Wind Speed Forecasting using Different Neural Network Algorithms

The wind energy generation depends upon the nature of direction of wind and varying wind speed. This paper presents the comparison of different wind speed forecasting algorithms i.e. Regression Method and Neural Network (different neural network algorithms- 1. Levenberg-Marquardt 2. Bayesian Regularization 3. Scaled Conjugate Gradient.). Matlab tool is used to find the result of these methods which is compared by minimum MAPE (Mean Absolute Percentage Error). To implement these algorithms we take 6 month data of wind speed. The Bayesian Regularization algorithm has the least MAPE which is approx. 3.4%.