On the impact of regularization in data-driven predictive control
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916172609355776 |
|---|---|
| author | Breschi, Valentina Chiuso, Alessandro Fabris, Marco Formentin, Simone |
| author_facet | Breschi, Valentina Chiuso, Alessandro Fabris, Marco Formentin, Simone |
| contents | Model predictive control (MPC) is a control strategy widely used in industrial applications. However, its implementation typically requires a mathematical model of the system being controlled, which can be a time-consuming and expensive task. Data-driven predictive control (DDPC) methods offer an alternative approach that does not require an explicit mathematical model, but instead optimize the control policy directly from data. In this paper, we study the impact of two different regularization penalties on the closed-loop performance of a recently introduced data-driven method called $γ$-DDPC. Moreover, we discuss the tuning of the related coefficients in different data and noise scenarios, to provide some guidelines for the end user. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2304_00263 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | On the impact of regularization in data-driven predictive control Breschi, Valentina Chiuso, Alessandro Fabris, Marco Formentin, Simone Systems and Control Model predictive control (MPC) is a control strategy widely used in industrial applications. However, its implementation typically requires a mathematical model of the system being controlled, which can be a time-consuming and expensive task. Data-driven predictive control (DDPC) methods offer an alternative approach that does not require an explicit mathematical model, but instead optimize the control policy directly from data. In this paper, we study the impact of two different regularization penalties on the closed-loop performance of a recently introduced data-driven method called $γ$-DDPC. Moreover, we discuss the tuning of the related coefficients in different data and noise scenarios, to provide some guidelines for the end user. |
| title | On the impact of regularization in data-driven predictive control |
| topic | Systems and Control |
| url | https://arxiv.org/abs/2304.00263 |