Simulation Based Performance Evaluation of Queueing Disciplines for Multi-Class Traffic

Abstract

Queuing is one of the very vital mechanisms in traffic management system. Each router in the network must implement some queuing discipline that governs how packets are buffered while waiting to be transmitted. Several queue scheduling disciplines have been designed to improve the quality of service and to avoid congestion for networked multimedia applications. In this paper, we evaluate the performance of four queueing disciplines (FIFO, PQ, WFQ and DWRR) that are widely deployed for multi-class traffic and analyze their performance using OPNET simulator and compare their relative performance based on queueing delay, packet received, packet drop rate, end-to-end delay and delay jitter with RED and WRED policies. Keywords - Deficit-Weighted Round Robin, Multi-Class Traffic, OPNET Simulation, Priority Queuing, Weighted-Fair Queuing. I. Introduction With the growth of internet during the last decade IP networks are expected to support not only typical services like ftp and email but also video streaming and voice applications. There are many network parameters for its performance evaluation that are required for different application A number of queueing disciplines have been proposed to achieve the required quality of service in today's network services. In this paper, we analyze the performance of a typical network topology under four different queueing disciplines which are widely deployed and compare their performance OPNET simulator (2). The queueing disciplines considered are: First- In-First-Out (FIFO), Priority Queueing (PQ), Weighted Fair queueing (WFQ) and Deficit Weighted Round Robin queueing (DWRR). We also scrutinize the effect of two dropping policies, random-early drop (RED) (3) and weighted random-early drop(WRED), on their performance. We then present the simulation results and evaluate their performance.