Comparative Study of Forecasting Techniques for Small Wind Turbine Power Generation by Meteorological Parameters.

Green energy generation is increasing its presence in individual and large-scale electrical networks, due to the need to reduce the emission of greenhouse gases. This study performs a comparative study between different regression models, linear and non-linear, with the objective of determining the best method for the prediction of the energy generated by a mini wind turbine based on meteorological variables. First, the best configuration for the chosen techniques will be obtained, and then the best models will be compared. These comparisons will be based on different metrics: Mean Squared Error, Root Mean Squared Error, Mean Absolute Error, Median Absolute Error and Coefficient of Determination; obtained through a 10-kfold cross-validation.