Title: Mining Smart Meter Data for Improving Distribution Grid Operation and Resilience
Date: November 11, 2019
Bio: Dr. Zhaoyu Wang is the Harpole-Pentair Endowed Assistant Professor with Iowa State University.
He received the B.S. and M.S. degrees in electrical engineering from Shanghai Jiaotong University in
2009 and 2012, respectively, and the M.S. and Ph.D. degrees in electrical and computer engineering
from Georgia Institute of Technology in 2012 and 2015, respectively. He was a Research Aid at Argonne
National Laboratory in 2013 and an Electrical Engineer Intern at Corning Inc. in 2014. His research
interests include power distribution systems, microgrids, renewable integration, power system resilience,
and power system modeling. He is the Principal Investigator for a multitude of projects focused on these
topics and funded by the National Science Foundation, the Department of Energy, National Laboratories,
PSERC, Iowa Energy Center, and Industry. Dr. Wang received the IEEE PES General Meeting Best
Paper Award in 2017 and 2019, and the IEEE Industrial Application Society Prize Paper Award in 2016.
Dr. Wang is the Secretary of IEEE Power and Energy Society (PES) Award Subcommittee, Co-Vice
Chair of PES Distribution System Operation and Planning Subcommittee, and Vice Chair of PES Task
Force on Advances in Natural Disaster Mitigation Methods. He is an editor of IEEE Transactions on
Power Systems, IEEE Transactions on Smart Grid and IEEE PES Letters and an associate editor of IET
Smart Grid.
Abstract: In the past few years, Iowa State University has been collecting a large amount of smart
meter, PMU and SCADA data and associated grid models from collaborating utilities. This talk will
focus on smart meter data analysis and how they can benefit utility operations. We will begin the talk
by introducing the real smart meter data and one utility dataset that we share with the research
community. Then we will introduce the data cleaning as well as the basic knowledge on statistics and
machine learning to extract useful information from the data. By leveraging the smart meter data, we
have proposed a multi-timescale learning model that enables utilities to infer hourly consumption
patterns of unobservable customers using only their monthly billing information, thus significantly
enhancing the grid observability. Further, the smart meter data has been used to develop a model-free
framework to estimate cold load pick-up to assist utilities in making better service restoration plans and
enhancing grid resilience.