基于模糊理论的主动队列管理算法——FBLUE

FBLUE:A Fuzzy-based Algorithm for Active Queue Management

针对BLUE算法的队列长度增减迅猛、吞吐量波动大的缺陷,文中提出了一种改进算法——FBLUE。该算法在原有BLUE算法的基础上增加了门限机制,根据模糊理论使用平均队列长度来动态地调整丢包概率的变化步长。ns2仿真实验结果表明,FBLUE算法保持了BLUE算法丢包率低的优点,并在队列长度、带宽利用率上明显优于BLUE算法。

BLUE uses buffer overflow and link idle events to manage congestion.However,the buffer overflow and link idle events are two extreme points to reflect the congestion status,so BLUE suffers from queue size oscillations,which leads the throughput fluctuation.In this paper,a new active queue management algorithm named FBLUE is proposed.Combined with a threshold and based on the fuzzy theory,FBLUE uses average queue to adjust the dropping probability＇s increment and decrement factor dynamically.By the simulation,FBLUE is shown to perform significantly better than BLUE in terms of queue size and link utilization.