Research in Random Parameters of Genetic Algorithm and Its Application on TSP and Optimization Problems

Abstract

In this paper, we consider a variety of random parameters of genetic algorithms based on some benchmark functions and traveling salesman problem (TSP). We have analyzed parameters of the genetic algorithm such as population size, crossover probability and mutation probability. The experiments have shown that we cannot propose a uniform model for the parameters of a genetic algorithm. However increasing of population size can reduce genetic algorithm iterations but crossover probability and also mutation probability strongly depend on benchmark functions. doi: 10.14456/WJST.2015.3