Energy network

In the US, the SLAC National Accelerator Laboratory will use $6 million funding from the Department of Energy (DoE) to demonstrate how machine learning (ML) and artificial intelligence (AI) can be used to improve the resiliency of energy network.

The pilot Grid Resilience and Intelligence Project (GRIP) is part of $32 million in funding announced last week by the DoE towards the Grid Modernisation Initiative, a programme designed to modernise the US energy network in line with emerging utility business models and smart grid technologies.

Under the three-year pilot, the SLAC National Accelerator Laboratory will partner with utility companies members to the National Rural Electric Cooperative Association (NRECA) and other DoE national laboratories including the Berkeley Lab.

The programme will include AI being combined with massive amounts of data to enable energy networks to quickly identify asset failures and will possess self-healing capabilities. According to a statement, the pilot aims to strengthen the country’s energy system making it more resistant to storms, solar eclipses, cyber attacks and other disruptions without human intervention.

SLAC’s GISMO lab in partnership with Stanford University will develop ML algorithms to understand how an energy network can operate using data collected from utility operations, satellite imagery and other sources.

Smart energy network

The programme is expected to help the US to expand adoption of clean energy resources including solar and wind.

Sila Kiliccote, the principal investigator for the project, commented:  “This project will be the first of its kind to use artificial intelligence and machine learning to improve the resilience of the grid.

“While the approach will be tested on a large scale in California, Vermont and the Midwest, we expect it to have [a] national impact, and all the tools we develop will be made available either commercially or as open source code.”

For instance, NRECA will have its 834 utility members adopt standards and technologies developed under the pilot to improve customer service to more than 42 million customers in 47 states.

“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.

“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,” added Kiliccote.

Berkeley Lab will employ its algorithms developed to improve management of distributed energy resources through switching them on either island or grid mode to improve the reliability of grid systems during normal operations and in emergency cases.

 

Image Credit: 123rf