Energy shortage failure prediction in photovoltaic standalone installations by using machine learning techniques

Guillen Asensio, A. ; Sanz Gorrachategui, I. ; Bono Nuez, A. ; Bernal, C. ; Sanz Alcaine, J. M. ; Pérez Cebolla, F. J.

Resumen: The use of energy storage systems in standalone photovoltaic installations is essential to supply energy demands, independently of solar generation. Accurate prediction of the battery state is critical for the safe, durable, and reliable operation of systems in this type of installations. In this study, an installation located in the area of Aragon (Spain) has been considered. Two methods, based on different types of Recurrent Neural Networks (RNN), are proposed to predict the battery voltage of the installation two days ahead. Specifically, the Nonlinear Auto Regressive with Exogenous Input (NARX) network and the Long Short-Term Memory (LSTM) network are studied and compared. The implemented algorithms process battery voltage, temperature and current waveforms; and rely on the selection of different future scenarios based on weather forecasting to estimate the future voltage of the battery. The proposed methodology is capable of predicting the voltage with a Root Mean Squared Error (RMSE) error of 1.2 V for batteries of 48 V, in critical situations where the installation is running out of energy. The study contributes to the ongoing research of developing preventive control systems that help reduce costs and improve the performance of remote energy storage systems based on renewable energies with a positive outcome.

Idioma: Inglés

DOI: 10.1109/ACCESS.2021.3129930

Año: 2021

Publicado en: IEEE Access 9 (2021), 128660-128671
ISSN: 2169-3536

Factor impacto JCR: 3.476 (2021)

Categ. JCR: COMPUTER SCIENCE, INFORMATION SYSTEMS rank: 79 / 164 = 0.482 (2021) - Q2 - T2
Categ. JCR: TELECOMMUNICATIONS rank: 43 / 93 = 0.462 (2021) - Q2 - T2
Categ. JCR: ENGINEERING, ELECTRICAL & ELECTRONIC rank: 105 / 277 = 0.379 (2021) - Q2 - T2

Factor impacto CITESCORE: 6.7 - Engineering (Q1) - Computer Science (Q1) - Materials Science (Q1)

Factor impacto SCIMAGO: 0.927 - Computer Science (miscellaneous) (Q1) - Engineering (miscellaneous) (Q1)

Tipo y forma: Artículo (Versión definitiva)