Generative AI for smart grid modeling

MIT’s Information and Decision Systems Laboratory (LIDS) has received $1,365,000 in funding from the Appalachian Regional Commission (ARC) to support its participation in an revolutionary project entitled “Formation of the Smart Grid Deployment Consortium (SGDC) and expansion of the HILLTOP+ platform”.

The grant was provided through ARC’s Appalachian Regional Initiative for Stronger Economies, which promotes regional economic transformation through multistate collaboration.

Led by Kalyan VeeramachaneniResearch Scientist and Principal Investigator at LIDS’ Data to AI GroupThe focus of the project is the creation of AI-driven generative models for customer load data. Veeramachaneni and colleagues will work with a team of universities and organizations led by Tennessee Tech University, including collaborators from Ohio, Pennsylvania, West Virginia and Tennessee, to develop and deliver smart grid modeling services as a part of the SGDC project.

These generative models have wide-ranging applications, including grid modeling and training algorithms for energy technology startups. When the models are trained on existing data, they produce additional, realistic data that may complement limited data sets or replace sensitive data sets. Stakeholders can then use these models to grasp and plan for specific what-if scenarios that go far beyond what might be achieved with existing data alone. For example, the information generated can predict the potential load on the grid if an extra 1,000 households were to adopt solar technologies, how that load might change throughout the day, and similar contingencies, critical to future planning.

The generative AI models developed by Veeramachaneni and his team will provide inputs to modeling services based on the HILLTOP+ microgrid simulation platform, originally prototyped by MIT Lincoln Laboratory. HILLTOP+ will probably be used to model and test latest smart grid technologies in a virtual “protected space” to present rural electric utilities greater confidence in deploying smart grid technologies, including utility-scale battery storage. Energy technology startups will even profit from HILLTOP+’s network modeling services, allowing them to develop and virtually test their smart grid hardware and software products for scalability and interoperability.

The project goals to assist rural electricity suppliers and energy technology start-ups mitigate the risks related to using these latest technologies. “This project is a robust example of how generative AI can transform a sector – on this case the energy sector,” says Veeramachaneni. “To be useful, generative AI technologies and their development should be closely linked to expertise. I’m excited to partner and collaborate with lattice modeling experts to include the most recent and best from my research group and push the boundaries of those technologies.”

“This project is a testament to the facility of collaboration and innovation, and we stay up for working with our collaborators to drive positive change within the energy sector,” says Satish Mahajan, principal investigator on the project at Tennessee Tech and professor of electrical and electrical engineering Technical computer Science. Michael Aikens, director of Tennessee Tech’s Center for Rural Innovation, added: “Together, we’re taking vital steps toward a more sustainable and resilient future for the Appalachian region.”