Research Project

Advancing Multi-Dimensional Data Generation and Continuous Modeling in AI-based Cyber-Physical Systems

Project Information
- Project period: 01/15/2025 – 9/30/2026
- Principal investigator: Dr. Yuchen Liu (PI, NCSU)
- Graduate/undergraduate students: Everett Tucker (NCSU), Maulik Verma (NCSU)

Project Overview
- As an advanced layer of cyber-physical systems (CPS), hybrid data-driven emulators, predictors, and optimizers play a crucial role in the National Artificial Intelligence Research Resource (NAIRR) initiative by acting as intelligent models that replicate physical systems and processes. These virtual experimental counterparts allow researchers to optimize complex networked systems in a risk-free environment, accelerating discovery and innovation across various domains. This project aims to facilitate the seamless integration and utilization of AI tools by providing a platform to test and validate AI algorithms under realistic conditions. This project lays the foundations of a test platform by developing multi-dimensional data generation and continuous modeling approaches that merge tools from machine learning, communication theory, and distributed optimization to advance the AI-driven CPS across different areas.

Advancing NAIRR Infrastructure
- By providing a virtualized, data-driven, and continuously evolving runtime environment, the project will significantly enhance NAIRR’s infrastructure, fostering innovation, efficiency, and ethical AI development. They enable risk-free experimentation, optimize resource utilization, and empower researchers to tackle critical societal challenges through AI-powered cyber-physical systems.

Advancing AI research
- The project generates dynamic and scalable datasets, enabling AI models to be trained and tested under real-world conditions without costly data collection. Their precise system modeling capabilities allow researchers to explore complex interactions and edge cases, enhancing AI robustness and generalizability. Additionally, the data-model platform facilitates safe, iterative testing, ensuring models can be fine-tuned and validated without operational risks. This accelerates AI deployment across various domains, driving innovation while optimizing resource use and development cycles.