DocumentCode :
3096588
Title :
Scheduling strategy based on BP neural network and fuzzy feedback in networked control system
Author :
Pan, Wei-hua ; Han, Pu ; Zhang, Li-jing ; Wang, Tian-kun
Author_Institution :
Inf. & Network Manage. Center, North China Electr. Power Univ., Baoding, China
Volume :
2
fYear :
2009
fDate :
12-15 July 2009
Firstpage :
806
Lastpage :
810
Abstract :
For the performance of networked control system is limited to the network resources and compute resources, the scheduling strategy is the key factor. This paper proposed two level schedule strategy: First, the controller and sensor nodes can be configured as event-time hybrid driven mode to improve the utilization rate. Then, considering the error and error difference response, a BP neural network and fuzzy feedback scheduler that shares communication net is designed with the bandwidth constraints. Two different scheduling algorithms with stochastic delay are compared with respectively. Finally, the results of simulation highlights that proposed scheduling strategy can optimize the performance of control loop and is more flexible than the other algorithms in uncertain running conditions.
Keywords :
backpropagation; control engineering computing; feedback; fuzzy control; fuzzy set theory; neurocontrollers; scheduling; sensors; BP neural network; bandwidth constraint; communication net; error difference response; event-time hybrid driven mode; fuzzy feedback scheduler; network resource; networked control system; scheduling strategy; sensor node; stochastic delay; utilization rate; Communication system control; Computer networks; Fuzzy control; Fuzzy neural networks; Fuzzy systems; Networked control systems; Neural networks; Neurofeedback; Processor scheduling; Scheduling algorithm; BP neural network; Event-time driven; Fuzzy feedback; Information scheduling; Networked control system;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Machine Learning and Cybernetics, 2009 International Conference on
Conference_Location :
Baoding
Print_ISBN :
978-1-4244-3702-3
Electronic_ISBN :
978-1-4244-3703-0
Type :
conf
DOI :
10.1109/ICMLC.2009.5212460
Filename :
5212460
Link To Document :
بازگشت