参数自适应的随机早期检测算法

随机早期检测(Random Early Detection，RED)是一种广泛应用于包交换网络的主动队列管理技术，它通过保持较小的平均队列长度，在缓冲区溢出前主动丢包，降低路由器的丢包率，保持较低的服务延迟，避免缓冲区锁定，提高网络的利用率。但是RED严重依赖于参数的设置。该文根据保持网络流量平稳的丢包率和路由队列的变化提出了一种自适应地调节参数的RED改进算法。模拟实验的结果表明，自适应地调节参数提高了RED的适应性，降低了数据包排队延时和丢包率，提高了链路利用率。

An Adaptive RED Algorithm Restraining the Queue Ascending

Random Early Detection (RED) is a widely deployed active queue management scheme in packet switched networks, which improves the link utilization of the network and the internet performance. It can reduce the number of packets dropped in routers by dropping packets before the queue becomes full, provide lower-delay interactive service by keeping the average queue size small and avoid lock-out of the routers buffer by ensuring that there will almost always be a buffer available for an incoming packet. But its performance depends severely on the tuning of its operating parameters. In this paper, we propose an adaptive RED based on both the drop rate in the case of a stable traffic and the change of queue length. The simulation results show that the adaptive algorithm has improved the adaptability of the RED algorithm, reduced the delay of the queuing packet and the aggregate drop rate.