A research team including professors Jingrui He of the School of Information Sciences and Hanghang Tong of the Siebel School of Computing and Data Science at the University of Illinois Urbana-Champaign, has received a Phase II award through the US Department of Energy's Genesis Mission to develop a model for electric grid expansion.
The project, "Foundation Models for the Electric Grid: From Proof of Concept to Real-world Impacts," seeks to develop a next-generation grid foundation model known as GridFM, an artificial intelligence (AI) system that can rapidly simulate scenarios for adding new loads to the electric grid as the demand for electricity continues to grow. With the goal of building a model that can simulate one billion scenarios in 24 hours, the project aims to significantly accelerate grid expansion planning with optimal accuracy, affordability, and efficiency in operations.
Principal Investigator He and Co-PI Tong will lead the core GridFM development, especially around scalable graph learning and structured and agentic AI.
"What excites us is building the core AI foundation that makes the broader vision possible," He said. "We hope to create models that generalize across different grids, topologies, and tasks rather than requiring a new bespoke model for every system."
The three-year $14.2 million project was announced on September 1 at Brookhaven National Laboratory by DOE Assistant Secretary for the Office of Electricity Catherine Jereza. Brookhaven Lab is the lead on the project, which also includes collaborators from the National Laboratory of the Rockies, the Massachusetts Institute of Technology, Stony Brook University, and other public and private organizations.
He, recently named a 2026 University Scholar, is interested in the design, building, and testing of automated and semi-automated methods to explore, understand, characterize, and predict real-world data by means of traditional and modern AI, such as agentic systems. This work has applications to sustainability, agriculture, social network analysis, healthcare, and finance, among other areas.
Tong's expertise lies in large-scale data mining and machine learning, especially for graph and multimedia data.
"I am truly thrilled to have the opportunity to work with this wonderful group of researchers," Tong said, "and, even more importantly, to make a meaningful impact on this critical domain."
The Genesis Mission is a historic national initiative led by DOE, which is building the world's most powerful integrated science discovery platform. By uniting government, industry, academia, and philanthropy, it is accelerating breakthroughs in energy, scientific discovery, and national security through a new platform that combines AI, supercomputing, quantum systems, and advanced scientific instruments.