EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Application of AI for Short-Term PV Generation Forecast

Helder R O Rocha iD, Rodrigo Fiorotti iD, Jussara F Fardin iD, Hilel Garcia-Pereira iD, Yann E Bouvier iD, Alba Rodríguez-Lorente iD, Imene Yahyaoui iD

Sensors · 23.12.2023 · 24 (1) · 85

DOI: 10.3390/s24010085 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 23.12.2023. Verfasst von Helder R O Rocha und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electrical Engineering, Federal University of Espírito Santo, Av. Fernando Ferrari, 514, Vitória 29075-910, ES, Brazil. Die Arbeit wurde bisher 23-mal zitiert (Crossref) und nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: King Juan Carlos University, CNPq, FAPES.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The efficient use of the photovoltaic power requires a good estimation of the PV generation. That is why the use of good techniques for forecast is necessary. In this research paper, Long Short-Term Memory, Bidirectional Long Short-Term Memory and the Temporal convolutional network are studied in depth to forecast the photovoltaic power, voltage and efficiency of a 1320 Wp amorphous plant installed in the Technology Support Centre in the University Rey Juan Carlos, Madrid (Spain). The accuracy of these techniques are compared using experimental data along one year, applying 1 timestep or 15 min and 96 step times or 24 h, showing that TCN exhibits outstanding performance, compared with the two other techniques. For instance, it presents better results in all forecast variables and both forecast horizons, achieving an overall Mean Squared Error (MSE) of 0.0024 for 15 min forecasts and 0.0058 for 24 h forecasts. In addition, the sensitivity analyses for the TCN technique is performed and shows that the accuracy is reduced as the forecast horizon increases and that the 6 months of dataset is sufficient to obtain an adequate result with an MSE value of 0.0080 and a coefficient of determination of 0.90 in the worst scenarios (24 h of forecast).

Schlagwörter

Stichwörter der Autor:innen

BILSTMLSTMTCNartificial intelligencephotovoltaic powershort-term forecast

Autor:innen und Institutionen

  • Department of Electrical Engineering, Federal University of Espírito Santo, Av. Fernando Ferrari, 514, Vitória 29075-910, ES, Brazil.
  • Department of Electrical Engineering, Federal Institute of Espírito Santo, São Mateus 29932-540, ES, Brazil.
  • Higher School of Experimental Sciences and Technology, University of Rey Juan Carlos, 28933 Madrid, Spain.

ORCID-Profile: Helder R O Rocha, Rodrigo Fiorotti, Jussara F Fardin, Hilel Garcia-Pereira, Yann E Bouvier, Alba Rodríguez-Lorente, Imene Yahyaoui

Förderung

  • King Juan Carlos University
  • CNPq
  • FAPES
  • NiDA Project
  • university Rey Juan Carlos (Spain)
  • CNPq 309737/2021-4
  • FAPES-2021-WMR44
  • FAPES-2022-BWBR2

Zitieren

APA

Rocha, H. R. O., Fiorotti, R., Fardin, J. F., Garcia-Pereira, H., Bouvier, Y. E., Rodríguez-Lorente, A., & Yahyaoui, I. (2023). Application of AI for Short-Term PV Generation Forecast. Sensors, 24(1), 85. https://doi.org/10.3390/s24010085

Vancouver

Rocha HRO, Fiorotti R, Fardin JF, Garcia-Pereira H, Bouvier YE, Rodríguez-Lorente A, et al. Application of AI for Short-Term PV Generation Forecast. Sensors. 2023;24(1):85. doi:10.3390/s24010085

BibTeX
@article{Rocha2023,
  author = {Rocha, Helder R O and Fiorotti, Rodrigo and Fardin, Jussara F and Garcia-Pereira, Hilel and Bouvier, Yann E and Rodríguez-Lorente, Alba and Yahyaoui, Imene},
  title = {Application of AI for Short-Term PV Generation Forecast},
  journal = {Sensors},
  year = {2023},
  volume = {24},
  number = {1},
  pages = {85},
  doi = {10.3390/s24010085}
}
Kostenlos starten →