标题：An Improved Evolutionary Strategy of Genetic Algorithm and a New Method on Generation of Initial Population When Using Genetic Algorithms for Solving Constrained Optimization Problems
期刊名称：International Journal of Hybrid Information Technology
印刷版ISSN：1738-9968
出版年度：2014
卷号：7
期号：4
页码：331-344
DOI：10.14257/ijhit.2014.7.4.28
出版社：SERSC
摘要：The paper provides an improved evolutionary strategy (ES) of genetic algorithm (GA) on the basis of the existing literature. The ES overcomes the shortage of traditional GA whose excellent child individuals obtained in the crossover process may not survive in the process of mutation. In addition, the crossover probability and mutation probability which is hard to determine in traditional GA is removed for this proposed strategy. At the same time, it increases the number of individuals produced in process of crossover. This may increase the possibility of producing excellent individuals, thus lead to better improvement of the traditional GA. The test result of finding the optimal values of four functions using transitional GA and the proposed GA is presented in this paper. The result shows that the improved ES presented in this paper has faster calculation speed and significantly smaller number of iterations than the traditional GA. Thus, the improvement of improved ES is powerfully illustrated. Based on articles in the existing research literature, the initial population generation methods were further explored when using the genetic algorithm(GA) for solving constrained optimization problem. Through the research we present a new method about initial interior point's generation. Firstly, construct a constraint posed by the objective function, which is based on the characteristics of constrained optimization problems. Then translate the problem of evaluating the initial interior point into a problem of solving a series of unconstrained optimization. By solving the unconstrained optimization problem, we achieve the solution of the initial interior point. Based on this idea, the research has given a method on the generation of the rest initial population individuals. In addition, through the research we concluded that the key to generate the initial population is to obtain an initial point. The production of other individuals will take less time after the initial internal point is obtained. Finally, we verified by examples that the initial population generation method given by this paper is a fast and reliable method. Thus the shortage of the GA of which the initial population is difficult to be produced in some constrained optimization problem is overcome.
关键词：We would like to encourage you to list your keywords in this section. Genetic ; algorithm; Evolutionary strategies; Crossover probability; mutation probability; Initial ; interior point; Initial population; Constrained optimization problem
