Learning the dominance in diploid genetic algorithms for changing optimization problems

Abstract

Using diploid representation with dominance scheme is one of the approaches developed for genetic algorithms to address dynamic optimization problems. This paper proposes an adaptive dominance mechanism for diploid genetic algorithms in dynamic environments. In this scheme, the genotype to phenotype mapping in each gene locus is controlled by a dominance probability, which is learnt adaptively during the searching progress. The proposed dominance scheme isexperimentally compared to two other schemes for diploid genetic algorithms. Experimental results validate the efficiency of the dominance learning scheme.