Self-adaptive improved differential evolution algorithm
Liangdong Qu, Dengxu He, Yongsheng Li · 2010 Sixth International Conference on Natural Computation · 2010
A new self-adaptive improved differential evolution algorithm is presented. In order to improve the population's diversity and the ability of breaking away from the local optimum, according to the value of the variance of the population's fitness during the evolution process, a new mutation operator is adapted to mutate the population. In order to balance global and local search ability, the Scaling factor F is automatically updated according to the generations. In order to protect the better individuals to improve the convergent speed, the crossover rate CR is automatically updated according to the average value of the population's fitness. Several experimental results show that the new algorithm not only has can avoid the premature convergence remarkably, but also can improve convergent speed.