RESEARCH ON NETWORK NODE CLOSED LOOP CONTROL MECHANISM BASED ON PROBABILITY DROP SCHEME

摘要：

In order to solve the increasingly serious network congestion, a node closed loop PID control mechanism is proposed, which is based on BP neural network (abbr. BPNN).This mechanism works with active queue management (abbr.AQM) scheme with probability drop strategy, which forms a closed loop by controlling node buffer average queue size. The method tries to avoid the disadvantages of the traditional solutions, which control input and output traffic flow. This paper presents the closed loop configuration figure, and gives the algorithm realizations of PID controller model based on BP neural network and probability drop strategy. Simulation that runs on the OPNET software is carried out on the node model. The simulation results show that the proposed mechanism works well in terms of convergence speed of PID parameters, stability and anti-jamming of the average queue size and the system robustness.

关键词： Probability drop Active queue management Neural network Closed loop control

作者: DE-HUI SUN DA ZHANG

作者单位: The Key Laboratory of Beijing for Field-bus Technology & Automation, North China University of Technology,Beijing 100041, China

会议类型: 国际会议

会议名称: 2006 International Conference on Machine Learning and Cybernetics(IEEE第五届机器学习与控制论坛)

会议地点: 大连

会议语种:英文

页码: 252-255

在线出版日期: 2006-08-13（万方平台首次上网日期，不代表论文的发表时间）