基于突发数据流的丢包智能区分仿真

Simulation Analysis of the Intelligent Packet Loss Recognition Based on Bursty Flow

针对2种不同TCP算法控制下的数据流,后进入的流量容易引起丢包率增加的问题,提出将网络模型中传输层和网络层的拥塞控制算法相结合,对突发数据流引起的丢包率起到一个缓解作用。在该网络环境下,对随机早期检测算法作了改进,通过仿真,新算法在一定程度上能够区分突发流量,从而降低丢包率,为高可靠性网络的发展提供参考。

Aiming at the control of two different TCP algorithm under data stream, after entering the flow it is easy to cause the increase of packet loss rate, the transmission congestion and network layer control algorithm can be combined with the network model. So the packet loss rate plays a role in mitigation of burst data flow. In the net- work environment, the random early detection algorithm has been improved, through the simulation, the new algo- rithm can distinguish the bursty traffic to a certain extent, so as to reduce the packet loss rate, and provide a good reference value to the develooment of high reliability natwnrk.