Probabilistic Forecast of Wind Power Generation With Data Processing and Numerical Weather Predictions

With the increasing proportion of renewable energy, some problems have gradually emerged. To reduce the operating cost and improve system reliability, renewable power forecasting is an indispensable part. Compared with the deterministic prediction, the probabilistic forecast considers the uncertainty, which helps manage the power system operations. This study proposes a novel hour-ahead probabilistic forecasting method for wind power generation. It includes data preprocessing, adaptive neuro fuzzy inference system training model with fuzzy C-means clustering algorithm, and postprocessing of predicted interval (PI). The input data of the proposed forecasting model include the numerical weather prediction (NWP) ensemble wind speeds, NWP spot wind speeds, and historical wind power measurements. The research results demonstrate that the proposed model supports better performance and prediction stability. Furthermore, this work reveals that the data preprocessing and postprocessing of PI are essential for wind power forecasting. These processes greatly improve the performance of the probabilistic wind power forecasts.