How to mix CFD down-scaling and online measurements for short-term wind power forecasting: an artificial neural network application

摘要

This paper deals with bridging the gap between different approaches in wind power forecasting. More precisely, an Artificial Neural Network system is trained with two main inputs: online data from SCADA system and numerical calculations (Numerical Weather Prediction and Computational Fluid Dynamics). As a result, the system provides a smooth and optimal forecast for horizon between 30min to 48H.