For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
Multiscale Modeling with Stable Distribution Marginals for Long-Range Dependent Network Traffic
Chien Trinh NGUYEN Tetsuya MIKI
IEICE TRANSACTIONS on Communications
Publication Date: 2002/12/01
Print ISSN: 0916-8516
Type of Manuscript: PAPER
traffic modeling, long-range dependence, multifractals, multiplicative cascades, stable distribution,
Full Text: PDF(482.4KB)>>
As demonstrated by many studies, measured wide-area network traffic exhibits fractal properties, such as self-similarity, burstiness, and long-range dependence (LRD). In order to describe long-range dependent network traffic and to emphasize the performance aspects of descriptive traffic models with additive and multiplicative structures, the multifractal wavelet model (MWM), which is based on the binomial cascade, has been shown to match the behavior of network traffic over small and large time scales. In this paper, using appropriate mathematical and statistical analyses, we develop the MWM proposed in , which provides a complete description of long-range dependent network traffic. First, we present accurate parameters of the MWM over different time scales. Next, a marginal stable distribution of MWM network traffic data is analyzed. The accuracy of the proposed MWM compared to actual data measurements is confirmed by queuing behavior performance through computer simulations.