BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Department of Electrical and Computer Engineering (HKUECE) 電機與計算機工程系 - ECPv6.16.0//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-ORIGINAL-URL:https://ece.hku.hk
X-WR-CALDESC:Events for Department of Electrical and Computer Engineering (HKUECE) 電機與計算機工程系
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:Asia/Hong_Kong
BEGIN:STANDARD
TZOFFSETFROM:+0800
TZOFFSETTO:+0800
TZNAME:HKT
DTSTART:20230101T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Asia/Hong_Kong:20240110T110000
DTEND;TZID=Asia/Hong_Kong:20240110T120000
DTSTAMP:20260513T064928
CREATED:20240102T063048Z
LAST-MODIFIED:20250114T074608Z
UID:17912-1704884400-1704888000@ece.hku.hk
SUMMARY:Machine Learning for Real-Time Constrained Optimization: The Case of Optimal Power Flows
DESCRIPTION:Optimization problems subject to hard constraints are common in time-critical applications such as autonomous driving and wireless communication. However\, existing iterative solvers often face difficulties in solving these problems in real-time. In this talk\, we focus on one such problem – the critical optimal power flow (OPF) problem in power system operation. We develop DeepOPF as a neural network (NN) approach to solve OPF problems directly\, orders of magnitude faster than state-of-the-art iterative solvers. The idea is to employ NN’s approximation capability to learn the input-solution mapping of the OPF problem (or any constrained problem). Thus\, one can pass the input to the NN and receive a quality solution instantly. A fundamental issue\, however\, is to ensure NN solution feasibility with respect to the hard constraints\, which is non-trivial due to inherent NN prediction errors. To this end\, we present two approaches\, predict-and-reconstruct and homeomorphic projection\, to ensure NN solution strictly satisfies the equality and inequality constraints. In particular\, homeomorphic projection is a low-complexity scheme to guarantee NN solution feasibility for optimization over a general set homeomorphic to a unit ball\, covering all compact convex sets and certain classes of nonconvex sets. The idea is to (i) learn a minimum distortion homeomorphic mapping between the constraint set and a unit ball using an invertible NN (INN)\, and then (ii) perform a simple bisection operation concerning the unit ball so that the INN-mapped final solution is feasible with respect to the constraint set with minor distortion-induced optimality loss. We prove the feasibility guarantee and bound the optimality loss under mild conditions. Simulation results\, including those for non-convex AC-OPF problems in power grid operation\, show that homeomorphic projection outperforms existing methods in solution feasibility and run-time complexity\, while achieving similar optimality loss. We will also discuss open issues in machine learning for solving constrained puzzles. \nBiography of the speaker: \nMinghua received his B.Eng. and M.S. degrees from the Department of Electronic Engineering at Tsinghua University. He received his Ph.D. degree from the Department of Electrical Engineering and Computer Sciences at University of California Berkeley. He is a Professor of School of Data Science\, City University of Hong Kong. He received the Eli Jury award from UC Berkeley in 2007 (presented to a graduate student or recent alumnus for outstanding achievement in the area of Systems\, Communications\, Control\, or Signal Processing) and The Chinese University of Hong Kong Young Researcher Award in 2013. He also received several best paper awards\, including IEEE ICME Best Paper Award in 2009\, IEEE Transactions on Multimedia Prize Paper Award in 2009\, ACM Multimedia Best Paper Award in 2012\, IEEE INFOCOM Best Poster Award in 2021\, and ACM e-Energy Best Paper Award in 2023. Storage codes co-invented by Minghua have been incorporated into Microsoft Windows and Azure Cloud Storage\, serving hundreds of millions of users. His recent research interests include online optimization and algorithms\, machine learning in power system operation\, intelligent transportation\, distributed optimization\, delay-critical networking\, and capitalizing the benefit of data-driven prediction in algorithm/system design. He is an ACM Distinguished Scientist and an IEEE Fellow.
URL:https://ece.hku.hk/events/machine-learning-for-real-time-constrained-optimization-the-case-of-optimal-power-flows/
CATEGORIES:Seminar
ATTACH;FMTTYPE=image/jpeg:https://ece.hku.hk/wp-content/uploads/2024/02/Seminar-s-banner.jpg
END:VEVENT
END:VCALENDAR