A Long Range Dependent Internet Traffic Model Using Unbounded Johnson Distribution

Sunggon KIM  Seung Yeob NAM  

Publication
IEICE TRANSACTIONS on Communications   Vol.E96-B   No.1   pp.301-304
Publication Date: 2013/01/01
Online ISSN: 1745-1345
DOI: 10.1587/transcom.E96.B.301
Print ISSN: 0916-8516
Type of Manuscript: LETTER
Category: Fundamental Theories for Communications
Keyword: 
Internet traffic modeling,  long-range dependence,  fractional Gaussian noise,  unbounded Johnson distribution,  

Full Text: PDF(316.8KB)>>
Buy this Article




Summary: 
It is important to characterize the distributional property and the long-range dependency of traffic arrival processes in modeling Internet traffic. To address this problem, we propose a long-range dependent traffic model using the unbounded Johnson distribution. Using the proposed model, a sequence of traffic rates with the desired four quantiles and Hurst parameter can be generated. Numerical studies show how well the sequence of traffic rates generated by the proposed model mimics that of the real traffic rates using a publicly available Internet traffic trace.