Artificial intelligence (A.I.) and machine learning may be the answer to ongoing problems occurring in the electric grid.

Researchers from the Department of Energy’s SLAC National Accelerator Laboratory are utilizing A.I. to identify locations where the electric grid is susceptible to disruption, while also reinforcing those spots in advance to recover faster when failures do occur, as part of project known as Grid Resilience and Intelligence Project (GRIP).

“This project will be the first of its kind to use artificial intelligence and machine learning to improve the resilience of the grid,” Sila Kiliccote, director of SLAC’s Grid Integration, Systems and Mobility lab, GISMo, and principal investigator for the project, said in a statement. “While the approach will be tested on a large scale in California, Vermont and the Midwest, we expect it to have national impact and all the tools we develop will be made available either commercially or as open source code.”

Machine learning will be used so that computers can ingest large amounts of data and teach themselves how a system behaves and then A.I. will use the knowledge the machines have acquired to solve problems.

The researchers believe they can eventually create an autonomous grid that absorbs routine power fluctuations from clean energy sources like solar and wind, and be able to quickly respond to disruptive events with minimal intervention from humans.

GRIP represents one of seven Grid Modernization Laboratory Consortium projects looking at boosting grid resilience as part of a $32 million funding project. Six million will go toward GRIP over three years.

“One of the first places we will test our data analytics platform is at a major California utility,” Kiliccote said. “The idea is to populate the platform with information about what your particular part of the grid looks like, in terms of things like solar and wind power sources, batteries where energy is stored and how it’s laid out to distribute power to homes and businesses.

“Then you begin to look for anomalies—things that could be configured better.”

Kiliccote explained that if a grid can be divided into microgrids they can be isolated to prevent a power disruption from spreading and taking the system down.

“You can also learn a lot just from satellite imagery,” Kiliccote said. “For example, you could see where vegetation is growing with respect to the power lines, and anticipate when trees are likely to grow over the power lines and pull them over during a storm.”