基于跳跃基因算子的改进实数遗传算法

Improved real-coded genetic algorithm based on jumping gene operator

为了避免遗传算法在求解数值优化问题时出现搜索能力差、多样性缺失等弊端,提出一种基于实数编码的改进遗传算法(IRCGA).算法集成两个特别设计的算子:模拟二进制跳跃基因算子(SBJG)和多方向交叉算子(MX). SBJG算子以染色体为操作对象,本质上模拟了二进制跳跃基因操作中的插入运动,即利用一种随机的方式将选定的染色体块插入到染色体位点,实现种群内部染色体间的转位,为种群提供额外的遗传多样性;MX算子通过增加交叉方向的方式扩大算子的搜索区域,从而提升后代个体质量与算法的搜索能力.在11个实例的基础上进行对比实验,结果表明,采用改进算子能够明显提升算法在求解数值优化问题时的性能,同时,相比于其他先进有效的算法, IRCGA具有较强的搜索能力且能够维持一定的种群多样性,从而验证了改进算法的有效性和可行性.

In order to avoid the disadvantages of genetic algorithms in solving numerical optimization problems, such as poor search ability and lack of diversity, an improved real-coded genetic algorithm(IRCGA) is proposed. The algorithm integrates two specially designed operators: the simulated binary jumping gene(SBJG) operator and the multi-directional crossover(MX) operator. The SBJG operates on chromosomes. It essentially simulates the insertion motion in binary jumping gene operation, that is, inserts the selected chromosomal block into the chromosomal locus in a random way, and realizes the translocation between the chromosomes within the population, which provids additional genetic diversity for the population. The MX operator expands the search area of the operator by increasing the crossover direction to improve the quality of the offspring and the search ability of the algorithm. The comparative experiment is carried out on the basis 11 examples. The results show that the improved operator can significantly improve the performance of the algorithm in solving numerical optimization problems. At the same time, compared with other advanced and effective algorithms,the IRCGA has strong search ability and can maintain a certain population diversity, thus verifying the effectiveness and feasibility of the improved algorithm.