Self similarity analysis via fractional Fourier transform

Self similarity has taken great interest in computer networks since modeling of Ethernet traffic via self similarity. Recent studies have shown that network traffic exhibits long range dependency which could not be modeled with Poisson distribution. Time and frequency domain representations are frequently utilized to better visualize and characterize self similar stochastic processes. onal Fourier transform is a generalization of ordinary Fourier transform and find applications in many areas that ordinary Fourier transform has found. In this study, a network traffic analysis via fractional Fourier transform is performed. This study aims to better evaluate self similarity of network traffic via using fractional Fourier transform. Due to their high self similarity degrees, real IPv6 packet traffic is used for the analysis. We also perform analysis with an exact self similar process, fractional Gaussian noise to compare the results.