Different Environmental Conditions in Genetic Algorithm

TL;DR

This paper introduces an extended genetic algorithm that uses diverse local environmental conditions to enhance search efficiency, inspired by geographic isolation in natural evolution, and demonstrates improved performance in finding low-energy states in spin-glass systems.

Contribution

It presents a novel GA extension with environment-dependent local conditions, improving search efficiency for complex optimization problems.

Findings

Achieves lower-energy spin configurations more quickly.

Utilizes environment diversity to enhance global search.

Applicable as a meta-optimization method across various domains.

Abstract

We propose an extended genetic algorithm (GA) with different local environmental conditions. Genetic entities, or configurations, are put on nodes in a ring structure, and location-dependent environmental conditions are applied for each entity. Our GA is motivated by the geographic aspect of natural evolution: Geographic isolation reduces the diversity in a local group, but at the same time, can enhance intergroup diversity. Mating of genetic entities across different environments can make it possible to search for broad area of the fitness landscape. We validate our extended GA for finding the ground state of three-dimensional spin-glass system and find that the use of different environmental conditions makes it possible to find the lower-energy spin configurations at relatively shorter computation time. Our extension of GA belongs to a meta-optimization method and thus can be applied for a broad research area in which finding of the optimal state in a shorter computation time is the key problem.