Using Deep Learning in Forecasting the Production of Electricity from Photovoltaic and Wind Farms

Michał Pikus (), Jarosław Wąs and Agata Kozina
Additional contact information
Michał Pikus: Department of Applied Computer Science, Computer Science and Biomedical Engineering, Faculty of Electrical Engineering, Automatics, AGH University of Krakow, al. Mickiewicza 30, 30-059 Krakow, Poland
Jarosław Wąs: Department of Applied Computer Science, Computer Science and Biomedical Engineering, Faculty of Electrical Engineering, Automatics, AGH University of Krakow, al. Mickiewicza 30, 30-059 Krakow, Poland
Agata Kozina: Department of Process Management, Wroclaw University of Economics and Business, Komandorska 118/120, 53-545 Wroclaw, Poland

Energies, 2025, vol. 18, issue 15, 1-30

Abstract: Accurate forecasting of electricity production is crucial for the stability of the entire energy sector. However, predicting future renewable energy production and its value is difficult due to the complex processes that affect production using renewable energy sources. In this article, we examine the performance of basic deep learning models for electricity forecasting. We designed deep learning models, including recursive neural networks (RNNs), which are mainly based on long short-term memory (LSTM) networks; gated recurrent units (GRUs), convolutional neural networks (CNNs), temporal fusion transforms (TFTs), and combined architectures. In order to achieve this goal, we have created our benchmarks and used tools that automatically select network architectures and parameters. Data were obtained as part of the NCBR grant (the National Center for Research and Development, Poland). These data contain daily records of all the recorded parameters from individual solar and wind farms over the past three years. The experimental results indicate that the LSTM models significantly outperformed the other models in terms of forecasting. In this paper, multilayer deep neural network (DNN) architectures are described, and the results are provided for all the methods. This publication is based on the results obtained within the framework of the research and development project “POIR.01.01.01-00-0506/21”, realized in the years 2022–2023. The project was co-financed by the European Union under the Smart Growth Operational Programme 2014–2020.

Keywords: forecasting; DNN; renewable energy (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/1996-1073/18/15/3913/pdf (application/pdf)
https://www.mdpi.com/1996-1073/18/15/3913/ (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:15:p:3913-:d:1707590

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 ().