Reseach on the Self-Similarity of Multi-probabilty Ditribution Based on ON-OFF Models in AOS Multiplexing

Abstract

Pareto on-off models were widely adopted to simulate and construct network traffic with self-similar characteristic. In this paper, a new Pareto-Poisson model was proposed based on AOS multiplexing. And the new model can produce self-similarity network traffic with adjustable H parameter. In the R/S test algorithm, the new self-similar represents well the self-similar characteristic.