简要介绍了差分进化算法,对影响算法性能的主要参数种群规模,缩放因子和交叉因子进行了系统的实验,分析了各个参数对算法性能的影响及其最优选取问题,并给出了一些有益的结论,对运用差分进化算法时的参数选取有参考价值。
Differential evolution (DE) algorithm is introduced briefly. Systematic experiments are done on the important parameters, such as the population size, scaling factor and crossover factor that influence the ability of DE algorithm. The effects and the optimal selection of these major parameters on DE are analyzed. And some conclusions are derived, which may be useful for setting parameters value in using the DE algorithm.