Stochastic model predictive control of Markov jump linear systems based on a two-layer recurrent neural network

Publication Type:
Conference Proceeding
2013 IEEE International Conference on Information and Automation, ICIA 2013, 2013, pp. 564 - 569
Issue Date:
Filename Description Size
06720361.pdfPublished version444.26 kB
Adobe PDF
Full metadata record
This paper presents a stochastic model predictive control approach to constrained Markov jump linear systems based on neurodynamic optimization. The stochastic model predictive control problem is formulated as a nonlinear convex optimization problem, which is iteratively solved by using a two-layer recurrent neural network in real-time. The applied neural network can globally converge to the exact optimal solution of the optimization problem. Simulation results are provided to demonstrate the effectiveness and characteristics of the proposed approach. © 2013 IEEE.
Please use this identifier to cite or link to this item: