On the feasibility of utilizing correlations between user populations for traffic inference

On the feasibility of utilizing correlations between user populations for traffic inference

Lan, Kun-chan and Heidemann, John
USC/Information Sciences Institute

Kun-chan Lan and John Heidemann 2005. On the feasibility of utilizing correlations between user populations for traffic inference. Proceedings of the 30th IEEE International Conference on Local Computer Networks (Sydney, Australia, Nov. 2005), 132–139.

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.

Reference

@inproceedings{Lan05a,
  author = {Lan, Kun-chan and Heidemann, John},
  title = {On the feasibility of utilizing correlations between user populations for traffic inference},
  booktitle = {Proceedings of the 30th IEEE International Conference on Local Computer Networks},
  year = {2005},
  sortdate = {2005-11-01},
  project = {ant, nocredit, saman},
  jsubject = {traffic_modeling},
  publisher = {IEEE},
  address = {Sydney, Australia},
  month = nov,
  pages = {132--139},
  location = {johnh: pafile},
  url = {http://www.isi.edu/%7ejohnh/PAPERS/Lan05a.html},
  pdfurl = {http://www.isi.edu/%7ejohnh/PAPERS/Lan05a.pdf},
  myorganization = {USC/Information Sciences Institute}
}