Foundation models (FMs), pre-trained on large datasets and readily adaptable to a broad set of applications, are revolutionizing the field of artificial intelligence (AI). Powerful FMs for language and weather have recently emerged, proving that such models can be developed for complex systems. The GridFM project pioneers the concept of FMs for the electric power grid to be trained on grid data – as opposed to text data – with the overarching goal to develop the underlying technology to cope with the increasing complexity and uncertainties of a faster growing grid (e.g., due to hyperscalar data centers, crypto mining etc.).

A key benefit is the generalizability of FMs that enables stakeholders to readily fine-tune the model for specific needs and their own proprietary data in a scalable and economical way. These capabilities make the FM approach ideal for unifying data, technology, and industry expertise toward a common goal. Because of that, the GridFM project is supported by a fast-growing community of volunteers from industry, academia, and government from more than 100 organizations with over 250 members. To enable an open collaboration, the GridFM community is partnering with Linux Foundation for Energy, which is providing the tools and resources to developing non-differentiating code that can enable all GridFM stakeholders to develop and implement GridFM to transform their business and the power sector at large.

The GridFM community has three subgroups on technology, collaboration and governance. The entire community meets every 4^th Wednesday of the month at 11 am ET. In addition, the GridFM community meets twice a year for a technical deep dive/workshop.

The next and 5^th workshop will be held at Harvard John A. Paulson School of Engineering and Applied Sciences in Boston, MA, USA on March 17^th to 19^th, 2026.

If you are interested in joining the GridFM community, please sign up here. If you like to un-subscribe please, do this here.

A high-level presentation of GridFM is available here.