Title :
Novel Smith Predictor and BPNN for Wireless Networked Control Systems
Author :
Du, Feng ; Du, Wencai
Author_Institution :
Coll. of Inf. Sci. & Technol., Hainan Univ., Haikou, China
Abstract :
In order to effectively restrain the impact of network delays which are brought because of bandwidth constraint, path loss, signal attenuation and ambient noise in wireless networked control systems (WNCS), aiming at time-variant network delays and imprecise Smith predictor models, a new approach is proposed that novel Smith dynamic predictor combined with back propagation neural network (BPNN) control. Because new Smith predictor does not include network delay models, therefore network delays do not need to be measured, identified or estimated on-line, it is applicable to some occasions that network delays are random, time-variant or uncertain. Based on IEEE 802.11b/g (WLAN), the results of simulation experiment show validity of the control scheme.
Keywords :
backpropagation; bandwidth allocation; delays; neurocontrollers; time-varying systems; wireless LAN; BPNN; IEEE 802.11b/g; Smith dynamic predictor; Smith predictor models; WLAN; ambient noise; back propagation neural network control; bandwidth constraint; network delay models; path loss; signal attenuation; time-variant network delays; wireless networked control systems; Attenuation; Bandwidth; Delay effects; Delay estimation; Networked control systems; Neural networks; Predictive models; Propagation delay; Propagation losses; Wireless LAN; Smith predictor; back propagation neural network (BPNN); network delay; wireless networked control systems (WNCS);
Conference_Titel :
Information Processing, 2009. APCIP 2009. Asia-Pacific Conference on
Conference_Location :
Shenzhen
Print_ISBN :
978-0-7695-3699-6
DOI :
10.1109/APCIP.2009.24