Lognormal and Pareto distributions in the Internet

Numerous studies have reported long-tailed distributions for various network metrics, including file sizes, transfer times, and burst lengths. We review techniques for identifying long-tailed distributions based on a sample, propose a new technique, and apply these methods to datasets used in previous reports. We find that the evidence for long tails is inconsistent, and that lognormal and other non-long-tailed models are usually sufficient to characterize network metrics. We discuss the implications of this result for current explanations of self-similarity in network traffic.

[1]  Armand M. Makowski,et al.  M|G|/spl infin/ input processes: a versatile class of models for network traffic , 1997, Proceedings of INFOCOM '97.

[2]  Shuang Deng,et al.  Empirical model of WWW document arrivals at access link , 1996, Proceedings of ICC/SUPERCOMM '96 - International Conference on Communications.

[3]  Sally Floyd,et al.  Wide area traffic: the failure of Poisson modeling , 1995, TNET.

[4]  Joachim Charzinski,et al.  HTTP/TCP connection and flow characteristics , 2000, Perform. Evaluation.

[5]  Walter Willinger,et al.  Proof of a fundamental result in self-similar traffic modeling , 1997, CCRV.

[6]  M. Crovella,et al.  Estimating the Heavy Tail Index from Scaling Properties , 1999 .

[7]  Walter Willinger,et al.  Self‐Similar Network Traffic: An Overview , 2002 .

[8]  William J. Bolosky,et al.  A large-scale study of file-system contents , 1999, SIGMETRICS '99.

[9]  Azer Bestavros,et al.  Self-similarity in World Wide Web traffic: evidence and possible causes , 1996, SIGMETRICS '96.

[10]  Mark Crovella,et al.  Characteristics of WWW Client-based Traces , 1995 .

[11]  Joachim Charzinksi,et al.  HTTP/TCP connection and flow characteristics , 2000 .

[12]  Walter Willinger,et al.  Self-similarity through high-variability: statistical analysis of Ethernet LAN traffic at the source level , 1997, TNET.

[13]  Anja Feldmann,et al.  The changing nature of network traffic: scaling phenomena , 1998, CCRV.

[14]  Anja Feldmann,et al.  Dynamics of IP traffic: a study of the role of variability and the impact of control , 1999, SIGCOMM '99.

[15]  Martin Arlitt,et al.  Workload Characterization of the 1998 World Cup Web Site , 1999 .

[16]  Allen B. Downey,et al.  Evidence for long-tailed distributions in the internet , 2001, IMW '01.

[17]  Martin F. Arlitt,et al.  Workload characterization of a Web proxy in a cable modem environment , 1999, PERV.

[18]  Martin F. Arlitt,et al.  Web server workload characterization: the search for invariants , 1996, SIGMETRICS '96.

[19]  George S. Fishman,et al.  How heavy-tailed distributions affect simulation-generated time averages , 2006, TOMC.

[20]  M. Crovella,et al.  Heavy-tailed probability distributions in the World Wide Web , 1998 .

[21]  Martin Arlitt,et al.  A workload characterization study of the 1998 World Cup Web site , 2000, IEEE Netw..

[22]  Azer Bestavros,et al.  Explaining World Wide Web Traffic Self-Similarity , 1995 .

[23]  Azer Bestavros,et al.  Changes in Web client access patterns: Characteristics and caching implications , 1999, World Wide Web.

[24]  Vern Paxson,et al.  Empirically derived analytic models of wide-area TCP connections , 1994, TNET.

[25]  Walter Willinger,et al.  Self-Similar Network Traffic and Performance Evaluation , 2000 .

[26]  Kihong Park,et al.  On the relationship between file sizes, transport protocols, and self-similar network traffic , 1996, Proceedings of 1996 International Conference on Network Protocols (ICNP-96).

[27]  Mark A. McComb.  A Practical Guide to Heavy Tails , 2000, Technometrics.