Traffic modeling and weighted fair queueing performance analysis and practice in telecommunications
The internet traffic model and queueing performance evaluation are the key issues for quality of service(QoS)management and scheduling management of bandwidth.In 2019,they are also proposed by the Huawei company as one of the ten challenging problems in telecom-munication area.Based on a practical project from the Huawei company,we study the traffic modeling and queueing performance evaluation in telecommunications.Unlike the classic voice flows,the high-speed traffic flows involve some statistical properties such as the correlation and burstiness.This case activates us to study the more general traffic model.In this paper,we pro-pose a new parameter fitting approach of the batch Markov arrival process(BMAP).Based on the service mechanism of traffic flows in routers,this paper deals with a BMAP/PH/1 queueing system under weighted fair queueing(WFQ)discipline.We derive the stationary queue length distribution and performance measures(the expected queue length and delay,etc.).Finally,the performance of our proposed fitting approach is illustrated by using the teletraffic traces testing from the Huawei company.We show the effectiveness of the proposed model and the applicability of the analysis results obtained in the study via numerical and simulation experiments.
NETL
NSTL
万方数据
