IDEAS home Printed from https://ideas.repec.org/a/eee/energy/v320y2025ics0360544225008874.html
   My bibliography  Save this article

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

Author

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

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.

Suggested Citation

  • Failing, Johanna M. & Cardo-Miota, Javier & Pérez, Emilio & Beltran, Hector & Segarra-Tamarit, Jorge, 2025. "Deep learning approaches for predicting the upward and downward energy prices in the Spanish automatic Frequency Restoration Reserve market," Energy, Elsevier, vol. 320(C).
  • Handle: RePEc:eee:energy:v:320:y:2025:i:c:s0360544225008874
    DOI: 10.1016/j.energy.2025.135245
    as

    Download full text from publisher

    File URL: http://www.sciencedirect.com/science/article/pii/S0360544225008874
    Download Restriction: Full text for ScienceDirect subscribers only

    File URL: https://libkey.io/10.1016/j.energy.2025.135245?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    As the access to this document is restricted, you may want to search for a different version of it.

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:eee:energy:v:320:y:2025:i:c:s0360544225008874. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    We have no bibliographic references for this item. You can help adding them by using this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Catherine Liu (email available below). General contact details of provider: http://www.journals.elsevier.com/energy .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.