Selection Techniques in Genetic Algorithm

Genetic algorithms (GA) are search engines that either optimize or reduce predefined functions. The technique of selection is an important phase in GA. This research study aims to evaluate, compare, and rank the selection techniques in GA. The evaluated selection techniques are; roulette wheel selection, elitist selection, rank selection, tournament selection, truncation selection, Boltzmann selection, and stochastic Universal Sampling selection. The comparison was based on the following selected criteria; (performance accuracy, fitness value accuracy, execution time, preservation of diversity, computational cost, ease of use, and bias levels. The paper incorporates the aforementioned criteria into the fuzzy preference ranking organization method for enrichment evaluation (PROMETHEE). This decision-making tool was used to determine the most preferred selection techniques in GA. The results from this research study showed that with an outranking net flow of 0.0690 elitism was determined as the most effective selection technique for GA based on the given criteria and their importance levels. Followed by the tournament selection technique with a positive net flow of 0.0343 and then, the rank selection technique, roulette wheel selection technique, truncation selection technique, and stochastic universal sampling selection technique occupied the third, fourth, fifth, and sixth positions with a net flow of 0.0078, -0.0102, -0.0116, -0.0156. Boltzmann selection technique ranked least among the considered selection techniques with a net flow of -0.0738 due to its features with all the criteria. With this study, we have provided a supportive tool for the decision-makers in the selection of the genetic algorithm techniques, and we have shown the applicability of the fuzzy PROMETHEE approach in this case by providing the advantages and disadvantages of each decision point.