Performance Analysis of Different Operators in Genetic Algorithm for Solving Continuous and Discrete Optimization Problems

Abstract

Genetic algorithm (GA), as a powerful meta-heuristics algorithm, has broad applicability to different optimization problems. Although there are many researches about GA, few works have been done to synthetically summarize the impact of different genetic operators and different parameter settings on GA. To fill this gap, this paper has conducted extensive experiments on GA to investigate the influence of different operators and parameter settings in solving both continuous and discrete optimizations. Experiments on 16 nonlinear optimization (NLO) problems and 9 traveling salesman problems (TSP) show that tournament selection, uniform crossover, and a novel combination-based mutation are the best choice for continuous problems, while roulette wheel selection, distance preserving crossover, and swapping mutation are the best choices for discrete problems. It is expected that this work provides valuable suggestions for users and new learners. Copyright © 2021 by SCITEPRESS – Science and Technology Publications, Lda. All rights reserved.