Federal Project Grant Award Summary

The National Science Foundation's Division of Information and Intelligent Systems awarded a five-year CAREER grant totaling $346,590 to the University of Wisconsin–Madison, effective July 1, 2026 through June 30, 2031, under the Computer and Information Science and Engineering (CISE) program (CFDA 47.070). This project develops an artificial intelligence (AI)-native approach to edge network management that enables networks to adapt proactively to heterogeneous workloads and dynamic user contexts. The research advances an intent-centric control framework leveraging predictive and multi-timescale learning techniques to optimize how application performance depends on network resource allocation, addressing challenges posed by the coexistence of AI-driven data flows with traditional internet traffic on resource-constrained edge devices.

The project delivers methodologies to improve performance, efficiency, and reliability for AI-enabled services across critical application domains including education, healthcare, transportation, and immersive media. Research outputs are integrated into academic coursework and outreach activities, with the award supporting the professional development of Ph.D. and undergraduate students in computing and network systems research. By developing context-aware representations of application behavior—including inference tasks, collaborative model updates, sensing pipelines, and interactive workloads—this research addresses fundamental gaps in current reactive network management approaches and contributes to foundational knowledge in edge computing and intelligent systems.