A Measurement Study of Correlation of Internet Flow Characteristics
Kun-chan Lan and John HeidemannUSC/Information Sciences Institute
Abstract
Previous studies of Internet traffic have shown that a very small percentage of flows consume most of the network bandwidth. It is important to understand the characteristics of such flows for traffic monitoring and modelling purposes. Several prior researchers have characterized such flows using different classification schemes: by size as elephant and mice; by duration as tortoise and dragonfly; and by burstiness as alpha and beta traffic. However, it is not clear how these different definitions of flows are related to each other. In our work, we study these ``heavy-hitter'' flows in four orthogonal dimensions, namely size, duration, rate and burstiness, and examine how they are correlated. This paper makes three contributions: First, we systematically characterize prior definitions for the properties of such heavy-hitter traffic. Second, we show that there are strong correlations between some combinations of size, rate and burstiness. Finally, we show that these correlations can be explained by transport and application-level protocol mechanisms.Availability
This paper is available in several formats: abstract web page with pointers and cites, PDF, paper copies can be obtained by mail to the authors. Copyright terms for this paper appear below.
Reference
- Lan06a
- Kun-chan Lan and John Heidemann. A Measurement Study of Correlation of Internet Flow Characteristics. Computer Networks, 50 (1 ), pp. 46-62, January, 2006. <http://www.isi.edu/~johnh/PAPERS/Lan06a.html>.
@article{Lan06a,
author = "Kun-chan Lan and John Heidemann",
title = "A Measurement Study of Correlation of {Internet} Flow Characteristics",
keywords = "Internet traffic, elephant, tortise, cheetah,
porcupine",
xnote = "updated 20-Feb-05 wrt journal changes; orginal ref [Lan03c]",
url = "http://www.isi.edu/~johnh/PAPERS/Lan06a.html",
pdfurl = "http://www.isi.edu/~johnh/PAPERS/Lan06a.pdf",
journal = "Computer Networks",
year = "2006",
volume = "50",
number = "1",
month = "January",
pages = "46--62",
myorganization = "USC/Information Sciences Institute",
copyrightholder = "Elsevier Science Publishing Co., Inc.",
otherurl = "http://www.cse.unsw.edu.au/~klan/paper/flow.pdf",
}