A Multi-subpopulation Accelerating Genetic Algorithm based on Attractors (MAGA): Performance in Function Optimization

摘要

A multi-subpopulation accelerating genetic algorithm based on attractors (MAGA) is proposed to cope with the drawback of genetic algorithms. MAGA views the excellent individuals as attractors and generates local small populations in the neighbor of them to maintain the diversity of the population. In the course of searching, MAGA constantly shrinks the searching neighbor and uses the accelerating operators to speed up the evolution of MAGA. The convergence analysis shows MAGA can converge to global optimization under some circumstances. Finally, MAGA's efficiency is validated through optimization of two benchmark functions.