Multi-fidelity optimization for the day-ahead scheduling of Pumped Hydro Energy Storage

Optimizing the operation of Pumped-Hydro Energy Storage (PHES) requires accurately representing nonlinearities, such as reservoir geometry and water-power conversion efficiency. While traditional methods like Mixed-Integer Linear Programming (MILP) offer theoretical guarantees, they rely on approxim...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Journal of energy storage Jg. 103; S. 114096
Hauptverfasser: Favaro, Pietro, Gobert, Maxime, Toubeau, Jean-François
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier Ltd 01.12.2024
Elsevier
Schlagworte:
Computer Science
Electricity markets
Engineering Sciences
Machine Learning
Mixed-integer linear programming
Multi-fidelity optimization
Operations Research
Pumped hydro energy storage
Statistics
Surrogate-based optimization algorithms
Multi-fidelity optimization
90C26
Pumped hydro energy storage
Surrogate-based optimization algorithms
Electricity markets
Mixed-integer linear programming
ISSN:2352-152X, 2352-1538
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Optimizing the operation of Pumped-Hydro Energy Storage (PHES) requires accurately representing nonlinearities, such as reservoir geometry and water-power conversion efficiency. While traditional methods like Mixed-Integer Linear Programming (MILP) offer theoretical guarantees, they rely on approximations that can lead to suboptimal decisions and costly redispatch or penalties. Because of its inherent approximations, MILP is a low-fidelity optimization model. In this paper, we propose a multi-fidelity approach that combines MILP with a Surrogate-Based Optimization Algorithm (SBOA). MILP solutions are used as warm-starts for the SBOA, which refines the solutions using a high-fidelity simulator of PHES dynamics and redispatch costs. This allows the SBOA to handle nonlinearities and improve the initial MILP solution by exploring areas with higher expected value. Our approach is tested on a PHES unit that participates in the energy and reserve markets in Belgium. The results show that, despite the extensive efforts made in MILP modeling, decisions can still be improved through smart integration with SBOAs. •Exact optimization is augmented with global search methods.•The method is applied to the scheduling of Pumped Hydro Energy Storage.•MILP’s fast results are used as warm-start for higher-fidelity optimization search.•We find the best trade-off regarding the resources allocated to each method.•Multi-fidelity can strongly reduce the gap between ex-ante and ex-post profits.
ISSN:2352-152X
2352-1538
DOI:10.1016/j.est.2024.114096