An Effective Random Forest based Long-Term Wind Power Forecasting Technique

Accurate Wind Power Forecasting (WPF) has become an essential task for grid operators due to its ability to minimize the effect of wind power intermittency and the need of energy storage deployment. In this paper, a Random Forest (RF)-based long-term WPF technique is proposed. The model inputs consist of some meteorological parameters such as wind speed, temperature, and pressure. The input data are selected from the data NOAA’S Surface Radiation (SURFRAD) network at Bondville station (USA). The RF parameters (number of trees, number of leaves) are optimized to get the best prediction accuracy. The normalized RMSE and MAE metrics are computed to assess the performance of the proposed RF model.