Surrogate-based Optimization via Clustering for Box-Constrained Problems

TL;DR

This paper introduces SBOC, a clustering-based surrogate optimization framework that efficiently finds global minima in complex, high-dimensional box-constrained problems by combining surrogate modeling, clustering, and local search.

Contribution

It proposes a novel SBOC framework that integrates clustering with surrogate models for scalable, effective global optimization of large-scale systems.

Findings

Successfully identified global minima with less computational effort.

Performed well on high-dimensional test functions with four or more variables.

Ranked among top algorithms in approaching global minima closely.

Abstract

Global optimization of large-scale, complex systems such as multi-physics black-box simulations and real-world industrial systems is important but challenging. This work presents a novel Surrogate-Based Optimization framework based on Clustering, SBOC for global optimization of such systems, which can be used with any surrogate modeling technique. At each iteration, it uses a single surrogate model for the entire domain, employs k-means clustering to identify unexplored domain, and exploits a local region around the surrogate optimum to potentially add three new sample points in the domain. SBOC has been tested against sixteen promising benchmarking algorithms using 52 analytical test functions of varying input dimensionalities and shape profiles. It successfully identified a global minimum for most test functions with substantially lower computational effort than other algorithms. It worked especially well on test functions with four or more input variables. It was also among the top six algorithms in approaching a global minimum closely. Overall, SBOC is a robust, reliable, and efficient algorithm for global optimization of box-constrained systems.