Title :
A New Active Queue Management Algorithm Based on Self-Adaptive Fuzzy Neural-Network PID Controller
Author :
Yan Qiao ; Lei Qiongyu
Author_Institution :
Coll. of Comput. & Software, Shenzhen Univ., Shenzhen, China
Abstract :
Active queue management (AQM) is a very important research area in congestion control. But the complexity and dynamic characteristic of the computer network cause the traditional PID control algorithm low adaptability to dynamic environment due to its fixed parameters. In order to overcome such shortcomings, intelligent control theory was introduced to congestion control research, and a new AQM algorithm called FAPIDNN was proposed. Fuzzy controller automatically computers the learning rate according to the current network state, and the neural network PID controller calculate the packet dropping probability based on the learning rate provided by the fuzzy controller. Simulation results show that FAPIDNN algorithm is superior to the presented PID controller on the queue stability, convergence speed and time delay.
Keywords :
adaptive control; computer network management; delays; fuzzy neural nets; neurocontrollers; probability; telecommunication congestion control; three-term control; FAPIDNN; active queue management algorithm; computer network; congestion control; convergence speed; intelligent control theory; learning; packet dropping probability; queue stability; self-adaptive fuzzy neural-network PID controller; time delay; Biological neural networks; Control systems; Convergence; Heuristic algorithms; Neurons; Simulation; Stability analysis;
Conference_Titel :
Internet Technology and Applications (iTAP), 2011 International Conference on
Conference_Location :
Wuhan
Print_ISBN :
978-1-4244-7253-6
DOI :
10.1109/ITAP.2011.6006116