On Problems Of Network Congestion Control Based On Active Queue Management Algorithm

With the rapid development of Internet, network has been widely applied, while more and more serious congestion problems have been exposed. Network congestion control is one of key factors to ensure the stability of Internet since it can effectively improve network’s performance. As a complementary method to end-to-end congestion control, the Active Queue Management (AQM) algorithm take effective preventive measures before the congestion occurs by dropping packets purposeful, in order to ensure the network quality of service.This paper emphasized on designs of active queue management algorithms in network nodes for Internet congestion control. The primary work is:The thesis introduces the concept and meaning of congestion and congestion control, and the mechanism of congestion control of TCP/IP is introduced. Then the AQM algorithm of IP congestion control mechanism is emphatically introduced, and the paper indicates that the AQM is very important in congestion control. The AQM algorithm drops the data-packages before the queue achieving full, so that the terminal node can response early, and thus the congestion can be avoided truly. RED is the most famous AQM algorithm, and congestion control based on control theory becomes a new research focus.In order to improve the dynamic performance of the congestion control system, an AQM algorithm based on sliding mode variable structure control is proposed. The switching function of the AQM algorithm is connected by the switching function of linear sliding mode and nonsingular terminal sliding mode. If the system state is far away from the equilibrium, the system runs on linear sliding mode. If the system state is near to the equilibrium, the system runs on nonsingular terminal sliding mode. A switching control law is designed to guarantee the reaching time and sliding time are finite. The simulation show the designed AQM algorithm realizes the global fast convergence and improves the dynamic performance of the system.Because of many uncertain factors in the network, a robust AQM algorithm was presented for network congestion, which is based on uncertain parameters and variable link bandwidth. The unknown link bandwidth is modeled as a time-variant disturbance. The model of TCP/AQM including the state delay was presented in state variables. Then, the network congestion problem is solved by using the time-domain H∞control approach. The simulation results show that this algorithm is capable of achieving the desired queue length fast under the conditions of variable RTT and link bandwidth. The performances of the proposed algorithm increase greatly compared with the existing algorithm.Lastly, the research work is concluded. The further research direction is pointed out, and the prospect of solving congestion control is looked forward.