This paper investigates the methods to mitigate the impact of variable renewable energy sources (RES), like the wind, in power system focusing on the problem of the power production forecasting. In particular, the implementation of data mining approach for to solve the wind forecasting problem is proposed, starting from the study of the physics and of the dynamics of the meteorological phenomena associated to wind generation. With this aim, the proposed wind speed prediction model uses meteorological data about the evolution of the weather fronts distributed both spatially and temporally on a radius of about 500 km around the point where we need the wind prediction (the test point). The model implemented by using an ANN MLP in the NeuroSolutions™ platform, has been tested using real data on real wind farm located in South Italy; the test results highlight a good performance of the wind prediction with very low errors, also in condition of anomaly weather conditions.

A day-ahead wind speed forecasting using data-mining model-a feed-forward NN algorithm

FINAMORE, ANTONELLA ROSALIA;CALDERARO, Vito;GALDI, Vincenzo;PICCOLO, Antonio;CONIO, GASPARE;
2015-01-01

Abstract

This paper investigates the methods to mitigate the impact of variable renewable energy sources (RES), like the wind, in power system focusing on the problem of the power production forecasting. In particular, the implementation of data mining approach for to solve the wind forecasting problem is proposed, starting from the study of the physics and of the dynamics of the meteorological phenomena associated to wind generation. With this aim, the proposed wind speed prediction model uses meteorological data about the evolution of the weather fronts distributed both spatially and temporally on a radius of about 500 km around the point where we need the wind prediction (the test point). The model implemented by using an ANN MLP in the NeuroSolutions™ platform, has been tested using real data on real wind farm located in South Italy; the test results highlight a good performance of the wind prediction with very low errors, also in condition of anomaly weather conditions.
2015
9781479999828
9781479999828
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/11386/4670411
 Attenzione

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

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 16
  • ???jsp.display-item.citation.isi??? 9
social impact