DocumentCode :
3551068
Title :
Neural network control for TCP network congestion
Author :
Cho, Hyun C. ; Fadali, M. Sami ; Lee, Hyunjeong
Author_Institution :
Dept. of Electr. Eng., Nevada Univ., Las Vegas, NV, USA
fYear :
2005
fDate :
8-10 June 2005
Firstpage :
3480
Abstract :
Active queue management (AQM) has been widely used for congestion avoidance in transmission control protocol (TCP) networks. Although numerous AQM schemes have been proposed to regulate a queue size close to a reference level, most of them are incapable of adequately adapting to TCP network dynamics due to TCP´s non-linearity and time-varying stochastic properties. To alleviate these problems, we introduce an AQM technique based on a dynamic neural network using the back-propagation (BP) algorithm. The dynamic neural network is designed to perform as a robust adaptive feedback controller for TCP dynamics after an adequate training period. We evaluate the performances of the proposed neural network AQM approach using simulation experiments. The proposed approach yields superior performance with faster transient time, larger throughput, and higher link utilization compared to two existing schemes: random early detection (RED) and proportional-integral (PI)-based AQM. The neural AQM outperformed PI control and RED, especially in transient state and TCP dynamics variation.
Keywords :
PI control; adaptive control; backpropagation; control system synthesis; feedback; neurocontrollers; queueing theory; robust control; stochastic systems; telecommunication congestion control; transport protocols; PI control; TCP network congestion; back-propagation algorithm; dynamic neural network; neural network control; nonlinearity properties; proportional-integral control; queue size; random early detection; robust adaptive feedback controller design; time-varying stochastic properties; transient state; transmission control protocol; Adaptive control; Engineering management; Neural networks; Performance evaluation; Programmable control; Protocols; Robust control; Size control; Stochastic processes; Traffic control;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
American Control Conference, 2005. Proceedings of the 2005
ISSN :
0743-1619
Print_ISBN :
0-7803-9098-9
Electronic_ISBN :
0743-1619
Type :
conf
DOI :
10.1109/ACC.2005.1470511
Filename :
1470511
Link To Document :
بازگشت