CAREER: AI-Enabled Autonomous Coordination of Ultra-Large-Scale Converter-Based Distributed Energy Resources in Power Networks

This NSF CAREER project aims to advance the safe, stable, and economically optimal operation of integrated transmission-distribution power systems through the real-time coordination of ultra-large-scale power electronic converter-based distributed energy resources (C-DERs). The project will bring transformative changes to the operation and control paradigm of modern power systems characterized by the widespread deployment of heterogeneous C-DERs, including battery energy storage systems, electric vehicles, photovoltaic generation, and other flexible loads. This will be achieved by developing a systematic hierarchical coordination framework that enables real-time autonomous control of massive C-DERs and leverages their collective flexibility to support integrated transmission-distribution system operation. The intellectual merit of the project includes: (i) distributed optimal control of utility-owned C-DERs; (ii) scalable human-in-the-loop control of user-owned C-DERs; and (iii) AI-enabled dynamic aggregation and transmission-level coordination. The broader impacts of the project include: an immersive learning platform for hands-on experiential education; an AI-based intelligent teaching system to enhance individualized instruction; industry-oriented short courses that incorporate research outcomes into workforce education; a vertically integrated Pre-K-12 STEM pipeline to broaden early engagement; and strengthened collaboration with industry partners to maximize real-world impact and enable technology transfer. Coordinating ultra-large-scale heterogeneous C-DERs in real time offers substantial potential to support integrated transmission-distribution operation and enhance overall grid reliability. However, realizing this potential is hindered by four fundamental challenges: (i) scalability in coordinating extremely large C-DER populations; (ii) inherent nonlinearity of physical system dynamics; (iii) significant uncertainty of human user behaviors; and (iv) safety and stability requirements in grid operations. This NSF CAREER project will develop scalable AI-enabled dynamic aggregation and learning-based control algorithms and tools with provable performance guarantees to address these challenges. The core approach is to integrate model-based methods that leverage physical system structures with advanced data-driven techniques to exploit their complementary strengths and harness the benefits of both. Ultimately, the project will advance fundamental theory and methodology for the control and optimization of large-scale complex human-cyber-physical infrastructure systems with rigorous high-performance guarantees. 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. NSF Award ID: 2541998 | Program: 01002627DB NSF RESEARCH & RELATED ACTIVIT | Principal Investigator: Xin Chen | Institution: Texas A&M Engineering Experiment Station, COLLEGE STATION, TX | Award Amount: $500,000 View on NSF Award Search: https://www.nsf.gov/awardsearch/show-award/?AWD_ID=2541998 View on Research.gov: https://www.research.gov/awardapi-service/v1/awards/2541998.html