June 4, 11 & 18, 2021 Free and Open to the Public – No Registration Required Attend: Zoom Meeting (You may need to authenticate through your institution’s Zoom account before joining)
Watch: YouTube Live Stream (From our YouTube Channel, select the “Live Now” stream)
Electricity is the lifeblood of our society, and providing a reliable and efficient electricity supply is key to ensuring its welfare and sustainable economic growth. Modern power systems are experiencing fundamental transformations in structure and functionality driven by the integration of new technologies; these include renewable-based generation, Distributed Energy Resources (DERs), advanced sensors and controls.
This integration creates new opportunities to make power systems more efficient and reliable, but they also pose numerous operational challenges. For example, renewable-based generation, while enabling electricity decarbonization, increases power supply variability and uncertainty. In addition, the increased reliance on advanced sensors and distributed control schemes for DER coordination poses serious cybersecurity and privacy issues. On three consecutive Fridays in June, this workshop will explore three major domains in power systems — dynamics, control, and protection; cybersecurity and privacy; and markets and optimization — and their relationship to capabilities emerging from machine learning and artificial intelligence research to address the aforementioned challenges. Each day of the workshop will focus on one of the three domains by bringing together four experts to give a talk and then take part in a panel discussion that involves answering questions from the audience.
ORGANIZERS Duncan Callaway (University of California, Berkeley), Alejandro Domínguez-García (University of Illinois at Urbana-Champaign), and Marija Ilic (Massachusetts Institute of Technology) SPEAKERS Tamer Başer (University of Illinois at Urbana-Champaign), Daniel Bienstock (Columbia University), Spyros Chatzivasileiadis (Technical University of Denmark), Christine Chen (University of British Columbia), Zico Kolter (Carnegie Mellon University), Na Li (Harvard University), Scott Moura (University of California, Berkeley), Ram Rajagopal (Stanford University), Anna Scaglione (Arizona State University), Pascal Van Hentenryck (Georgia Institute of Technology), Louis Wehenkel (University of Liege), Baosen Zhang (University of Washington) PROGRAM (All times are Pacific Time) Day 1: Infrastructure Protection and Control 9:00 am – 9:45 am: Ram Rajagopal (Stanford University) 9:45 am – 10:30 am: Safe and Efficient Reinforcement Learning for Power System Control, Baosen Zhang (University of Washington) 10:30 am – 10:45 am: Break 10:45 am – 11:30 am: Removing Barriers for Machine Learning Applications in Power System, Spyros Chatzivasileiadis (Technical University of Denmark) 11:30 am – 12:15 pm: Incorporating Constraints into Deep Learning, with Application to Grid Optimization, Zico Kolter (Carnegie Mellon University) 12:15 pm – 12:30 pm: Break 12:30 pm – 1:30 pm: Panel Discussion Day 2: Cybersecurity and Privacy 9:00 am – 9:45 am: Policy Optimization for Robust and Secure Reinforcement Learning, Tamer Başer (University of Illinois at Urbana-Champaign) 9:45 am – 10:30 am: Differential Privacy in Power Systems, Pascal Van Hentenryck (Georgia Institute of Technology) 10:30 am – 10:45 am: Break 10:45 am – 11:30 am: Grid Graph Signal Processing: Theory and Practical Applications, Anna Scaglione (Arizona State University) 11:30 am – 12:15 pm: Data Science and Financial Engineering in Day-Ahead Markets, Daniel Bienstock (Columbia University) 12:15 pm – 12:30 pm: Break 12:30 pm – 1:30 pm: Panel Discussion Day 3: Markets, OPF, and Demand Side Response 9:00 am – 9:45 am: Learning and Control of Residential Demand Response, Na Li (Harvard University) 9:45 am – 10:30 am: Learning & Optimization of Distributed Energy Resources: SlrpEV and Hopfield Methods, Scott Moura (University of California, Berkeley) 10:30 am – 10:45 am: Break 10:45 am – 11:30 am: Machine Learning for Optimal Decision Making in Bulk Power Systems Reliability Management, Louis Wehenkel (University of Liege) 11:30 am – 12:15 pm: Deep Reinforcement Learning for Demand Response in Distribution Networks, Christine Chen (University of British Columbia) 12:15 pm – 12:30 pm: Break 12:30 pm – 1:30 pm: Panel Discussion
|