Modeling the GPRS Network Latency with a Double Pareto-lognormal or a Generalized Beta Distribution

Taking a newly collected large data set on the TCP connection termination latency in GPRS networks we try to identify the underlying statistical distribution. The data extends the observed latencies to large time scales necessitating a heavy-tail distribution. Many distributions work well for the main body of the data. However, the heavy tail of the distribution benefits from mixing different statistical distributions. We compare several distributions and find that the double Pareto-lognormal distribution and the generalized Beta distribution of the second kind fit the data equally well.

[1]  Stefan Baumgärtner,et al.  Model Choice and Size Distribution: A Bayequentist Approach , 2012 .

[2]  James B. McDonald,et al.  Some Generalized Functions for the Size Distribution of Income , 1984 .

[3]  James B. McDonald,et al.  A generalization of the beta distribution with applications , 1995 .

[4]  Alexis Akira Toda.  The double power law in income distribution: Explanations and evidence , 2012 .

[5]  H. Akaike.  A new look at the statistical model identification , 1974 .

[6]  Richard P. Brent,et al.  Modern Computer Arithmetic , 2010 .

[7]  W. Reed.  The Normal-Laplace Distribution and Its Relatives , 2006 .

[8]  Jacob Otieno,et al.  From The Classical Beta Distribution To Generalized Beta Distributions , 2008 .

[9]  Mark E. J. Newman,et al.  Power-Law Distributions in Empirical Data , 2007, SIAM Rev..

[10]  Broderick O. Oluyede,et al.  Weighted generalized beta distribution of the second kind and related distributions , 2012 .

[11]  Christos Faloutsos,et al.  Mobile call graphs: beyond power-law and lognormal distributions , 2008, KDD.

[12]  Fabio Ricciato,et al.  Network-Wide Measurements of TCP RTT in 3G , 2009, TMA.

[13]  Péter Benkö,et al.  A large-scale, passive analysis of end-to-end TCP performance over GPRS , 2004, IEEE INFOCOM 2004.

[14]  Michael Mitzenmacher,et al.  A Brief History of Generative Models for Power Law and Lognormal Distributions , 2004, Internet Math..

[15]  William J. Reed,et al.  The Double Pareto-Lognormal Distribution—A New Parametric Model for Size Distributions , 2004, WWW 2001.

[16]  Daniel T. Robb,et al.  Random Phenotypic Variation of Yeast (Saccharomyces cerevisiae) Single-Gene Knockouts Fits a Double Pareto-Lognormal Distribution , 2012, PloS one.

[17]  Chuan Chuan Zhang,et al.  The Double Pareto-Lognormal Distribution and its applications in actuarial science and finance , 2015 .

[18]  Yuan Ye,et al.  Properties of Weighted Generalized Beta Distribution of the Second Kind , 2012 .