DocumentCode :
550721
Title :
An active queue management algorithm based on adaptive variable structure control using neuron learning
Author :
Zhou Chuan ; Wu Yifei ; Chen Qingwei
Author_Institution :
Sch. of Autom., Nanjing Univ. of Sci. & Technol., Nanjing, China
fYear :
2011
fDate :
22-24 July 2011
Firstpage :
4397
Lastpage :
4401
Abstract :
Considering the non-linearity of TCP model, uncertainty of RTT and fluctuation of network load, an active queue management scheme based on variable structure control by using single neuron adaptive learning is proposed. The nonlinear variable structure controller (VSC) is used to guarantee the swiftness and robustness of queue response at router. However, the jitter of VSC will cause the queue fluctuation and performance degradation.Therefore a single neuron is introduced to adjust the parameters of the variable structure controller in order to alleviate the effect of jitter and modelling uncertainty. The scheme can reduce the jitter problem and enhance the robustness for AQM control system greatly. Finally, simulation results show the effectiveness of the proposed algorithm through NS-2 simulator.
Keywords :
neurocontrollers; nonlinear control systems; queueing theory; telecommunication congestion control; telecommunication network management; variable structure systems; AQM control system; NS-2 simulator; TCP model; active queue management algorithm; adaptive variable structure control; jitter problem; modelling uncertainty; neuron learning; nonlinear variable structure controller; nonlinearity; queue fluctuation; single neuron adaptive learning; Delay; Fluctuations; Internet; Jitter; Neurons; Robustness; Simulation; Active Queue Management; Congestion Control; Jitter; Neuron; Variable Structure Control;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Control Conference (CCC), 2011 30th Chinese
Conference_Location :
Yantai
ISSN :
1934-1768
Print_ISBN :
978-1-4577-0677-6
Electronic_ISBN :
1934-1768
Type :
conf
Filename :
6001060
Link To Document :
بازگشت