Open AccessSupervisory output prediction for bilinear systems by reinforcement learning
Author(s) -
Chasparis Georgios C.,
Natschläger Thomas
Publication year - 2017
Publication title -
iet control theory and applications
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.059
H-Index - 108
eISSN - 1751-8652
pISSN - 1751-8644
DOI - 10.1049/iet-cta.2016.1400
Subject(s) - bilinear interpolation , reinforcement learning , computer science , process (computing) , scheme (mathematics) , supervisory control , partition (number theory) , control theory (sociology) , model predictive control , control engineering , artificial intelligence , control (management) , engineering , mathematics , mathematical analysis , combinatorics , computer vision , operating system
Online output prediction is an indispensable part of any model predictive control implementation. For several application scenarios, operating conditions may change quite often, while designing the data collection process may not be an option. To this end, this study introduces a supervisory output prediction scheme, tailored specifically for input–output stable bilinear systems, that intends on automating the process of selecting the most appropriate prediction model during runtime. The selection process is based upon a reinforcement‐learning scheme, where prediction models are selected according to their prior prediction performance. An additional selection process is concerned with appropriately partitioning the control‐inputs' domain also to allow for switched‐system approximations of the original bilinear dynamics. The authors show analytically that the proposed scheme converges (in probability) to the best model and partition. They also demonstrate these properties through simulations of temperature prediction in residential buildings.