A Comprehensive Analytical Model for Weighted Fair Queuing under Multi-Class Self-Similar Traffic

Weighted fair queueing (WFQ) is a practical scheduling discipline for supporting differentiated quality-of-service (QoS) in computer networks and communication systems. Analytical models are important tools for system performance evaluation and resource optimization. However, there is not any comprehensive model reported in the open literature for analytically investigating the performance behaviors of WFQ subject to multiple self-similar traffic flows. To fill this gap, this paper develops such a model and derives the upper bounds for the distributions of several important QoS performance metrics including queue length, packet delay and loss of traffic flows in the WFQ system. The comparison between analytical and simulation results using the traffic parameters obtained from real-world MPEG frame traces validates the accuracy of the developed model which can be used for investigating the performance behavior of WFQ systems with multi-class self- similar traffic under realistic working conditions.