A Machine Learning Model for Procurement of Secondary Reserve Capacity in Power Systems with Significant vRES Penetrations

João Passagem dos Santos () and Hugo Algarvio ()
Additional contact information
João Passagem dos Santos: Department of Geographic Engineering, Geophysics and Energy, Faculty of Sciences, University of Lisbon, Campo Grande, 1749-016 Lisbon, Portugal
Hugo Algarvio: LNEG—National Laboratory of Energy and Geology, Est. Paço Lumiar 22, 1649-038 Lisbon, Portugal

Energies, 2025, vol. 18, issue 6, 1-19

Abstract: The growing investment in variable renewable energy sources is changing how electricity markets operate. In Europe, players rely on forecasts to participate in day-ahead markets closing between 12 and 37 h ahead of real-time operation. Usually, transmission system operators use a symmetrical procurement of up and down secondary power reserves based on the expected demand. This work uses machine learning techniques that dynamically compute it using the day-ahead programmed and expected dispatches of variable renewable energy sources, demand, and other technologies. Specifically, the methodology incorporates neural networks, such as Long Short-Term Memory (LSTM) or Convolutional neural network (CNN) models, to improve forecasting accuracy by capturing temporal dependencies and nonlinear patterns in the data. This study uses operational open data from the Spanish operator from 2014 to 2023 for training. Benchmark and test data are from the year 2024. Different machine learning architectures have been tested, but a Fully Connected Neural Network (FCNN) has the best results. The proposed methodology improves the usage of the up and down secondary reserved power by almost 22% and 11%, respectively.

Keywords: energy markets; forecast; machine learning; neural networks; reserve systems; secondary capacity; variable renewable (search for similar items in EconPapers)
JEL-codes: Q Q0 Q4 Q40 Q41 Q42 Q43 Q47 Q48 Q49 (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/1996-1073/18/6/1467/pdf (application/pdf)
https://www.mdpi.com/1996-1073/18/6/1467/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jeners:v:18:y:2025:i:6:p:1467-:d:1614010

Access Statistics for this article

Energies is currently edited by Ms. Agatha Cao

More articles in Energies from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().