Predicting wind power generation using machine learning and CNN-LSTM approaches

Abstract

Wind power has grown significantly over the last decade regarding its combability with emission targets and climate change in many countries. A reliable and accurate approach to wind power forecasting is critical for power system operations and day-to-day grid functioning. However, regarding to the nonstationary nature of wind power series, classic forecasting methods can hardly provide the desired accuracy and cause risks and uncertainties for system operation, which substantially affects how wind power companies make energy market decisions. This study proposes novel algorithmic approaches utilizing machine learning techniques to predict wind turbine power. Applied algorithms include extremely randomized trees, light gradient boosting machine, ensemble methods, and the CNN-LSTM method. Based on the provided results, the lowest mean square error value is related to the CNN-LSTM method, indicating that this method is more accurate. Also, the ensemble method provides admissible results despite the high speed of the algorithm.