An Elitist Polynomial Mutation Operator for Improved Performance of MOEAs in Computer Networks

Abstract

Polynomial mutation has been utilized in evolutionary optimization algorithms as a variation operator. In previous work on the use of evolutionary algorithms for solving multiobjective problems, two versions of polynomial mutations were introduced. In this study we will examine the latest version of polynomial mutation, the highly disruptive, which has been utilised in the latest version of NSGA-II. This paper proposes an elitist version of the highly disruptive polynomial mutation. The experimental results show that the proposed elitist polynomial mutation outperforms the existing mutation mechanism when applied in a well known evolutionary multiobjective algorithm (NSGA-II) in terms of hypervolume, spread of solutions and epsilon performance indicator.