MEchanics GAthering –MEGA- Seminar: Constrained Efficient Global Optimization of Expensive Black-box Functions
Abstract:
Optimizing the performance of unknown black-box systems with unmodeled constraints is a ubiquitous problem in science and engineering. In this talk, I will present the CONFIG algorithm, a simple and provably efficient constrained global optimization algorithm to solve it. We also demonstrate the effectiveness of CONFIG algorithm in the applications. It is first applied to a set of artificial numerical benchmark problems to corroborate its effectiveness. It is then applied to a classical constrained steady-state optimization problem of a continuous stirred-tank reactor. Simulation results show that our CONFIG algorithm can achieve performance competitive with the popular CEI algorithm, which has no known optimality guarantee. As such, the CONFIG algorithm offers a new tool, with both a global optimality guarantee and competitive empirical performance, to optimize the performance for a black-box system with soft unmodeled constraints. Last, but not least, the open-source code is available as a python package to facilitate future applications.
Biography:
Wenjie Xu is a Ph.D. candidate in Electrical Engineering with the Automatic Control Laboratory, EPFL, and a guest Ph.D. student with the Urban Energy Systems Laboratory at Empa. He is jointly supervised by Prof. Colin Jones at EPFL and Dr. Bratislav Svetozarevic from Empa. He received MPhil degree from The Chinese University of Hong Kong in 2020 and B.E. degree from Tsinghua University in 2018. His research interests include data-driven optimization, controller tuning, intelligent transportation, and smart energy systems, with research results published in IEEE journals (T-ITS, T-NNLS), ACM conferences (MobiHoc, BuildSys) and control conferences (ACC, IFAC). He received the ASME Energy Systems Technical Committee Best Paper Award at the 2022 American Control Conference.
Optimizing the performance of unknown black-box systems with unmodeled constraints is a ubiquitous problem in science and engineering. In this talk, I will present the CONFIG algorithm, a simple and provably efficient constrained global optimization algorithm to solve it. We also demonstrate the effectiveness of CONFIG algorithm in the applications. It is first applied to a set of artificial numerical benchmark problems to corroborate its effectiveness. It is then applied to a classical constrained steady-state optimization problem of a continuous stirred-tank reactor. Simulation results show that our CONFIG algorithm can achieve performance competitive with the popular CEI algorithm, which has no known optimality guarantee. As such, the CONFIG algorithm offers a new tool, with both a global optimality guarantee and competitive empirical performance, to optimize the performance for a black-box system with soft unmodeled constraints. Last, but not least, the open-source code is available as a python package to facilitate future applications.
Biography:
Wenjie Xu is a Ph.D. candidate in Electrical Engineering with the Automatic Control Laboratory, EPFL, and a guest Ph.D. student with the Urban Energy Systems Laboratory at Empa. He is jointly supervised by Prof. Colin Jones at EPFL and Dr. Bratislav Svetozarevic from Empa. He received MPhil degree from The Chinese University of Hong Kong in 2020 and B.E. degree from Tsinghua University in 2018. His research interests include data-driven optimization, controller tuning, intelligent transportation, and smart energy systems, with research results published in IEEE journals (T-ITS, T-NNLS), ACM conferences (MobiHoc, BuildSys) and control conferences (ACC, IFAC). He received the ASME Energy Systems Technical Committee Best Paper Award at the 2022 American Control Conference.
Practical information
- General public
- Free
Organizer
- MEGA.Seminar Organizing Committee