WHY THIS MATTERS IN BRIEF
Being able to fully automate the American energy grid could reduce regulatory burden, improve resilience and reliability, and make it more efficient.
The US Department of Energy, whose supercomputers are already building their own AI’s, has announced it will explore a first of a kind program to discover whether or not Artificial Intelligence (AI) could help electric grids handle power fluctuations, avoid failures, resist damage, and recover faster from major storms, cyberattacks, solar flares and other disruptions. And elsewhere other organisations are also trying to re-invent energy grids using blockchain, but that’s a different story…
“The new project, called GRIP, for Grid Resilience and Intelligence Project, was awarded up to $6 million over three years late last year and it’s the first project of its kind to help power grids deal with disturbances,” said Sila Kiliccote, GRIP’s principal investigator and director of the Grid Integration, Systems and Mobility lab at the SLAC National Accelerator Laboratory in Menlo Park, Calif.
GRIP will develop algorithms to learn how power grids work by analysing smart meter data, utility scale Supervisory Control And Data Acquisition (SCADA) data, electric vehicle charging data, and even satellite and street view imagery.
“By looking at satellite and street-view imagery, we can see where vegetation is growing with respect to power lines, how long it takes to grow, and anticipate what the effects of high winds might have on that vegetation, such as pulling trees onto power lines during storms,” said Kiliccote.
The aim with GRIP is to address three different kinds of problems.
“First we need to anticipate and get in front of grid events,” said Kiliccote, “next we’d like to minimize the effects of grid events when they do happen. Finally, after the event ends, we’d want to bring systems back as quickly as possible. GRIP’s first year is devoted to anticipating grid problems. Predictive analytics will help identify places where the electric grid is vulnerable to disruption so it can be reinforced.”
“The second year will aim to help grids absorb disruptions. For instance, a grid can be divided into virtual ‘islands’ or micro-grids, that can be isolated to prevent a power disruption from spreading and taking down the entire grid,” he added, “and the third year will focus on helping grids recover from events.”
“Ultimately, we’d like to see a grid that can run on its own, an autonomous grid like an autonomous car,” said Kiliccote, “however, unlike autonomous cars, an autonomous grid will need to be able to handle additional components added to it while it is still running.”
GRIP’s partners not only include universities, but also utilities around the country and companies such as Tesla. Some of the first places the project will test its data analytics platform are Southern California Edison, a leader in smart metering, and Packetized Energy, which helps grids manage distributed energy resources.
“One of our largest partners is the National Rural Electric Cooperative Association (NRECA), which represents more than 800 cooperatives that supplies electricity to something like 42 million people in 47 states,” said Kiliccote, “the knowledge and tools we develop in GRIP could easily be adopted by NRECA’s member coops.”
Another GRIP partner, Lawrence Berkeley National Laboratory, will deploy and validate control systems it has developed for solar inverters that automatically convert the variable direct current from solar cells to alternating current that is fed into power grids. The aim being to help create power grids that can automatically reconfigure themselves to best use distributed energy resources such as wind and solar in ways that maximize reliability during both normal and emergency operations.
“Once we build our data analytics platform, we’ll make it open source so a lot of academics can develop tools they can test on the platform,” adds Kiliccote, “and GRIP will run its AI systems on a currently unnamed partner’s computing clusters.”