带基向量种群的改进差分进化算法

Modified Differential Evolution Algorithm with Base Vector Group

在基向量随机选择中,差分进化算法的收敛速度较慢。为此,提出一种改进的差分进化算法。从当前种群中选择一定数量个体组成基向量种群,在进行变异操作时,从该基向量种群中选择个体作为基向量。使用标准测试函数对算法进行验证,结果表明,该算法能缩小基向量选择范围,减少迭代次数。

In base vector randomly selection, the convergence speed of Differential Evolution（DE） algorithm is low. In order to solve this problem, a Modified DE（MDE） algorithm is proposed. Some good individuals are chosen to form the base vector group. Base vector is chosen from the base vector group when mutation is operated. Test functions are used to prove the new algorithm. Results show that the modified algorithm can reduce the selecting range of base vector and the iteration times for convergence.