Planning: DCL EPSCOR: CISE Large: Distributed Edge Intelligence in Support of Next-Generation Applications

Society has witnessed revolutionary growth of capabilities in data capturing, through the wide-spread deployment of Internet of Things, and intelligent analytics, through advances in Artificial Intelligence (AI). To fully realize the potential of such a transformation, this project addresses the bottleneck of bringing data and advanced analytics together. Specifically, the project’s novelties are the development of enabling technologies for integrating distributed intelligence into the network edge to support next-generation smart applications. The project's broader significance and importance are its potential to transform how high-impact application domains such as smart energy systems and smart agriculture leverage AI to open unexplored frontiers. The project also includes educational and outreach activities for graduate, undergraduate, and K-12 students, and builds new research capacity that significantly benefits the EPSCOR jurisdiction of Kentucky. This project has three main thrusts. The first develops techniques for the life cycle of distributed intelligence, including data curation, decentralized learning/fine-tuning, and distributed inferencing, with a focus on optimizing the efficiency in a resource-constrained edge environment and adapting to the requirements of the supported application. The second thrust analyzes exemplary applications that can benefit from edge intelligence and identifies their requirements, with an initial focus on smart energy systems and smart agriculture. The third thrust focuses on the planning activities. The objective is to engage stakeholders from the target application domains and to perform preliminary studies for evaluating candidate technologies and formulating future research questions. Activities include two in-person workshops, one held at the University of Kentucky and the other at the Pennsylvania State University, and meetings with domain experts who are potential Co-PIs in a future CISE Large proposal. 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.