基于交叉亲和度评价的多种群遗传算法

A multi-population genetic algorithm based on cross accessibility evaluation

为进一步解决传统多种群遗传算法进化过程中迅速丧失种群多样性,导致的易早熟、收敛到局部最优解等问题,提出一种基于交叉亲和度评价的多种群遗传算法,采用多种群并行搜索的思想,结合模拟退火算法提高算法的搜索能力,种群之间通过交叉推优选出的交流个体,进行亲和度评价替换目标种群个体来完成交流。通过对TSP问题的求解表明,算法得到的解都接近最优解,性能优于传统多种群遗传算法。

To solve traditional multiple population genetic algorithm for rapid loss of species diversity in the process of evolution,which may result in easy premature convergence to local optimal solution,a multiple population genetic algorithm based on cross accessibility evaluation is put forward.By adopting the idea of parallel search multiple species,it combines with the simulated annealing algorithm to improve the search ability. The individualis elected by crossover excellent recommendation among multiple populations and the target population is replaced through evaluating accessibility to complete communication. Finally,the algorithm is used to solve the TSP problem. The results show that the solution is close to the optimal solution and the performance is superior to traditional multiple population genetic algorithm.