Predicting The Power of a Wind Turbine with Machine Learning-Based Approaches from Wind Direction and Speed Data

It is foreseen that the electrical energy produced using limited resources such as hydroelectric, natural gas, and thermal power plants may cause problems in terms of energy continuity in the long term. Therefore, with the incentives of governments, investment in renewable energy sources is increasing every year. Wind energy is one of the most important renewable energy sources. The calculation of the power to be produced in wind power plants is both difficult and requires experience. In this study, the amount of power produced in a wind turbine was estimated using machine learning-based regression algorithms (7 different algorithms) using wind speed and wind direction data. The proposed approach was evaluated on data from a wind turbine in Turkey. Among the regression algorithms evaluated according to the R2 performance metric, the best performance was achieved with the AdaBoosting algorithm.