Short Term Wind Speed Forecasting with ANN in Batman, Turkey

Abstract

In this paper, Artificial Neural Network (ANN) technique has been used for the short term estimation of wind speed in the region of Batman, Turkey. The data were collected by the Turkish State Meteorological Service (TSMS) during ten years through a network of measurement stations located in the place of interest. Different ANN models has been developed for the short term wind speed forecasting in Batman, Turkey, using data measurements of 10 year obtained from the Turkish State Meteorological Service. First a model with ten neurons in hidden layer was chosen, the results were not sufficiently satisfactory. Other three models were developed, consisting of twenty neurons, thirty neurons and forty neurons in the hidden layers. The model of forty neurons was the best for the short term wind speed forecasting, with mean squared error and regression values of 0.311136 and 0.978094 for training respectively. The developed model for short term wind speed forecasting showed a very good accuracy to be used by the General Directorate of Electrical Power Resources Survey and Development Administration (EIE) in Batman, Turkey for the energy supply.