Title :
Tree-based variable selection for dimensionality reduction of large-scale control systems
Author :
Castelletti, Andrea ; Galelli, Stefano ; Restelli, Marcello ; Soncini-Sessa, Rodolfo
Author_Institution :
Dept. of Electron. & Inf., Politec. di Milano, Milan, Italy
Abstract :
This paper is about dimensionality reduction by variable selection in high-dimensional real-world control problems, where designing controllers by conventional means is either impractical or results in poor performance.
Keywords :
hydrodynamics; large-scale systems; mobile robots; nonlinear control systems; pendulums; reduced order systems; set theory; trees (mathematics); wheels; Tono Dam; control variable; coupled 1D hydrodynamic-ecological model; dimensionality reduction; disturbance variables; large-scale control system; model-free variable selection approach; nonlinear dependencies; one-step state transition; ranking algorithm; real-world control problem; recursive variable selection algorithm; state variable; state variables; statistical measure; tree based variable selection; two-wheeled inverted pendulum robot; Aerospace electronics; Computational modeling; Control systems; Estimation; Heuristic algorithms; Input variables; Mathematical model;
Conference_Titel :
Adaptive Dynamic Programming And Reinforcement Learning (ADPRL), 2011 IEEE Symposium on
Conference_Location :
Paris
Print_ISBN :
978-1-4244-9887-1
DOI :
10.1109/ADPRL.2011.5967387