Improved differential evolution algorithm with adaptive mutation and control parameters

This paper presents an improved differential evolution algorithm with adaptive mutation and control parameters (IADE) for global numerical optimization over continuous space. In the IADE algorithm, scaling factor F and crossover rate CR are adaptive various by using the previous learning experience, the target individuals will be mutation by the population fitness variance according to the mutation probability. Adaptive mutation can enhance the algorithm escape from local optima. The results show that the new algorithm of the global search capability has been improved, effectively avoid the premature convergence and later period oscillatory occurrences.