基于S型函数动态自适应改进的RED算法

An improved random early detection algorithm based on parameter adaptive dynamic adjustment

针对随机早期检测(RED)算法所存在的参数敏感性问题,本文提出了一种基于参数自适应动态调整的RED算法。针对RED算法的丢弃概率函数是线性的这一问题,利用S型升半哥西分布函数对传统RED算法的丢包率函数进行非线性处理,同时借鉴自适应RED算法调整最大丢弃概率的思想,并利用目标队长的范围和平均队列长度的关系引入参数自适应动态调整策略对最大丢包率进行改进。仿真结果表明改进算法在性能方面有较好的改善效果。

Aiming at the parameter sensitivity problem of RED algorithm, this paper proposes a random early detection (RED) algorithm based on parameter adaptive dynamic adjustment. In view of the problem that the discarding probability function of the RED algorithm is linear, it uses the S type ascending semi Cosi distribution function for the nonlinear processing of the packet loss rate function of the traditional RED algorithm, and uses the adaptive RED algorithm to adjust the maximum discarding probability, and introduces the parameter adaptation by using the relation of the range of the target queue and the length of the queue. The dynamic adjustment strategy improves the maximum packet loss rate. Simulation results show that the improved algorithm has better performance in terms of performance.