Generative AI for smart grid modelling

MIT’s Laboratory for Information and Decision Systems (LIDS) aims to apply generative AI to smart grid modelling.

The initiative, part of the Tennessee Tech University led smart grid modelling and testing ‘Smart Grid Deployment Consortium’ project in the Appalachian region of the US, will focus on creating AI-driven generative models for customer load data.

These will then form inputs to the modelling services of the HILLTOP microgrid simulation platform for modelling and testing new smart grid technologies, in particular for the rural electric utilities that serve much of the region and for example for energy tech startups that are interested in scalability and interoperability.

“This project is a powerful example of how generative AI can transform a sector – in this case, the energy sector,” says Kalyan Veeramachaneni, principal research scientist and principal investigator at the LIDS.

Have you read?
Generative AI solutions for utilities on the rise
The vital role of R&D in the energy transition

“In order to be useful, generative AI technologies and their development have to be closely integrated with domain expertise. I am thrilled to be collaborating with experts in grid modelling, and working alongside them to integrate the latest and greatest from my research group and push the boundaries of these technologies.”

The generative models are expected to have far-reaching applications in that when trained on existing data, they can create additional, realistic data that can augment or replace limited datasets.

For example, in this case generated data can predict the potential load on the grid if an additional 1,000 households were to adopt solar technologies and how that load might change throughout the day

The initiative has been awarded $1.37 million in funding from the Appalachian Regional Commission and will include other participants from across Ohio, Pennsylvania, West Virginia and Tennessee.