An FSU team developed a forecasting system called GridFusionX that combines information such as past electricity demand, power generated from renewable sources, and energy market prices to generate predictions that grid operators can use to run the grid more efficiently. The system uses a graph neural network to map how what happens in one region can affect neighboring regions.

“What happens in one area can affect neighboring areas because they share power lines, weather patterns and energy markets. By continuously analyzing these pieces, we can predict energy needs more accurately and adapt to ensure both reliability and cost savings,” says Tuy Nguyen. In real-world tests, GridFusionX improved forecasting accuracy by up to 56% and cut reserve costs by as much as 66%.

• Olugbenga Anubi
• Tuy Nguyen