IBM reports 30% more accurate solar, wind forecasts in DOE-backed project

IBM Research (NYSE:IBM) said Thursday it has developed a new forecasting technology achieving 30% greater accuracy in solar and wind forecasts when compared to conventional approaches.

The company has been working on the project as part of a research programme financed by the SunShot Initiative of the US Department of Energy (DOE).

Together with academic, government and industry partners, IBM researchers have developed the Self-learning weather Model and renewable forecasting Technology (SMT). It relies on machine learning, Big Data and analytics to analyse, learn from and improve solar forecasts derived from a large number of weather models.

IBM noted that that approach can be used in renewable energy forecasting in general, including wind and hydro.

"By improving the accuracy of forecasting, utilities can operate more efficiently and profitably. That can increase the use of renewable energy sources as a more accepted energy generation option," said Bri-Mathias Hodge, who is in charge of the Transmission and Grid Integration Group at the National Renewable Energy Laboratory (NREL). The latter is a collaborator in the research project.

IBM said that for a limited time it will make available foundational solar forecasts at 5-km (3.1-mile) spatial resolution to help government agencies and other entities in the lower 48 states best assess their impact on supply and demand, and on operations.

Choose your newsletter by Renewables Now. Join for free!