A Tale of the Tails: Power-laws in Internet Measurements

Select |




Print


Mahanti, Aniket; Carlsson, Niklas; Mahanti, Anirban; Arlitt, Martin; Williamson, Carey


2013-01-15


Journal Article


N/A


Power-laws are ubiquitous in the Internet and its applications. In this survey article, we provide a review of such properties in Internet measurements. First, we give definitions of power-law distributions, such as Pareto and Zipf, while also reviewing heavy tails and long tails, and discussing a well-known model for understanding power-law behaviour in computer networks. Second, we present several examples of Internet workload properties exhibiting power-law behaviour. Finally, we explore several implications of power-law in computer networks. Using examples from past and present, we review how researchers have studied and exploited power-law properties. We observe that despite the challenges posed, power-laws have been effectively leveraged by researchers to improve the design and performance of Internet-based systems.


Power law, Internet measurements


nicta:5064


Mahanti, Aniket; Carlsson, Niklas; Mahanti, Anirban; Arlitt, Martin; Williamson, Carey. A Tale of the Tails: Power-laws in Internet Measurements. 2013-01-15. N/A. http://hdl.handle.net/102.100.100/98272?index=1



Loading citation data...

Citation counts
(Requires subscription to view)