基于改进多生境排挤算法的量子遗传算法

The Quantum Genetic Algorithm Based on Improved Multi-Niche Crowding Algorithm

针对量子遗传算法在复杂连续函数优化中存在着收敛速度慢、易陷入局部最优的缺陷,提出一种基于改进多生境拥挤算法的量子遗传算法。基本思想是:在保留多生境排挤算法搜索速度较快这一优势的同时,引入聚类分析,提高其搜索能力,然后将改进的多生境排挤算法引入量子遗传算法。仿真实验结果显示,多生境排挤量子遗传算法与基本量子遗传算法相比较,在全局收敛性和收敛速度方面有了一定程度的改进和提高。

A quantum genetic algorithm based on improved multi-niche crowding algorithm is proposed to solve the problems of slow convergence speed and easily falling into local optimal in the quantum genetic algorithm in complex continuous function optimization.The basic idea is to introduce the clustering analysis to improve its search ability while preserving the advantages of the fast searching speed of the multi-niche crowding algorithm.Then the improved multi-niche crowding algorithm is introduced into the quantum genetic algorithm.The simulation results show that there is a certain degree of improvement in the aspects of global convergence and convergence speed for the improved algorithm when compared with multi-niche crowding algorithm and basic quantum genetic algorithm.