Performance Comparison between Active and Passive Queue Management
The queue management algorithm, which is applied to a router, plays an important role in providing Quality of Service (QoS). In this paper we present a simulation-based performance evaluation and compare two popular queue management methods; Random Early Detection (RED) and Drop Tail, in terms of queue size, queuing delay, queuing delay variation, packet drop rate and bandwidth utilization. We also study the effect of buffer behavior on each one of these QoS measurements, as well as considering the effects of using ECN on RED Performance. Simulation results indicate that RED performed better related to Drop Tail in terms of queuing delay, queuing delay variation, and (lower) packet drop rate. Furthermore, using ECN improves RED's bandwidth usage and packet drop rate. Also by measuring the router CPU utilization, we indicate that the difference between active and passive queue management algorithms in terms of CPU utilization, is mostly depend on the buffer size and the network traffic load.
Keywords: Queue Management, Random Early Detection, QoS, Congestion Control
Download Full-Text
