Machine Learning Applied to the Operation of Fully Renewable Energy Systems

This work presents a novel learning algorithm for the operation policy of power systems trying to minimize the cost of fulfilling the energy demand. The algorithm improves upon the classical reinforcement learning methods by controlling the sampling variance in the estimation of the future cost spat...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:2023 IEEE PES GTD International Conference and Exposition (GTD) S. 139 - 143
Hauptverfasser: Chaer, Ruben, Ramirez, Ignacio, Casaravilla, Gonzalo
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 01.05.2023
Schlagworte:
Approximate Stochastic Dynamic Programming
Costs
Heuristic algorithms
Lakes
Power system dynamics
Reinforcement learning
Reinforcement Machine Learning
Renewable Energies
Solar energy
Stochastic processes
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:This work presents a novel learning algorithm for the operation policy of power systems trying to minimize the cost of fulfilling the energy demand. The algorithm improves upon the classical reinforcement learning methods by controlling the sampling variance in the estimation of the future cost spatial differences, together with parameter regularization and dynamic exploring techniques. The proposed strategy was applied to a case of what could be the power system of Uruguay by 2050 based strongly in hydro, wind and solar energies, including three lakes, four groups of battery banks, and the basin runoff of the two main Uruguayan rivers. The generation in the year 2022 in Uruguay was 43% hydraulic, 40% wind plus solar, 7% biomass and 10% based on fossil fuels. This composition prints a very relevant stochastic component that makes it difficult to apply machine learning techniques without the kind of algorihms proposed in this work.
DOI:10.1109/GTD49768.2023.00053