NSF Convergence Accelerator - Track D: AI-Enabled Provably Resilient Networked Microgrids

The NSF Convergence Accelerator supports use-inspired, team-based, multidisciplinary efforts that address challenges of national importance and will produce deliverables of value to society in the near future. The broader impact and potential societal benefit of this Convergence Accelerator Phase I project is to develop coordinated networked microgrids (NMs) that have the potential to help restore neighboring distribution grids after a major blackout. These NMs also hold promise to significantly enhance the day-to day reliability of the powergrid. Many organizations (including the US Department of Energy) believe that, ultimately, NM R&D will lead to the next wave of smart-grid technology, which has the potential to achieve the vision of a highly resilient grid. Specifically, this project aims to develop and demonstrate Artificial Intelligence (AI) enabled, provably resilient networked microgrids (AI-grid). AI-Grid has the potential to transform today’s community power infrastructures into tomorrow’s autonomic microgrids and flexible services immune to cyber-attacks, high levels of renewable energy penetration, faults, and disastrous events, which have the potential to benefit various commercial sectors as well as the military. The key innovation proposed in this project is a programmable platform that integrates continuous-depth deep neural networks, reachability analysis, formal control, and cybersecurity technologies to enable scalable, self-protecting, autonomic and ultra-resilient microgrids and NMs capable of coordinating ultra-scale distributed energy systems and cultivating America’s smart communities and cities. For example, the Grid at the Energy & Innovation Park (EIP), a $1 billion microgrid project aimed at transforming “Hardware City” — New Britain, CT— from a traditional manufacturing Center into the new Center for Connecticut’s digital economy. This project will share with the relevant communities the resultant learning and control models, as well as the monitoring data from test beds and operational microgrids run by their collaborators. The adoption of AI-Grid in the EIP data center microgrid will demonstrate the tremendous potential in empowering our nation’s digital economic engine – the swiftly growing array of Data Centers. This project will provide a powerful living laboratory/classroom and big data sets to stimulate innovations towards smart, replicable, sustainable, and connected communities and infrastructures. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.