Some Further Experiments with Crossover Operators for Genetic Algorithms

Article type: Research Article

Authors: Misevičius, Alfonsas^{; *} | Kuznecovaitė, Dovilė | Platužienė, Jūratė

Affiliations: Kaunas University of Technology, Department of Multimedia Engineering, Studentų st. 50-400/416a, LT-51368 Kaunas, Lithuania. E-mails: [email protected], [email protected], [email protected]

Correspondence: [*] Corresponding author.

Abstract: Crossover operators play a very important role by creation of genetic algorithms (GAs) which are applied in various areas of computer science, including combinatorial optimization. In this paper, fifteen genetic crossover procedures are designed and implemented using a modern C# programming language. The computational experiments have been conducted with these operators by solving the famous combinatorial optimization problem – the quadratic assignment problem (QAP). The results of the conducted experiments on the characteristic benchmark instances from the QAP instances library QAPLIB illustrate the relative performance of the examined crossover operations. All crossover procedures are publicly available with the intention that the GA researchers will choose a procedure which suits the individual demand at the highest degree.

Keywords: metaheuristic methods, genetic algorithms, genetic crossover operators, combinatorial optimization, quadratic assignment problem

Journal: Informatica, vol. 29, no. 3, pp. 499-516, 2018