Prediction of Wind Speed and Power with LightGBM and Grid Search: Case Study Based on Scada System in Turkey

Due to the speeding up of climate change, there is an urgent need to switch from using fossil fuels to producing energy using renewable energy sources. This change has to happen as soon as feasibly possible. Thus, in this article, to forecast wind speed and wind energy output in Turkey, the Light Gradient Boosting Machine (LightGBM) approach was applied, the hyperparameters of the LightGBM were tuned to the grid search method, and finally some evaluation criteria such as root mean square error and R2 were calculated to show the performances of the LightGBM. Fortunately, an R2 value of 0.98 for forecasting wind speed was found after 25 s. Additionally, the assessment criterion R2 =1 for predicting the production power of the wind turbine was attained after 90 s.