An Empirical Study on Machine Learning Models for Wind Power Predictions

Wind power prediction is of great importance in the utilization of renewable wind power. A lot of research has been done attempting to improve the accuracy of wind power predictions and has achieved desirable performance. However, there is no complete performance evaluation of machine learning methods. This paper presents an extensive empirical study of machine learning methods for wind power predictions. Nine various models are considered in this study which also includes the application and evaluation of deep learning techniques. The experimental data consists of seven datasets based on wind farms in Ontario, Canada. The results indicate that SVM, followed by ANN, has the best overall performance, and that k-NN method is suitable for longer ahead predictions. Despite the findings that deep learning fails to give improvement in basic predictions, it shows the potential for more abstract prediction tasks, such as spatial correlation predictions.