基于智能管理缓冲区的网络拥塞控制算法

该文从数据包占用缓冲区的实时状态出发，运用模糊理论对缓冲区占用率状态这一模糊性问题进行描述，建立基于智能管理缓冲区的拥塞控制模型，对所有的数据流根据其服务质量要求进行优先级分类，并取得相应的队列带宽，采取整体和局部相结合的方法，路由器智能管理缓冲区。实验仿真结果表明，基于智能管理缓冲区的拥塞控制算法（IMBA）与RED、TD-FIFO等算法比较，在保护和隔离非拥塞状态的连接方面，具有更好的公平性，从而进一步改进了路由器的拥塞控制性能。

Network Congestion Control Algorithm Based on Intelligent Management of Buffer

By describing the practical buffer performance in routers, a new intelligent management buffer model based on queues and a congestion control algorithm based on the model are presented. All kinds of packets are firstly classified into queues according to their own priorities, and a suitable bandwidth is achieved. A mothed is used which combines entireness with part. Routers intelligently manage buffers. Simulation results show: compared with the random early detection (RED) algorithm and tail drop first in first out (TD-FIFO) algorithm, especially keeping from being affected by the connections with congestion, the proposed algorithm has better networking performance in the fairness of all connection. It really improves the router' s ability to deal with network congestion.