无线网络中一种智能控制的组播拥塞控制机制

针对现有组播拥塞控制算法应用到无线网络中存在的性能下降问题，提出一种基于新的智能组播拥塞控制机制ECMCC。ECMCC机制根据网络相对队列时延和数据包丢失检测网络的拥塞状态，采用代表集合机制反馈信息，利用专家控制器的推理判断区分丢包原因和当前的网络状态，进而采取不同的控制策略调节组播源端发送速率。仿真结果表明，ECMCC机制收敛速度快、灵敏性好、速率变化平滑，在有线网络中具有良好的TCP友好性。同时，ECMCC能有效区分网络拥塞和随机差错，提高了网络的吞吐量，适用于无线网络环境，且在无线网络较低误码率时具有一定的TCP友好性。

Intelligent-controlled multicast congestion control mechanism for wireless networks

In order to improve the performance of existing multicast congestion control algorithm applied to wireless networks, an intelligent-controlled multicast congestion control mechanism is proposed based on expert control for wireless networks, termed ECMCC.ECMCC detects the network congestion state according to network relative queue delay and packet loss, feedbacks information to multicast source based on representatives set mechanism, distinguishes between wireless link errors and network congestion,and judges the current state of the network,then takes different multicast source control strategies to adjust the sending rate.The simulation results show that, ECMCC mechanism has good convergence and sensitivity, smooth sending rate, and good TCP-friendliness in wire network.And ECMCC mechanism enhances the capability to distinguish between network congestion and random errors, and improves the network throughput.ECMCC can adapt itself to a wireless network environment well, achieving some extent on TCP-friendliness over low bit error ratio wireless channel and keeping stable receiving rate over high bit error wireless channel.