“21st PSCC 2020 papers submission and review platform

Full Program »

Learning to Control in Power Systems: Design and Analysis Guidelines for Concrete Safety Problems

View File
PDF
0.9MB

Rapid progress in machine learning and artificial intelligence (AI) has brought renewed attention to its applicability in power systems for modern forms of control that help integrate higher levels of renewable generation and address increasing levels of uncertainty and variability. In this paper we discuss these new applications and shine light on the most relevant new safety risks and considerations that emerge when relying on learning for control purposes in electric grid operations. We build on recent taxonomical work in AI safety and focus on four concrete safety problems. We draw on two case studies, one in frequency regulation and one in distribution system control, to exemplify these problems and show mitigating measures. We then provide general guidelines and literature to help people working on integrating learning capabilities for control purposes to make safety risks a central tenet of design.

Author(s):

Roel Dobbe    
AI Now Institute, New York University
United States

Patricia Hidalgo-Gonzalez    
University of California, Berkeley
United States

Stavros Karagiannopoulos    
EEH - Power Systems Laboratory, ETH Zurich
Switzerland

Rodrigo Henriquez-Auba    
University of California, Berkeley
United States

Gabriela Hug    
EEH - Power Systems Laboratory, ETH Zurich
Switzerland

Duncan S. Callaway    
University of California, Berkeley
United States

Claire J. Tomlin    
University of California, Berkeley
United States

 

Powered by OpenConf®
Copyright ©2002-2014 Zakon Group LLC