IEEE Power & Energy Society Live Online Learning
Topic: A Machine Learning Framework for Stability Analysis of the Future Power Grids
Presented by: Dr. Jin Tan, National Renewable Energy Laboratory
With increasing penetrations of PV generation (including other distributed energy resources), future distribution systems, which will be governed by faster dynamics and complex dispatch mechanisms, requiring novel estimation and control of distribution-located assets. Open Energy Data Initiative – System Integration (OEDI-SI) is currently developing key software tools, datasets novel distribution state estimation, control optimization, and transient event analyses. This initiative will enable users to have access to open-source data and algorithms along with ability to incorporate user-specific data to perform distribution-level analyses. More specifically, the focus of the effort is on developing distribution system state estimation (DSSE), distribution optimal power flow (D-OPF), and transient event analysis. In this tutorial we will provide an overview and hands-on training on utilizing the tools developed in OEDI-SI by multiple National Labs and DOE.
Dr. Jin Tan is a principal engineer and a distinguished member of the research staff in the Grid Automation and Controls Group within the Power Systems Engineering Center at the National Renewable Energy Laboratory (NREL). She leads development of the Multi-Timescale Integrated Dynamic and Scheduling (MIDAS) framework to address the challenges of planning and operating extremely high renewable penetrated grid. She is also developing advanced electromagnetic transient (EMT) simulation capability for power grids with large numbers of distributed energy resources to study the stability of 100% renewables.