Keynote: Towards Automated Machine Learning on Imperfect Data for Situational Awareness in Power System
Speaker: Yunchuan Liu (Governors State University, Illinois, USA)
is an Assistant professor with the Division of Science Mathematics and Technology at Governors State University. He received his Ph.D. degree from the Department of Computer Science and Engineering at University of Nevada, Reno, in 2022. His current research interests include machine learning and data analytics for energy system applications. His paper has won the Best Paper Award at IEEE PES General Meeting 2022.
Abstract: Thanks to the wide deployment of sensors (e.g., phasor measurement units (PMUs)), which provide golden opportunities to achieve high level of situational awareness for reliable and cost-effective grid operations. However, the data collected from the real-world power system is of low quality (e.g., noisy, missing, insufficient and inaccurate timestamp data). Employing Machine Learning (ML) without considering these distinct features in real-world applications cannot build good ML models. 2 main contributions of our work:1) A novel machine learning framework is proposed for robust event classification to address the low data quality issues; 2) a weakly supervised learning framework is proposed to address the challenge of insufficient training labels.