Active queue management using adaptive RED

Random Early Detection (RED) [1] is an active queue management scheme which has been deployed extensively to reduce packet loss during congestion. Although RED can improve loss rates, its performance depends severely on the tuning of its operating parameters. The idea of adaptively varying RED parameters to suit the network conditions has been investigated in [2], where the maximum packet dropping probability maxp has been varied. This paper focuses on adaptively varying the queue weight wq in conjunction with maxp to improve the performance. We propose two algorithms viz., wq-thresh and wq-ewma to adaptively vary wq. The performance is measured in terms of the packet loss percentage, link utilization and stability of the instantaneous queue length. We demonstrate that varying wq and maxp together results in an overall improvement in loss percentage and queue stability, while maintaining the same link utilization. We also show that maxp has a greater influence on loss percentage and queue stability as compared to wq, and that varying wq has a positive influence on link utilization.