Self-Adaptive Genetic Algorithms with Simulated Binary Crossover

Abstract

Self-adaptation is an essential feature of natural evolution. However, in the context of function optimization, self-adaptation features of evolutionary search algorithms have been explored mainly with evolution strategy (ES) and evolutionary programming (EP). In this paper, we demonstrate the self-adaptive feature of real-parameter genetic algorithms (GAs) using a simulated binary crossover (SBX) operator and without any mutation operator. The connection between the working of self-adaptive ESs and real-parameter GAs with the SBX operator is also discussed. Thereafter, the self-adaptive behavior of real-parameter GAs is demonstrated on a number of test problems commonly used in the ES literature. The remarkable similarity in the working principle of real-parameter GAs and self-adaptive ESs shown in this study suggests the need for emphasizing further studies on self-adaptive GAs.

Brief Review of Techniques Used to Develop Adaptive Evolutionary Algorithms

“…A propose of the use of a crossover operator named simulated binary reproduction (SBX) on real genetic algorithms is presented by Deb and Beyer [8]. The purpose is to obtain similar results as evolutionary strategies, but using genetic algorithms.…”

Selection-Insertion Schemes in Genetic Algorithms for the Flexible Ligand Docking Problem

“…-The simulated binary crossover (SBX), which assigns more probability for offspring to remain closer to their parents than away from them, generates two offspring as described in [23]. -The non-uniform mutation (NUM) operator [24], when applied to an individual x i at generation gen, mutates a randomly chosen variable x j i according to…”

An Adaptive Penalty Scheme for Steady-State Genetic Algorithms

“…The operators used were: (i) random mutation (which modifies a randomly chosen variable of the selected parent to a random value uniformly distributed between the lower and upper bounds of the corresponding variable), (ii) non-uniform mutation (as proposed by Michalewicz [30]), (iii) Muhlenbein's mutation (as described in [31]), (iv) multi-parent discrete crossover (which generates an offspring by randomly taking each allele from one of the n p selected parents), and (v) Deb's SBX crossover as described in [32].…”