WLAN业务量特性分析及Hurst参数辨识

Hurst Parameter Estimation and Characteristics Analysis of Wireless LAN Traffic

研究了无线局域网业务量统计特性;并运用R/S统计、方差-时间图和周期图法对测度无线局域网业务量自相似程度和突发性的重要参数Hurst参数进行辨识。仿真结果表明,无线局城网业务量具有自相似统计特性。通过比较其Hurst参数辨识的三种方法可知:利用方差-时间图法和周期图法得到的Hurst参数辨识值接近相等,而R/S统计辨识的Hurst参数值偏离较大。对无线局域网流量的准确建模以及网络传输中流量控制和优化网络资源配置以及提高网络性能具有重要作用。

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.