Paper ID: 2312.07034

GNBG-Generated Test Suite for Box-Constrained Numerical Global Optimization

Amir H. Gandomi, Danial Yazdani, Mohammad Nabi Omidvar, Kalyanmoy Deb

This document introduces a set of 24 box-constrained numerical global optimization problem instances, systematically constructed using the Generalized Numerical Benchmark Generator (GNBG). These instances cover a broad spectrum of problem features, including varying degrees of modality, ruggedness, symmetry, conditioning, variable interaction structures, basin linearity, and deceptiveness. Purposefully designed, this test suite offers varying difficulty levels and problem characteristics, facilitating rigorous evaluation and comparative analysis of optimization algorithms. By presenting these problems, we aim to provide researchers with a structured platform to assess the strengths and weaknesses of their algorithms against challenges with known, controlled characteristics. For reproducibility, the MATLAB source code for this test suite is publicly available.

Submitted: Dec 12, 2023