Research And Design Of Fuzzy Control Strategy For The Congestion Control

Internet has been developed into the infrastructure of today's social life. People are expecting more and more capabilities such as performance, content and safety from network. However, the main kind of service is still"Best Effort"in the Internet. All packets are treated equally. There lacks of efficient queue management. Congestion happens here and there, which causes the dropping of packets or the jitteriness of transport, and even pervades to collapse the network.There are many factors influencing network quality of service. An important one is network congestion. As a crucial method to avoid and control network congestion, congestion control is not only the critical factor of network performance and efficiency improvement, but also the premise of improving network quality of service.This paper reviews the current network congestion control mechanism, the end system congestion control mechanism and router congestion control mechanisms. Summed up the application of fuzzy theory in the active queue management now in several typical applications. Introduced the fuzzy control theory and designed the fuzzy control of active queue management algorithm.In this paper, summed up the current congestion control algorithm of the strengths and weaknesses, based on analyzing several of the current popular active queue management algorithms, such as RED, PI. And proposed a more optimized solution─Fuzzy-Control based on simulation analysis of the PI algorithm. This method don't need to consider the structure of the system itself, only the system input and output. The method is simple, and simulation results show Fuzzy-Control algorithm can achieve a more stable equilibrium point faster than the PI algorithm, and can provide more stable average queue length, lower packet loss rate and delay jitter, improve the net transfer TCP throughput, thereby improving the quality of network data transmission.