Title :
An Enhanced PID Based Active Queue Management Algorithm
Author :
Zhou Chi-Min ; Deng Li-guo ; Zhao Jing
Author_Institution :
Sch. of Inf. Sci. & Technol., Chengdu Univ., Chengdu, China
Abstract :
The AQM (Active Queue Management) Algorithm such as RED, PI, REM have too long respond time and some other problems. Though it makes some enhancement, the PID (Proportional Integral Differential) active queue management algorithm can not make the queue length converge to expectation with longer delay. Because of self-adapt control of BP (back-propagation) neural network, this issue bring forward a BP neural network based PID active queue management algorithm.
Keywords :
Internet; adaptive control; backpropagation; neural nets; queueing theory; telecommunication congestion control; three-term control; active queue management algorithm; backpropagation neural network; enhanced PID; self adapt control; Artificial neural networks; Control systems; Delay; Internet; Mathematical model; Neurons; Stability analysis; AQM; BP neural network; PID;
Conference_Titel :
Computational Aspects of Social Networks (CASoN), 2010 International Conference on
Conference_Location :
Taiyuan
Print_ISBN :
978-1-4244-8785-1
DOI :
10.1109/CASoN.2010.26
