蜜蜂双种群进化型遗传算法

Double bee population evolutionary genetic algorithm

为了改善传统遗传算法的性能,由蜜蜂种群繁殖进化的方式得到启发,提出了一种蜜蜂双种群进化型遗传算法(DBPGA)。算法共有两个种群,一个是通过迭代进行遗传操作得到的;另一个在每代进化过程中随机引入。每个种群中的最优个体作为蜂王分别以概率与其它个体(雄蜂)进行交配操作。既能增强对种群最优个体所包含信息的开采能力,又能提高算法的勘探能力,从而避免算法过早地收敛。实验结果表明,该算法对于改进和提高遗传算法性能及求解连续非线性规划问题是有效可行的。

A double bee population evolutionary genetic algorithm （DBPGA） is proposed. In DBPGA, there is double bee population. One is from generation by the DBPGA, the other is a random population, and consequentially it enhances the exploration of genetic algorithm. Optimum individual being a queen-bee in each population crossover with each selected individual （drone）. As a result it reinforces the exploitation of genetic algorithm, avoids premature convergence, and extends search area. Results for several continuous nonlinear programming problems show that DBPGA is an efficient and effective improved genetic algorithm.