B0605
Title: Model-free approaches to state estimation and control of electric power grids using emerging machine learning techniques
Authors: Tim Hansen - South Dakota State University (United States) [presenting]
Abstract: The trend in electric power systems is the displacement of traditional synchronous generation (e.g., coal, natural gas) with renewable energy resources (e.g., wind, solar photovoltaic) and battery energy storage. These energy resources require power electronic converters (PECs) to interconnect to the grid and have different response characteristics and dynamic stability issues compared to conventional synchronous generators. The design of data-driven state estimation and control techniques is discussed using emerging machine learning methods to improve the reliability of the future electric power grid. Specifically, neural ordinary differential equations (NODEs) and a soft-actor-critic (SAC) reinforcement learning framework are shown to infer critical power systems data faster in real time to assess and proactively mitigate extreme events.
