朴素差分进化算法

Nave differential evolution algorithm

针对变异算子学习方式的单一性,提出一种朴素变异算子,其基本思想是向优秀的个体靠近,同时远离较差个体,其实现方式是设计一种缩放因子调整策略,如果三个随机个体在某维上比较接近,则缩放因子变小,反之变大。在实验过程中通过平均适应度评价次数、成功运行次数和加速比等指标表明,基于朴素变异算子的差分进化算法能有效提高算法的收敛速度和健壮性。

In order to solve singleness of mutation study, a naive mutation strategy was proposed to approach the best individual and depart the worst one. So, a scale factor self-adaptation mechanism was used and the parameter was set to a small value when the dimension value of three random individuals is very close to each other, otherwise, set it to a large value. The results showed that the Differential Evolution（ DE） with the new mechanism exhibits a robust convergence behavior measured by average number of fitness evaluations, successful running rate and acceleration rate.