A Path- Based Metric for Network Analysis" won the IETF Applied Networking Research Prize. Professor Crovella is a Fellow of the ACM and of the IEEE.