Wind Forecast at Medium Voltage Distribution Networks

Due to the intermittent and variable nature of wind, Wind Power Generation Forecast (WPGF) has become an essential task for power system operators who are looking for reliable wind penetration into the electric grid. Since there is a need to forecast wind power generation accurately, the main contribution of this paper is the development, implementation, and comparison of WPGF methods in a framework to be used by distribution system operators (DSOs). The methodology applied comprised five stages: pre-processing, feature selection, forecasting models, post-processing, and validation, using the historical wind power generation data (measured at secondary substations) of 20 wind farms connected to the medium voltage (MV) distribution network in Portugal. After comparing the accuracy of eight different models in terms of their relative root mean square error (RRMSE), extreme gradient boosting (XGBOOST) appeared as the best-suited forecasting method for wind power generation. The best average RRMSE achieved by the proposed XGBOOST model for 1-year training (January-December of 2020) and 6 months forecast (January-June of 2021) corresponds to 13.48%, outperforming the predictions of the Portuguese DSO by 20%.

Automated summary

This study focuses on the development, implementation, and comparison of wind power generation forecast methods for distribution system operators. By applying a five-stage methodology including pre-processing, feature selection, forecasting models, post-processing, and validation, the accuracy of eight different models is compared using historical wind power generation data from 20 wind farms in Portugal. The extreme gradient boosting (XGBOOST) model is identified as the best-suited method, achieving an average relative root mean square error (RRMSE) of 13.48% for a 1-year training and 6-month forecast period, outperforming the predictions of the Portuguese distribution system operator by 20%.