An introduction to a novel crossover operator for real-value encoded genetic algorithm: Gaussian crossover operator

Abstract

The following article describes a novel implementation of a crossover operator for real-value encoded Genetic Algorithms (GA). The method, Gaussian Crossover Operator (GCO), utilizes the properties of Gaussian functions and Gaussian distribution for offspring generation. Each parent's fitness is evaluated in the context of general population by a heuristic function, i.e. the devised operator is performance based — the parents' individual fitness values act as a basis for a non-deterministic weighing mechanism. The child's gene value is a Gaussian Variable drawn upon the normal distribution determined by the overall state of the algorithm and the antecedent's evaluation. The performance of the algorithm is discussed and compared with the underlaying classical Genetic Algorithm and other GA implementations found in the literature; several test cases are considered. The results show that the proposed Gaussian Crossover Operator is feasible for solving optimization problems.