基于种群多样性的自适应遗传算法优化仿真

摘要

An improved adaptive genetic algorithm is proposed to solve the problem of "premature" and slow convergence speed of traditional genetic algorithm.The algorithm introduces the population diversity evaluation index which can reflect the population evolution state.By using the population variance and entropy of gene space to evaluate the diversity of population,the evolutionary state of the population is divided into four kinds of situations,in dif ferent states,different selection method of mutation probability and cross probability is adopted.In the course of evolution,cross and mutation rate of genetic algorithm is adaptively changed according to the evolutionary state of the population.This method can not only speed up the convergence of the algorithm,but also maintain the diversity of the population.Simulation results verify the effectiveness of the proposed algorithm.%为解决传统遗传算法“早熟”的问题,实现遗传算法的交叉和变异概率随种群进化状态自适应的调整,提出了一种种群多样性的自适应遗传算法.“早熟”产生的主要原因是种群多样性的过早丧失,而保持种群的多样性对于进化起着至关重要的作用.改进的自适应遗传算法引入了能够反映种群进化状态的种群多样性评价指标,利用基因空间种群的方差和熵来评价种群的多样性,将种群的进化状态分为四种情况讨论,根据种群多样性评价指标在不同的状态下对个体操作概率进行动态调整.仿真结果验证了改进算法的有效性,改进方法不仅加快了算法的收敛速度,而且能够有效的保持种群的多样性,一定程度上避免了过早收敛.