As more renewable energy sources such as wind, solar, and hydropower come online, maintenance of those assets becomes more complex. The U.S. expects to generate 44 percent of its power from renewable sources by 2050. That growth will add hundreds of millions of inverters, most if not all internet-connected, to the national energy grid.

This is happening as older parts of the grid are beginning to fail. Close management of the health of both new and existing grid assets will be key to meeting the nation’s need for reliable electric power.

The U.S. Department of Energy’s (DOE’s) Argonne National Laboratory has announced that it is working with a spectrum of power companies–from operators of aging hydropower plants to large solar arrays–to rethink how they manage their grid assets.

The result of that collaboration has been artificial intelligence (AI) technology that can predict when grid components will fail. The AI system collects data from sensors installed throughout the grid to create a predictive model that forecasts component wear and tear. The goal is for the system to recommend repair or replacement of equipment before it fails.

“Companies want to know the health of their assets,” said Feng Qiu, head of the Advanced Grid Modeling group at Argonne, who led this research. ​“Our prognostic models that leverage condition-monitoring information can tell them the useful remaining time of their equipment — how many years, months and weeks it has left.”

This intent of Argonne’s approach is to estimate infrastructure and asset health, predict failure risks, and adapt maintenance decisions based on current real-world data. Using data collected from the field, Argonne researchers have been able to show AI’s value to energy providers. One project on solar inverters, for example, the team showed that it could potentially reduce total maintenance costs by 43 percent to 56 percent, unnecessary crew visits by 60 percent to 66 percent, and increase profit by 3 percent to 4 percent.

By minimizing downtime and addressing maintenance issues before they escalate, energy providers can enhance grid reliability and resilience. Argonne claims the models can predict failures in the entire network–from transmission plants to power lines–that produces and transports electricity from where it is generated to where it is consumed. The U.S. has more than 240,000 high-voltage transmission lines and 50 million transformers. Most of the large and expensive transformers are near the end of their lifespan. About 70% have been in service for 25 years or more. Increasing load and volatile renewable energy integration are pushing an aging power grid to the limit.

Argonne expects that providing this asset health management tool to operators will help ensure the future reliability and security of our electric grid. It might also level the playing field for small energy companies, which will have access to the same cutting-edge technology as the major corporations.