Constraint handling in efficient global optimization

Bagheri, Samineh; Konen, Wolfgang; Allmendinger, Richard; Branke, Jürgen; Deb, Kalyanmoy; Fieldsend, Jonathan E.; Quagliarella, Domenico; Sindhya, Karthik

doi:10.1145/3071178.3071278

Cited by 29 publications

(11 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, the concept has been generalized to solve multi-objective optimization problems by using decomposition [21] or replacing the objective with a performance indicator-based metric [25]. The idea has also been extended to handle constraints, which is especially important for solving real-world optimization problems [2]. Because much effort has been made to extend the initially proposed concept, this can be considered a rather general approach.…”

Section: Related Workmentioning

confidence: 99%

Psaf

Blank

Deb

2021

Proceedings of the Genetic and Evolutionary Computation Conference

Self Cite

View full text Add to dashboard Cite

In the last two decades, significant effort has been made to solve computationally expensive optimization problems using surrogate models. Regardless of whether surrogates are the primary drivers of an algorithm or improve the convergence of an existing method, most proposed concepts are rather specific and not very generalizable. Some important considerations are selecting a baseline optimization algorithm, a suitable surrogate methodology, and the surrogate's involvement in the overall algorithm design. This paper proposes a probabilistic surrogate-assisted framework (PSAF), demonstrating its applicability to a broad category of single-objective optimization methods. The framework injects knowledge from a surrogate into an existing algorithm through a tournament-based procedure and continuing the optimization run on the surrogate's predictions. The surrogate's involvement is determined by updating a replacement probability based on the accuracy from past iterations. A study of four well-known population-based optimization algorithms with and without the proposed probabilistic surrogate assistance indicates its usefulness in achieving a better convergence. The proposed framework enables the incorporation of surrogates into an existing optimization algorithm and, thus, paves the way for new surrogate-assisted algorithms dealing with challenges in less frequently addressed computationally expensive functions, such as different variable types, large dimensional problems, multiple objectives, and constraints. CCS CONCEPTS• Theory of computation → Nonconvex optimization; Bioinspired optimization.

show abstract

Section: Related Workmentioning

confidence: 99%

Psaf

Blank

Deb

2021

Proceedings of the Genetic and Evolutionary Computation Conference

Self Cite

View full text Add to dashboard Cite

show abstract

“…The details of the implementation of the EGO algorithm are given in 19, 23, 43, 44. The EGO algorithm above requires the size of the initial design point and a convergence criterion.…”

Section: Numerical Modelmentioning

confidence: 99%

“…The EGO algorithm with constrained expected improvement (CEI) approach 43 was selected and used as the optimization tool to maximize carbon conversion and rate of methanol production and to handle the maximum temperature constraint. The modification proposed by 44 was applied to CEI for better constraint management. A properly trimmed absolute deviation (SCAD) penalty 45 was applied during the hyper parameter estimation of the Kriging model.…”

Section: Introductionmentioning

confidence: 99%

Derivative‐Free Optimization of a Fixed‐Bed Methanol Synthesis Reactor

Obut

2021

Chem Eng & Technol

View full text Add to dashboard Cite

A one‐dimensional heterogeneous fixed‐bed methanol synthesis reactor model was developed for the optimization of carbon conversion and rate of methanol production. The developed model was validated both at pellet and reactor scales. The reactor inlet syngas composition and cooling water temperature, i.e., the design variables, providing the highest carbon conversion and rate of methanol production were determined by a constrained derivative‐free optimization algorithm. The results revealed that after optimization the carbon conversion was increased by 12 % and the rate of methanol production by 48 %. Under the optimized conditions, the stoichiometric number was in the range of industrial values.

show abstract

“…The EI in the presence of constraints is defined as the expected value of I(ϑ) conditional on the observations (see, e.g., [4]). Under the same assumptions…”

Section: Improvement-based Infill Criteriamentioning

confidence: 99%

Constrained multi-fidelity surrogate framework using Bayesian optimization with non-intrusive reduced-order basis

Khatouri

Benamara

Breitkopf

et al. 2020

Adv. Model. and Simul. in Eng. Sci.

View full text Add to dashboard Cite

This article addresses the problem of constrained derivative-free optimization in a multi-fidelity (or variable-complexity) framework using Bayesian optimization techniques. It is assumed that the objective and constraints involved in the optimization problem can be evaluated using either an accurate but time-consuming computer program or a fast lower-fidelity one. In this setting, the aim is to solve the optimization problem using as few calls to the high-fidelity program as possible. To this end, it is proposed to use Gaussian process models with trend functions built from the projection of low-fidelity solutions on a reduced-order basis synthesized from scarce high-fidelity snapshots. A study on the ability of such models to accurately represent the objective and the constraints and a comparison of two improvement-based infill strategies are performed on a representative benchmark test case.

show abstract

Constraint handling in efficient global optimization

Cited by 29 publications

References 15 publications

Psaf

Psaf

Derivative‐Free Optimization of a Fixed‐Bed Methanol Synthesis Reactor

Constrained multi-fidelity surrogate framework using Bayesian optimization with non-intrusive reduced-order basis

Contact Info

Product

Resources

About