An analysis of different deep learning neural networks for intra-hour solar irradiation forecasting to compute solar photovoltaic generators' energy production

Renewable energies are the alternative that leads to a cleaner generation and a reduction in CO2 emissions. However, their dependency on weather makes them unreliable. Traditional energy operators need a highly accurate estimation of energy to ensure the appropriate control of the network, since ene...

Descripción completa

Detalles Bibliográficos
Autores: Etxegarai, G. (Garazi)|||/items/ecafc318-31cc-4f30-a2e6-75c4b401f3e3, López, A. (Andrés)|||/items/9f70b953-8d32-406c-b007-2fce2e8e1df5, Aginako, N. (Naiara)|||/items/d61a4042-661c-4544-8c53-5676f455ec3b, Rodríguez, F. (Fermín)|||/items/99068aae-e6c7-4106-9d20-0528327fa474
Tipo de recurso: artículo
Fecha de publicación:2022
País:España
Institución:Universidad de Navarra
Repositorio:Dadun. Depósito Académico Digital de la Universidad de Navarra
Idioma:inglés
OAI Identifier:oai:dadun.unav.edu:10171/63742
Acceso en línea:https://hdl.handle.net/10171/63742
Access Level:acceso abierto
Palabra clave:Solar irradiation forecasting
Artificial neural network
Very short-term forecasting
Long short term memory
Convolutional neural network
Descripción
Sumario:Renewable energies are the alternative that leads to a cleaner generation and a reduction in CO2 emissions. However, their dependency on weather makes them unreliable. Traditional energy operators need a highly accurate estimation of energy to ensure the appropriate control of the network, since energy generation and demand must be balanced. This paper proposes a forecaster to predict solar irradiation, for very short-term, specifically, in the 10 min ahead. This study develops two tools based on artificial neural networks, namely Long-Short Term Memory neural networks and Convolutional Neural Network. The results demonstrate that the Convolutional Neural Network has a higher accuracy. The tool is tested examining the root mean square error, which was of 52.58 W/m2 for the testing step. Compared against the benchmark, it has obtained an improvement of 8.16%. Additionally, for the 82% of the tested days it has given a less than 4% error between the predicted and the actual energy generation. Results indicate that the forecaster is accurate enough to be implemented on a photovoltaic generation plan, improving their integration into the electrical grid, not only for providing power but also ancillary services.