DTHMM based delay modeling and prediction for networked control systems  

作　　者：Shuang Cong Yuan Ge Qigong Chen Ming Jiang Weiwei Shang 

机构地区：[1]Department of Automation, University of Science and Technology of China, Hefei 230027, R R. China [2]Department of Electrical Engineering, Anhui Polytechnic University, Wuhu 241000, E R. China

出　　处：《Journal of Systems Engineering and Electronics》2010年第6期1014-1024,共11页系统工程与电子技术（英文版）

基　　金：supported in part by the National Natural Science Foundation of China (60774098; 60843003; 50905172);the Science Foundation of Anhui Province (090412071; 090412040);the University of Science and Technology of China Initiative Foundation

摘　　要：In the forward channel of a networked control system （NCS）, by defining the network states as a hidden Markov chain and quantizing the network-induced delays to a discrete sequence distributing over a finite time interval, the relation between the network states and the network-induced delays is modelled as a discrete-time hidden Markov model （DTHMM）. The expectation maximization （EM） algorithm is introduced to derive the maximumlikelihood estimation （MLE） of the parameters of the DTHMM. Based on the derived DTHMM, the Viterbi algorithm is introduced to predict the controller-to-actuator （C-A） delay during the current sampling period. The simulation experiments demonstrate the effectiveness of the modelling and predicting methods proposed.In the forward channel of a networked control system （NCS）, by defining the network states as a hidden Markov chain and quantizing the network-induced delays to a discrete sequence distributing over a finite time interval, the relation between the network states and the network-induced delays is modelled as a discrete-time hidden Markov model （DTHMM）. The expectation maximization （EM） algorithm is introduced to derive the maximumlikelihood estimation （MLE） of the parameters of the DTHMM. Based on the derived DTHMM, the Viterbi algorithm is introduced to predict the controller-to-actuator （C-A） delay during the current sampling period. The simulation experiments demonstrate the effectiveness of the modelling and predicting methods proposed.

关 键 词：networked control system discrete-time hidden Markov model network state delay prediction. 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置] TP391.41[自动化与计算机技术—控制科学与工程]