Applied Research Of The Multiobjective Genetic Algorithms By Dominative-Recessive Diploid Codes

Genetic algorithms is a global optimization search algorithms based on the population evolution, and the chromosome structure of high biology in nature is often Diploid or polyploid as they have dominative and recessive genes. By using the above two concepts, this paper presents a new algorithms, which is named dominance-recessive diploid codes multiobjective genetic algorithms, to solve the multiobjective optimization through the introduction of a new dominative- recessive codes. Given the Scheme Theorem, the feasibility of such a code is provided. Then, search capability and diversity of solutions between this algorithms and the binary algorithms in the aspect of solution search space is compared, with the solutions Quantitative described. Furthermore, by using the Numerical experiments of three Classic multiobjective optimization test functions, this algorithms and the efficient binary multiobjective algorithms named niched pareto genetic alogorithms are compared. From the solution, we know that this paper's algorithms is obviously superior to the niched pareto genetic alogorithms about the distribution, convergence of solution and the capability of anti-prematurity. Thus, It is interpreted that the algorithm is feasible from the aspects of theoretic analysis and numerical experiments, and pareto solutions can be came to.