Forecast for surface solar irradiance at the Brazilian Northeastern region using NWP model and artificial neural networks

Featured Image

Why is it important?

The purpose of this work was establishing a methodology to produce 24h-forecasts for solar irradiation for the Brazilian Northeastern region by using Weather Research and Forecasting Model (WRF) combined with a statistical post-processing method. The cluster analysis technique using the Ward method was employed to identify the areas presenting similar climate features. Then, the entire Brazilian Northeastern (NEB) was divided into four homogeneous regions. The model- WRF provided the short-term solar irradiance forecasts for each NEB climate region. The WRF outputs were refined by using artificial neural networks (ANNs) technique. We found the best ANN architecture and a group of 10 predictors, in which deeper analyses were carried out, including performance evaluation for Fall and Spring of 2011 ( the rainy and the dry seasons in NEB). There was a significant improvement of the forecasts for solar energy when using the ANNs: lower bias and RMSE.