Hurst Parameter Estimation and Characteristics Analysis of Wireless LAN Traffic
Mao Yuming · Dianzi Ke-ji Daxue xuebao · 2007
In this paper,the statistical properties of WLAN are studied.Three statistical analysis methods, R/S statistic,variance-time plots and periodogram-based analysis are applied to the Hurst parameter estimation of the degree of the self-similarity and the burstiness of the WLAN traffic.Simulation results show that the WLAN traffic is characterized by self-similarity.By comparing the above three statistical analysis methods,the estimations of Hurst paramater by variance-time plots and periodogram-based analysis methods are approximated equal.But the estimation result of R/S statistic deviates from other two methods.greatly.The research results will play important role in the WLAN traffic exact modeling,traffic control,network resources optimization and network performance improvement.