Keynote

Topic

Synergistic Integration of Machine Learning and Mathematical Optimization for Difficult Optimization Problems

Professor Peter B. Luh

Abstract

　　Many important optimization problems in manufacturing and power systems involve discrete decision variables, and the complexity to obtain an optimal solution increases exponentially as the problem size increases, limiting solution quality or problem sizes that can be effectively solved. Also, there is “no learning” in optimization – after a problem instance is solved, to solve a different instance, we usually need start the solution process all over again. When machine learning is used to solve such problems, success is generally limited to small problems because of complexity.

　　The above ideas will be presented by using unit commitment of power systems and job shop scheduling of manufacturing systems as examples.

Speaker

Prof. Peter B. Luh   Board of Trustees Distinguished Professor SNET Professor, Communications & Information University of Connecticut Storrs, Connecticut, USA Distinguished Chair Professor, Department of Electrical Engineering National Taiwan University Taipei, Taiwan, R.O.C Contact: peter.luh@uconn.edu

　　Peter Luh received his B.S. from National Taiwan University, M.S. from M.I.T., and Ph.D. from Harvard University. He was with the University of Connecticut from 1980 to 2020, and was a Board of Trustees Distinguished Professor and the SNET Professor of Communications & Information Technologies upon retirement in early 2021. He is now a Distinguished Chair Professor at the Department of Electrical Engineering at the National Taiwan University and a YuShan Scholar.

　　Professor Luh is a Life Fellow of IEEE, a member of IEEE Publication Services and Products Board (PSPB), and the Chair of PSPB's Publishing Conduct Committee overseeing IEEE plagiarism and publishing ethics violation cases. He was the founding Editor-in-Chief of the IEEE Transactions on Automation Science and Engineering (T-ASE 2003-2007), a co-founder of IEEE Conference on Automation Science and Engineering series; the Chair of IEEE TAB Periodicals Committee (2018-19) overseeing 200+ IEEE journals and magazines from cradle to grave; and the Chair of IEEE TAB Periodicals Review and Advisory Committee (2020-21) periodically reviewing these journals and magazines. His research interests include intelligent manufacturing, smart grid, energy-smart buildings, and mathematical optimization of complex mixed-integer problems with combinatorial complexity. He received IEEE Robotics and Automation Society 2013 Pioneer Award, 2017 George Saridis Leadership Award, and 2018 IEEE T-ASE Best Paper Award.