NSF backs Stony Brook’s plan for AI-enabled power grid


Entrust control of the national electricity grid to artificial intelligence? Which could may be be mistaken?

Keep calm, humans. What looks like the opening of every human-machine sci-fi epic you’ve ever seen is actually a giant leap towards safety and reliability, researchers say, a national energy grid based on AI is our secure energy future.

And the National Science Foundation agrees, as evidenced by a $ 5 million “cooperative agreement” that will fund 10 national research teams – led by Stony Brook University – to develop a self-sustaining power grid, AI compatible, invulnerable to cyber attacks, systemic failures. and catastrophic accidents.

Peng Zhang: Natural intelligence.

Professor Peng Zhang of Stony Brook University and collaborators from academia, industry and government are already working hand in hand on ‘Grid AI’ under the auspices of the NSF Convergence Accelerator Program , which supports basic multidisciplinary research designed to accelerate society-improving solutions.

In this case, the solution would be a more resilient national energy grid. Work began in 2020 with a $ 1 million NSF Phase 1 grant and continues with the $ 5 million top-up announced on September 16; Phase 2 “will focus on extending the prototype of the solution and building a sustainability plan beyond NSF funding,” according to SBU.

To date, more than 30 partners – academia, electric utilities, local and state governments, and others – have contributed to the mission, which involved everything from deep learning computers and encrypted controls to fully programmable microgrids.

Now, according to lead researcher Zhang, SUNY Empire Innovation Professor in the Department of Electrical and Computer Engineering at SBU College of Engineering and Applied Sciences, it’s time for the long pants.

“We hope to show that our AI-Grid solution is affordable, lightweight, secure and repeatable, providing unprecedented flexibility for an approach to transforming today’s infrastructure into the autonomous AI-Grid of tomorrow,” said Zhang , trumpeting the AI-Grid. huge potential for energy resilience and economic equality.

Sounds innocent enough: the AI-Grid prototype, under construction at SBU.

“[Phase 2] will demonstrate AI-Grid’s ability to strengthen our country’s digital economic engines, alleviate the pains of communities suffering from high electricity costs, and eliminate low-power reliability and low resilience, ”a he added.

Contributors based at Stony Brook include the university’s electrical and computer engineering department and the computer science department – a “multidisciplinary collaboration (which) strengthens our research enterprise while demonstrating to our students how complex problems are solved in the modern world, ”according to College of Engineering and Applied Sciences, interim dean Jon Longtin.

“The technologies that Peng and his team are developing come at a critical time as the country turns to renewables and the inevitable impact they will have on the grid over the next decade,” added Longtin, also a professor. of mechanical engineering at CEAS.

Jon Longtin: Critical pivot.

Off-campus collaborators in Phase 2 include the Brookhaven National Laboratory, New England-based utility Eversource Energy, PSEG Long Island, Hitachi America, and several other academic and industry partners.

With an eye to the future, Zhang’s AI-Grid team recently entered into end-user agreements with Energy and Innovation Park, a fuel cell-centric, grid-connected energy project based in Connecticut; the Epic Institute, a global climate solutions organization based in California; and the Chicago-based Bronzeville Community Microgrid project.

Before the end of Phase 2, these end users must test, demonstrate and, if all goes according to plan, implement AI-Grid technology – precisely the kind of high-speed and highly productive collaboration that the Accelerator program convergence is considering, according to Douglas Maughan, who is leading the NSF effort.

“A convergence approach is essential to solving societal challenges at scale, which is why the NSF Convergence Accelerator requires our funded teams to include a wide range of expertise from academia, from organizations with purpose. nonprofit, industry, government and other communities, ”Maughan said in a statement. declaration. “The fusion of ideas, techniques and approaches combined with human-centered design concepts helps our teams to accelerate their ideas towards solutions within three years. “

Source link


About Author

Leave A Reply