Comparison between performances of different neural networks for wind speed forecasting in Payam airport, Iran

Abstract

Wind energy is one of the cleanest and most consistent sources of energy. This kind of energy is used in wind farms to produce electricity. The output power of a wind farm has a cubic relationship with the speed of wind; therefore, it is very important to forecast wind speed for assessing the future output power of a wind farm. Due to the nonlinear nature of wind and also its speed, the usage of nonlinear methods like artificial neural networks for wind speed forecasting has been widely spread. There are different kinds of neural networks which are used in wind speed forecasting. The outputs of these neural networks have different accuracies. Some of these networks have more accommodation with reality while some others have less. In this research, the outputs of different neural network in wind speed forecasting have been compared with reality. The data were provided from Payam airport weather station in Karaj, Iran. Based on the results of this research the most appropriate neural network for wind speed forecasting in Payam airport has been determined. © 2015 American Institute of Chemical Engineers Environ Prog, 34: 1191–1196, 2015