Learning-based hierarchical control of water reservoir systems
(2022) In IFAC Journal of Systems and Control 19.- Abstract
The optimal control of a water reservoir system represents a challenging problem, due to uncertain hydrologic inputs and the need to adapt to changing environment and varying control objectives. In this work, we propose a real-time learning-based control strategy based on a hierarchical predictive control architecture. Two control loops are implemented: the inner loop is aimed to make the overall dynamics similar to an assigned linear model through data-driven control design, then the outer economic model-predictive controller compensates for model mismatches, enforces suitable constraints, and boosts the tracking performance. The effectiveness of the proposed approach is illustrated on an accurate simulator of the Hoa Binh reservoir in... (More)
The optimal control of a water reservoir system represents a challenging problem, due to uncertain hydrologic inputs and the need to adapt to changing environment and varying control objectives. In this work, we propose a real-time learning-based control strategy based on a hierarchical predictive control architecture. Two control loops are implemented: the inner loop is aimed to make the overall dynamics similar to an assigned linear model through data-driven control design, then the outer economic model-predictive controller compensates for model mismatches, enforces suitable constraints, and boosts the tracking performance. The effectiveness of the proposed approach is illustrated on an accurate simulator of the Hoa Binh reservoir in Vietnam. Results show that the proposed approach outperforms stochastic dynamic programming.
(Less)
- author
- Kergus, Pauline LU ; Formentin, Simone ; Giuliani, Matteo and Castelletti, Andrea
- organization
- publishing date
- 2022
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- Constrained control, Control application, Data-driven control, Predictive control, Water reservoir
- in
- IFAC Journal of Systems and Control
- volume
- 19
- article number
- 100185
- publisher
- Elsevier
- external identifiers
-
- scopus:85123921695
- ISSN
- 2468-6018
- DOI
- 10.1016/j.ifacsc.2022.100185
- project
- Scalable Control of Interconnected Systems
- language
- English
- LU publication?
- yes
- id
- e93103a8-6c00-4f8f-bc8d-871d5148c0be
- date added to LUP
- 2022-04-06 15:03:23
- date last changed
- 2022-05-11 12:57:07
@article{e93103a8-6c00-4f8f-bc8d-871d5148c0be,
abstract = {{<p>The optimal control of a water reservoir system represents a challenging problem, due to uncertain hydrologic inputs and the need to adapt to changing environment and varying control objectives. In this work, we propose a real-time learning-based control strategy based on a hierarchical predictive control architecture. Two control loops are implemented: the inner loop is aimed to make the overall dynamics similar to an assigned linear model through data-driven control design, then the outer economic model-predictive controller compensates for model mismatches, enforces suitable constraints, and boosts the tracking performance. The effectiveness of the proposed approach is illustrated on an accurate simulator of the Hoa Binh reservoir in Vietnam. Results show that the proposed approach outperforms stochastic dynamic programming.</p>}},
author = {{Kergus, Pauline and Formentin, Simone and Giuliani, Matteo and Castelletti, Andrea}},
issn = {{2468-6018}},
keywords = {{Constrained control; Control application; Data-driven control; Predictive control; Water reservoir}},
language = {{eng}},
publisher = {{Elsevier}},
series = {{IFAC Journal of Systems and Control}},
title = {{Learning-based hierarchical control of water reservoir systems}},
url = {{http://dx.doi.org/10.1016/j.ifacsc.2022.100185}},
doi = {{10.1016/j.ifacsc.2022.100185}},
volume = {{19}},
year = {{2022}},
}