Model predictive control (MPC) is an enabling technology in applications requiring controlling physical processes in an optimized way under constraints on inputs and outputs. However, in MPC closed-loop performance is pushed to the limits only if the plant under control is accurately modeled; otherwise, robust architectures need to be employed, at the price of reduced performance due to worst-case conservative assumptions. In this letter, instead of adapting the controller to handle uncertainty, we adapt the learning procedure so that the prediction model is selected to provide the best closed-loop performance. More specifically, we apply for the first time the above 'identification for control' rationale to hierarchical MPC using data-driven methods and Bayesian optimization.

Performance-oriented model learning for data-driven mpc design

Bemporad A.
2019-01-01

Abstract

Model predictive control (MPC) is an enabling technology in applications requiring controlling physical processes in an optimized way under constraints on inputs and outputs. However, in MPC closed-loop performance is pushed to the limits only if the plant under control is accurately modeled; otherwise, robust architectures need to be employed, at the price of reduced performance due to worst-case conservative assumptions. In this letter, instead of adapting the controller to handle uncertainty, we adapt the learning procedure so that the prediction model is selected to provide the best closed-loop performance. More specifically, we apply for the first time the above 'identification for control' rationale to hierarchical MPC using data-driven methods and Bayesian optimization.
2019
identification for control; machine learning; Predictive control for nonlinear systems
File in questo prodotto:
File Dimensione Formato  
1904.10839.pdf

accesso aperto

Tipologia: Documento in Pre-print
Licenza: Creative commons
Dimensione 454.39 kB
Formato Adobe PDF
454.39 kB Adobe PDF Visualizza/Apri
08698829.pdf

non disponibili

Tipologia: Versione Editoriale (PDF)
Licenza: Nessuna licenza
Dimensione 564.88 kB
Formato Adobe PDF
564.88 kB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.11771/13285
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 85
social impact