Enhanced performance for multivariable optimization problems by use of GAs with recessive gene structure

Abstract

In this article we introduce the recessive gene model (RGM), as a tool in numerical function optimization with binary coded genetic algorithms (GAs). GAs are widely applied in many optimization problems, and usually their main setback is loss of diversity, leading to either evolutionary stagnation or premature convergence. The dual-gene system exploits local continuities in multivariable, multimodal functions, thereby ensuring optimal propagation and avoiding premature convergence. Our simulations show that the efficiency of RGM is superior to the usual analysis employing only dominant genes, that RGM performs better on small populations than the single dominant gene at the same computational cost, and that RGM occasionally performs the function of mutation.