Very-Short Term Wind Speed Forecasting Via Distance Algorithm in Machine Learning

This paper proposes distance matrices, Euclidean, and offset translation methods in machine learning prediction of wind speed. The primary aim for this research is to design forecasting models for very short-term and short-term wind speed prediction based on these two methods by using historical data on wind speed. The test data is collected at a wind power station at 10 minutes intervals. Furthermore, we evaluate the output in different time horizons in comparison to the benchmark method (persistence). To ensure the output results, comparing this method with the persistence method is essential. The proposed method performance was evaluated and compared with the conventional persistence method performance in terms of mean absolute error.