Deep Reinforcement Learning for Intraday Multireservoir Hydropower Management
Mathematics · 03.01.2025 · 13 (1) · 151
DOI: 10.3390/math13010151 ↗Kurz gefasst
Fachartikel in der Zeitschrift Mathematics, online erschienen am 03.01.2025. Verfasst von Rodrigo Castro-Freibott und 3 weiteren Autor:innen. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Recovery, Transformation, and Resilience Plan, Ministerio de Ciencia e Innovación of Spain, ERDF A way of making Europe.
Abstract (Originalsprache)
This study investigates the application of Reinforcement Learning (RL) to optimize intraday operations of hydropower reservoirs. Unlike previous approaches that focus on long-term planning with coarse temporal resolutions and discretized state-action spaces, we propose an RL framework tailored to the Hydropower Reservoirs Intraday Economic Optimization problem. This framework manages continuous state-action spaces while accounting for fine-grained temporal dynamics, including dam-to-turbine delays, gate movement constraints, and power group operations. Our methodology evaluates three distinct action space formulations (continuous, discrete, and adjustments) implemented using modern RL algorithms (A2C, PPO, and SAC). We compare them against both a greedy baseline and Mixed-Integer Linear Programming (MILP) solutions. Experiments on real-world data from a two-reservoir system and a simulated six-reservoir system demonstrate that while MILP achieves superior performance in the smaller system, its performance degrades significantly when scaled to six reservoirs. In contrast, RL agents, particularly those using discrete action spaces and trained with PPO, maintain consistent performance across both configurations, achieving considerable improvements with less than one second of execution time. These results suggest that RL offers a scalable alternative to traditional optimization methods for hydropower operations, particularly in scenarios requiring real-time decision making or involving larger systems.
Förderung
- Recovery, Transformation, and Resilience Plan
- Ministerio de Ciencia e Innovación of Spain
- ERDF A way of making Europe
Zitieren
APA
Castro-Freibott, R., García-Sánchez, Á., Espiga-Fernández, F., & Cruz, G. G. D. L. (2025). Deep Reinforcement Learning for Intraday Multireservoir Hydropower Management. Mathematics, 13(1), 151. https://doi.org/10.3390/math13010151
Vancouver
Castro-Freibott R, García-Sánchez Á, Espiga-Fernández F, Cruz GGDL. Deep Reinforcement Learning for Intraday Multireservoir Hydropower Management. Mathematics. 2025;13(1):151. doi:10.3390/math13010151
BibTeX
@article{CastroFreibott2025,
author = {Castro-Freibott, Rodrigo and García-Sánchez, Álvaro and Espiga-Fernández, Francisco and Cruz, Guillermo González-Santander de la},
title = {Deep Reinforcement Learning for Intraday Multireservoir Hydropower Management},
journal = {Mathematics},
year = {2025},
volume = {13},
number = {1},
pages = {151},
doi = {10.3390/math13010151}
}
EUVIMED