Homonuclear Molecules Optimization (HMO) meta-heuristic algorithm

Amin Mahdavi‐Meymand

doi:10.1016/j.knosys.2022.110032

Return

Homonuclear Molecules Optimization (HMO) meta-heuristic algorithm

2022-12-01

PRE

Amin Mahdavi‐Meymand

Mohammad Zounemat‐Kermani *

DOI：10.1016/j.knosys.2022.110032

Original

Original request for help

Save

Abstract

En 中文

This study introduces a novel meta-heuristic algorithm known as Homonuclear Molecules Optimization (HMO) for optimizing complex and nonlinear problems. HMO is inspired by the arrangement of electrons around atoms given the Bohr atomic model and the structure of homonuclear molecules. This algorithm is based on creating the initial population of a set of atoms in the search space and the electrons associated with each atom (searching agents) given the quantum numbers. In each iteration, the best electron of each atom is selected as the new location of the nucleus, and a number of atoms move toward the atom with the best solution to form a homonuclear molecule. The results of applying the MHO algorithm were evaluated in comparison with three classical optimization algorithms of PSO, GA, and DE along with a novel algorithm called Equilibrium Optimizer (EO). The HMO was able to precisely solve unimodal functions and find global and local solutions for multimodal functions. The outcomes of Wilcoxon's rank-sum test demonstrated that there is a significant difference between the final results of HMO and those of the other algorithms (a = 0.05%). Overall, it was concluded that the HMO outperforms the classical algorithms and can compete with new and efficient algorithms such as EO.(c) 2022 Elsevier B.V. All rights reserved.

Keywords:

Search algorithm

Non-linear optimization

Artificial intelligence

Swarm algorithm

Electron cloud