Congestion Control Based On The Intelligent Network Of Technology Research

In recent years, with the expanding of user numbers in Internet, the problem of network congestion is becoming more and more serious. Therefore, designing a simple and efficient congestion control algorithm becomes an urgently problem in network management. Active queue management (AQM) combines with TCP end-to-end congestion control being the main approach to solve the problem of Internet congestion control at present. Active queue management and transport control protocol (TCP) are all the while two active fields in communication group.In this thesis, Internet end-to-end congestion control is studied. The main research works and conclusions are as follows:This paper summarizes the study status in quo and common algorithm of network congestion control in detail, analyzes its study trends in detail, introduces the link algorithm executed by network and the source algorithm executed by host computers or edge devices.This paper dissertates in details the application of control theories in active queue management, emphasizes the PID control algorithm,integral-separated PID algorithm and differential-before-PID, and also proves the stability of PID algorithm.This paper designs an incomplete derivation fuzzy-PID controller, and simulates this algorithm with the NS-2 simulation software. Simulation results have shown that, this algorithm can improve the dynamic state property better.