Learning and Control Using Gaussian Processes

Achin Jain, Truong Nghiem, Manfred Morari, Rahul Mangharam

Research output: Chapter in Book/Report/Conference proceedingConference contribution

50 Scopus citations

Abstract

Building physics-based models of complex physical systems like buildings and chemical plants is extremely cost and time prohibitive for applications such as real-time optimal control, production planning and supply chain logistics. Machine learning algorithms can reduce this cost and time complexity, and are, consequently, more scalable for large-scale physical systems. However, there are many practical challenges that must be addressed before employing machine learning for closed-loop control. This paper proposes the use of Gaussian Processes (GP) for learning control-oriented models: (1) We develop methods for the optimal experiment design (OED) of functional tests to learn models of a physical system, subject to stringent operational constraints and limited availability of the system. Using a Bayesian approach with GP, our methods seek to select the most informative data for optimally updating an existing model. (2) We also show that black-box GP models can be used for receding horizon optimal control with probabilistic guarantees on constraint satisfaction through chance constraints. (3) We further propose an online method for continuously improving the GP model in closed-loop with a real-time controller. Our methods are demonstrated and validated in a case study of building energy control and Demand Response.

Original languageEnglish (US)
Title of host publicationProceedings - 9th ACM/IEEE International Conference on Cyber-Physical Systems, ICCPS 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages140-149
Number of pages10
ISBN (Print)9781538653012
DOIs
StatePublished - Aug 21 2018
Event9th ACM/IEEE International Conference on Cyber-Physical Systems, ICCPS 2018 - Porto, Portugal
Duration: Apr 11 2018Apr 13 2018

Publication series

NameProceedings - 9th ACM/IEEE International Conference on Cyber-Physical Systems, ICCPS 2018

Conference

Conference9th ACM/IEEE International Conference on Cyber-Physical Systems, ICCPS 2018
Country/TerritoryPortugal
CityPorto
Period4/11/184/13/18

Keywords

  • active learning
  • Gaussian Processes
  • Machine learning
  • optimal experiment design
  • receding horizon control

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Control and Optimization

Fingerprint

Dive into the research topics of 'Learning and Control Using Gaussian Processes'. Together they form a unique fingerprint.

Cite this