基于一因多效的遗传算法研究

Study of genetic algorithms based on pleiotropy

在自然界中存在着"一因多效"的现象,即某一基因可影响生物的许多性状的生长发育。模仿这一生物现象,提出了基于一因多效的遗传算法,建立了基因型与表现型之间的一对多的非线性关系,打破了遗传算法中惯用的一一对应关系。并阐述了一因多效遗传算法有利于维护问题空间的多样性,从而可采用小规模种群来提高算法的运行效率。以求解Rosenbrock函数的全局最优解为例,通过与传统遗传算法的对比实验,证实了一因多效遗传算法的可行性。

In nature, pleiotropy is the effect that a single gene may simultaneously affect several phenotypic traits. Simulating pleiotropy of biology, a genetic algorithm based on pleiotropy is proposed. The nonlinear function between the genotype and phenotype or one-to-many mapping relationship is built, which breaks out one-to-one mapping in traditional genetic algorithm. Pleiotropy has an advantage to maintain the diversity of the problem space so, the run rate can be improved by using small population size. Compared with the traditional GA for the global optimization of Rosenbrock function, the results show the proposed algorithm is efficient.