IBM: DOE Solar Forecast Accuracy Up 30% With SMT Machine Learning Tool

The Energy Department has achieved a 30 percent increase in accuracy on wind, hydro and solar forecasts through the use of an IBM-built system that uses machine learning techniques, the company said Thursday.

IBM said the Self-learning weather Model and renewable forecasting Technology platform is designed to analyze and generate weather model-derived solar forecasts through analytics, big data and other cognitive computing systems.

“By improving the accuracy of forecasting, utilities can operate more efficiently and profitably,” said Dr. Bri-Mathias Hodge, head of the transmission and grid integration group at the National Renewable Energy Laboratory.

“That can increase the use of renewable energy sources as a more accepted energy generation option.”

The SMT system is part of DOE’s SunShot Initiative, which intends to develop platforms meant to bolster adoption of solar energy.