An Improved Adaptive Active Queue Management Algorithm Based on Nonlinear Smoothing
Jingjun Zhang, Wenlong Xu, Liguo Wang · Procedia Engineering · 2011
According to analyzing the principle and limitations of RED and its improved algorithms, an improved adaptive RED congestion control mechanism is proposed in this paper, which imposes nonlinear smooth for packet loss rate function of RED algorithm by using the membership function of the ascend demi-cauchy of fuzzy distribution. The speed of growth of packet loss rate is relatively slow near the minimum threshold, while near the maximum threshold the speed of growth of packet loss rate is relatively faster. ThePmax will be dynamically adjusted by the length of average queue and the target for adapting the changing of network environment. NS simulation shows that this algorithm has been significantly improved for packet loss rate, throughput and other performance.