开发基于 AI 和 HPC 的电力系统在线安全评估和智能控制方法 Development of AI- and HPC-based Methods for Power System Online Security Assessment and Intelligent Control
, Associate Professor, ZJU-UIUC Institute
Modern power grids are experiencing grand challenges caused by their stochastic and dynamic nature. They can violate traditional study assumptions and operational rules, and existing control systems are difficult to adapt to the new challenges due to the lack of computational power and accurate grid models for use in real time, leading to growing concerns about secure and economical power grid operation. It's critical to comprehensively assess operational risks and provide prompt control actions in real time. Ruisheng Diao will first introduce his research on developing HPC-based methods for speeding up large-scale power system simulations to enhance situational awareness, then present a novel AI-based control platform for providing autonomous operational controls using state-of-the-art deep-reinforcement learning algorithms.