Short-term wind speed prediction using several artificial neural network approaches in Eskisehir

Abstract

Due to the negative environmental impact of using fossil energy sources and depletion of fossil fuels, the alternative energy sources are being searched all over the world. Since wind energy is clean and renewable, the penetration of wind energy for electricity generation is increasing day by day. Wind power plants require continuous and appropriate intensity winds. In terms of the reliability and power quality of the power system, the variability of wind energy has led to problems. To minimize these problems, highly accurate wind speed prediction method should be used. In this study, accurate short term wind speed prediction approach is aimed for increasing efficiency of wind energy production. The short term wind speed prediction approached is trained/tested with real three years hourly averaged wind speed values from Eskisehir region of Turkey. Feed forward backpropagation network and Levenberg-Marquardt algorithms are used for analyzing and the identified four network model are compared in terms of mean square error values.