Influence of raw data analysis for the use of neural networks for win farms productivity prediction

Author

Beccali, M. ; Culotta, S. ; Galletto, J.M. ; Macaione, A.

Author_Institution

Dipt. dell´´Energia, Univ. degli Studi di Palermo, Palermo, Italy

fYear

2011

fDate

14-16 June 2011

Firstpage

791

Lastpage

796

Abstract

In the last decade wind energy had a strong growth because of cost effectiveness of the technology and the high remunerative of investments. The increase of wind power penetration in power grids, however, makes necessary the development of instruments for prediction of productivity of a wind farm. This paper presents a study dealing with the capability of neural network to forecast short term production of a wind farm by the correlation of wind and energy production data. Available measures of wind parameters were related to productivity data of a real wind farm. Also wind data not strictly related to the site have been used in order to assess their possible influence on the production. After a first step of data pre-processing a statistical analysis has been done. The model of input-output correlation is based on the use of artificial neural networks.

Keywords

forecasting theory; neural nets; power engineering computing; power generation planning; prediction theory; productivity; statistical analysis; wind power plants; artificial neural network; data preprocessing; power grid; raw data analysis; short term production forecasting; statistical analysis; wind farm productivity prediction; Correlation; Neural networks; Productivity; Wind energy; Wind farms; Wind forecasting; Artificial neural networks; multi layer perceptron; wind data; wind energy production;

fLanguage

English

Publisher

ieee

Conference_Titel

Clean Electrical Power (ICCEP), 2011 International Conference on

Conference_Location

Ischia

Print_ISBN

978-1-4244-8929-9

Electronic_ISBN

978-1-4244-8928-2

Type

conf

DOI

10.1109/ICCEP.2011.6036394

Filename

6036394