Abstract
[Google Meet]
連結點我
Digital twins are evolving from passive dashboards into engines that actively support decision-making. This micro-course shows how to design and operate AI-in-the-loop digital twins that can safely influence real systems, with a particular focus on Network Digital Twins (NDTs) for the 6G era. We begin with the first principles: the relationship between a model, a shadow instance, and a full twin; standard reference architectures that span data ingestion through state stores, simulators, AI services, and orchestration; and the role of verification, validation, and uncertainty quantification (VVUQ) in earning trust. On the networking side, we tie these ideas to concrete standards and interfaces: analytics platforms feed NDT “what-if” experiments, whose outcomes are turned into O-RAN RIC policies. We show how this workflow de-risks emerging 6G capabilities such as non-terrestrial networks (NTN), reconfigurable intelligent surfaces (RIS), and integrated sensing and communications (ISAC). Case studies from manufacturing, healthcare, and live networks highlight measurable benefits. Participants leave with a concise checklist for scoping twin capabilities, instrumenting metrics, and running deployments that progress from shadow to canary to blue-green, plus a reading pack for deeper study.
連結點我
Digital twins are evolving from passive dashboards into engines that actively support decision-making. This micro-course shows how to design and operate AI-in-the-loop digital twins that can safely influence real systems, with a particular focus on Network Digital Twins (NDTs) for the 6G era. We begin with the first principles: the relationship between a model, a shadow instance, and a full twin; standard reference architectures that span data ingestion through state stores, simulators, AI services, and orchestration; and the role of verification, validation, and uncertainty quantification (VVUQ) in earning trust. On the networking side, we tie these ideas to concrete standards and interfaces: analytics platforms feed NDT “what-if” experiments, whose outcomes are turned into O-RAN RIC policies. We show how this workflow de-risks emerging 6G capabilities such as non-terrestrial networks (NTN), reconfigurable intelligent surfaces (RIS), and integrated sensing and communications (ISAC). Case studies from manufacturing, healthcare, and live networks highlight measurable benefits. Participants leave with a concise checklist for scoping twin capabilities, instrumenting metrics, and running deployments that progress from shadow to canary to blue-green, plus a reading pack for deeper study.
Bio
Dr. Shih-Chun Lin is an Associate Professor of Electrical and Computer Engineering at North Carolina State University, where he directs the Intelligent Wireless Networking Laboratory. He received his B.S. in Electrical Engineering and M.S. in Communication Engineering from National Taiwan University, and his Ph.D. in Electrical and Computer Engineering from the Georgia Institute of Technology. His research spans wireless networking and communications, software-defined infrastructures, vehicular edge computing, non-terrestrial networks, digital twins, and AI-driven networking. His recent work focuses on generative edge AI for open drone broadband systems, 6G smart fab and vehicle infrastructure, and hybrid space with quantum machine learning.