Processes and Benchmarks for Extreme Event Analysis in Power Systems

October 2022

Extreme events, such as heat waves or very strong storms, may cause extensive damage and have substantial impacts on power systems, which post extreme challenges to system operation entities. As the large power infrastructure in the US ages, better understanding and preparing for extreme events is a much needed effort for researchers, operators, and planners. We need approaches to increase grid resiliency and recovery capabilities, as well as improved procedures for decision making and damage evaluation. On the other hand, every extreme event is also a rare learning opportunity. For example, the severe weather event of February 2021, winter storm Uri in Texas, has initiated many studies in academia and industry to examine and improve the ERCOT power grid and utilities’ operating procedures. With all the efforts and achievements, we are hardening and preparing the power grid for future challenges.

Active Committees/Task Forces of Interest
  • To learn more & get involved, please check out the AMPS website.
  • The Big Data Webinar Series WG under AMPS BDA Subcommittee has a tutorial series where experts from industry and academia are invited to speak about a large variety of trending topics including extreme events.
Technical Reports & Applicable Papers or Presentations
Other Available Material

Inverter-based Resources Subsynchronous Oscillations: Events and Mechanism Analysis 
IEEE-PES Webinar: July 2022
Lingling Fan (USF), Yunzhi Cheng (ERCOT), Jayanth R. Ramamurthy (AEMO), Xiaorong Xie (Tsinghua Univ), Jan Shair (Tsinghua University) , Zhixin Miao (USF) IBR SSO Task Force 

This webinar presents a survey of real-world subsynchronous oscillation events associated with inverter-based resources (IBR) over the past decade.

Physics-aware and Risk-aware Machine Learning for Power System Operations

IEEE-PES Webinar: February 2022
Hao Zhu

Recent years have witnessed rapid transformations of contemporary advances in machine learning (ML) and data science to aid the transition of energy systems into a truly sustainable, resilient, and distributed infrastructure. A blind application of the latest-and-greatest ML algorithms to solve stylized grid operation problems, however, may fail to recognize the underlying physics models or safety constraint requirements. This talk will introduce three examples of bridging physics- and risk-aware ML advances into efficient and reliable grid operations. First, we develop a topology-aware approach using graph neural networks (GNNs) to predict the price and line congestion as the outputs of real-time optimal power flow problem. Building upon the underlying relation between prices and topology, this proposed solution significantly reduces the model complexity of existing end-to-end ML methods while efficiently adapting to varying grid topology. Second, we put forth a risk-aware ML method to ensure the safety guarantees of data-driven, scalable reactive power dispatch policies in distribution grids. The resultant policies can directly account for the statistical risks on prediction error to attain guaranteed voltage violation performance. Last, we consider a reinforcement learning framework for managing a large number of dynamical, flexible energy resources such as electrical vehicles, and demonstrate the need to simplify the system representation through physics-aware state/action aggregation.

Predicting the onset of cascading failures using machine learning

General Meeting Panel Session: July 2022

Panel session from IEEE PES GM 2022.

Late Breaking News – Texas Energy Crisis

General Meeting Panel Session: July 2021
W-J Lee, T. Pierpoint, D. Ortiz, M. Lauby, M. Carpenter

This panel of diverse industry leaders will discuss the realities of the situation and provide balanced perspective on mechanisms through which the effects could be mitigated in the future.