Deep learning approaches for predicting the upward and downward energy prices in the Spanish automatic Frequency Restoration Reserve market

Johanna M. Failing, Javier Cardo-Miota, Emilio Pérez, Hector Beltran and Jorge Segarra-Tamarit

Energy, 2025, vol. 320, issue C

Abstract: The integration of renewable energy sources (RES) into power systems presents significant challenges due to their inherent variability and stochastic nature. This has led to an increased reliance on Ancillary Services (ASs), particularly frequency regulation, to maintain grid stability. The automatic Frequency Restoration Reserve (aFRR) service is critical in addressing real-time imbalances in power systems. This paper introduces a detailed study of the Spanish frequency regulation markets and focuses on forecasting energy prices in the Spanish aFRR market using deep learning techniques. Specifically, three models — Feedforward Neural Networks (FNN), Convolutional Neural Networks (CNN), and Long short-term memory (LSTM) – are employed to predict upward and downward aFRR energy prices. The study evaluates the effectiveness of these models using time series data from the Spanish power system and several performance metrics such as MAE and RMSE. A correlation study and a Sequential Backward Selection algorithm are proposed to select the inputs for each model. The results demonstrate the superiority of feedforward models for upward price forecasting, while convolutional models perform better for downward prices. These findings provide valuable insights for service providers aiming to optimize their bidding strategies in the Spanish aFRR market.

Keywords: Electricity price forecasting; Ancillary services; aFRR service; Energy markets; Neural networks; Deep learning (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0360544225008874
Full text for ScienceDirect subscribers only

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:eee:energy:v:320:y:2025:i:c:s0360544225008874

DOI: 10.1016/j.energy.2025.135245

Access Statistics for this article

Energy is currently edited by Henrik Lund and Mark J. Kaiser

More articles in Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().