Brookhaven National Laboratory will lead a three-year, $14.2M project using...

Brookhaven National Laboratory will lead a three-year, $14.2M project using artificial intelligence to model ways to better manage electric grids. Credit: Brookhaven National Laboratory

Brookhaven National Laboratory will lead a three-year national project using complex new artificial intelligence systems to quickly model billions of scenarios to help grid operators adapt to spur-of-the moment challenges and longer-term planning needs, the U.S. Department of Energy announced Tuesday.

The $14.2 million project will pool the resources of research institutes such as BNL and Stony Brook University, private entities such as IBM Research and utilities such as LIPA and Con Edison to model ways to quickly deploy new resources or adapt to large electric-load fluctuations.

Officials at an event at BNL's Upton facility on Tuesday said the platform has applications for everyday utility operation, when agencies such as LIPA are deciding how to best deploy wind, solar and conventional plants and in cybersecurity, when keeping power on is essential.

The project, part of the Department of Energy’s Genesis Mission, will build an artificial intelligence grid foundation model called GridFM, which will allow for the quick simulation of potentially billions of scenarios, including how new electric demands can best be managed, how grids can best deploy new power sources and how to keep grids reliable and efficient.

WHAT NEWSDAY FOUND

  • Brookhaven National Laboratory will lead a three-year national project using complex new artificial intelligence systems to model ways to quickly deploy new resources for electrical grids or adapt to large electric-load fluctuations.
  • The $14.2 million project will pool the resources of research institutes such as BNL and Stony Brook University, private entities such as IBM Research and utilities such as LIPA and Con Edison.
  • Officials said the platform has applications for everyday utility operation, when agencies such as LIPA are deciding how to best deploy wind, solar and conventional plants and in cybersecurity, when keeping power on is essential.

Such projections using standard models can take months or more. The goal is to do the work within 24 hours, refining the best models from billions reviewed. Some $3.9 million of the funding will be allocated directly to BNL, according to an announcement Tuesday.

With the expected addition of big new electric loads for things such as energy-gobbling data centers, the project will develop ways to simulate and analyze a billion scenarios to meeting those challenges, and do it within a day, according to the agencies.

"The grid is an incredibly complex organism," BNL director John Hill said in an interview Tuesday. "It's a big system that keeps us all alive, so you want to be able to protect that system and keep it as reliable as you possibly can. If something goes wrong, you want to be able to react in real time to fix that thing and keep the power on."

The AI-based system would do just that.

"By providing utilities enhanced artificial intelligence tools, they can plan and operate the grid faster, more reliably, and more cost-effectively to help meet the demands of a growing economy while delivering affordable, reliable power for homes and businesses while unleashing American energy dominance," DOE Assistant Secretary for Electricity Catherine Jereza said in a statement Tuesday.

She told Newsday at the announcement that the new platform could be crucial to quick responses to cyberattacks, while helping utilities make vital instantaneous decisions about shedding load to keep the lights on during peak demand periods.

"During a heat wave, you do load shedding to help conserve the energy so that you can keep the lights on or the cooling on in some areas, and [using artificial intelligence systems] they are able to reduce that [need to shut off customers] by more than 50%," she said.

In addition to SBU and LIPA, collaborators on the project include Cornell University, Nvidia and National Grid, among dozens of others.

Utilities will provide operational data and system experience, BNL said, while researchers and technology providers will provide artificial intelligence expertise and computing resources. The open-source development also involves a partnership with the Linux Foundation Energy.

"Artificial intelligence is often seen as a growing burden on the electric grid, but through the Genesis Mission, we have an opportunity to turn that challenge into an advantage," said Hendrik Hamann, chief artificial intelligence scientist for innovation, science and security at Brookhaven Lab. New York State this summer implemented a 12-month moratorium on data centers over 50 megawatts. Brookhaven Town has an 18-month moratorium.

The DOE’s Genesis Mission seeks to build the world’s most powerful integrated science discovery platform, BNL said, using government, industry, academia and philanthropy to advance breakthroughs in energy, scientific discovery and national security through a new platform that combines artificial intelligence, supercomputing, quantum systems and advanced scientific instruments, the agencies said.

Public housing wait time ... Nepal flood survivor speaks ... 'The Big Chill' reading in the Hamptons  Credit: Newsday

NY ICE arrest numbers ... Public housing wait time ... High school football season cancelled ... Let's Go: GoBoats East Quogue

Public housing wait time ... Nepal flood survivor speaks ... 'The Big Chill' reading in the Hamptons  Credit: Newsday

NY ICE arrest numbers ... Public housing wait time ... High school football season cancelled ... Let's Go: GoBoats East Quogue

SUBSCRIBE

Unlimited Digital AccessOnly 25¢for 6 months

ACT NOWSALE ENDS SOON | CANCEL ANYTIME