Researchers from North Carolina State University have demonstrated techniques that can improve day-ahead solar forecasts by up to 13% over the most consistently performing individual model. “But increasing use of solar can also make forecasting supply and demand more challenging because the availability of sunlight isn’t always consistent. Utilities need accurate day-ahead solar forecasts to be able to plan ahead.” “We wanted to use the models to find the relationship between weather data and solar power generation,” Chou says. For additional information on improving the accuracy of solar power forecasting, read the original article by Tracey Peake on the North Carolina State University website or in its feature as “A Hybrid Machine Learning Framework for Enhanced Day-Ahead Solar Forecasting in Large Scale Systems” in the Journal of Cleaner Production.