A reliable and accurate forecasting model is one of the most effective solutions to deal with the problem of renewable energy sources integration. In this paper, a model for the medium-long-term wind speed prediction, based on spatiotemporal evolution of weather fronts and Multi-Layer Perceptron Neural Network (MLP NN) data mining model, is developed. The model inputs are the historical and current meteorological data, such as pressure, temperature and wind intensity. These data describe the evolution of the weather fronts in a wide area around the point of interest, which goes beyond the local bounds. The model, trained and tested using real weather data, predicts the 24-h ahead wind speed. Forecasted results are compared with real data registered in the test site. This comparison demonstrates the efficiency and the effectiveness of the proposed strategy.

A Day-ahead Wind Speed Prediction based on Meteorological Data and the Seasonality of Weather Fronts

Finamore A.;Calderaro V.
;
Galdi V.;Piccolo A.;
2019-01-01

Abstract

A reliable and accurate forecasting model is one of the most effective solutions to deal with the problem of renewable energy sources integration. In this paper, a model for the medium-long-term wind speed prediction, based on spatiotemporal evolution of weather fronts and Multi-Layer Perceptron Neural Network (MLP NN) data mining model, is developed. The model inputs are the historical and current meteorological data, such as pressure, temperature and wind intensity. These data describe the evolution of the weather fronts in a wide area around the point of interest, which goes beyond the local bounds. The model, trained and tested using real weather data, predicts the 24-h ahead wind speed. Forecasted results are compared with real data registered in the test site. This comparison demonstrates the efficiency and the effectiveness of the proposed strategy.
2019
978-1-5386-7434-5
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11386/4747010
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 6
  • ???jsp.display-item.citation.isi??? 5
social impact