小生境分布估计量子遗传算法及其仿真分析  

A niche estimation of distribution quantum genetic algorithm and its simulation analysis

作　　者：刘振[1] 彭军[1] 刘勇[1] 

机构地区：[1]海军航空工程学院接改装训练大队,山东烟台264001

出　　处：《计算机工程与科学》2016年第1期89-94,共6页Computer Engineering & Science

基　　金：国家自然科学基金(61174031;60674090)

摘　　要：针对现有量子遗传算法进化机制存在的收敛速度慢以及易陷入局部极值的问题,为提高量子进化算法的全局收敛性能,结合小生境技术中的共享适应度函数方法,提出了小生境分布估计量子遗传算法NEDQGA,在种群内部利用多粒度机制和边缘积模块(MPM)进行量子染色体的两步旋转;并提出利用MPM进行交叉的方法,从而增强了种群多样性,避免了优良模式的损失,加快了算法的收敛;对算法的收敛性进行了分析,提出了MPM更新量子染色体的熵收敛准则。经函数仿真分析,算法收敛效果明显提高。The traditional quantum genetic algorithm is slow in convergence speed and is easy to he trapped into local optimum. In order to overcome the above problems and enhance the convergence performance of the quantum genetic algorithm, we propose a novel niche estimation of distribution quantum genetic algorithm integrated with the fitness sharing function method. The quantum chromosome can be rotated in two steps in every subpopulation： the first step is the multi-granularity mechanism and the second step is the marginal product model （MPM） rotation. The quantum chromosome crossover based on the MPM can enhance the diversity of the population and avoid the loss of good models. The traits of convergence are also analyzed in the paper, and the entropy convergence criteria are proposed. Functional simulation results show that the proposed algorithm outperforms other traditional algorithms.

关 键 词：量子遗传算法 小生境 分布估计算法 扩展紧致遗传算法 

分 类 号：TP15[自动化与计算机技术—控制理论与控制工程]