An enhanced differential evolution with ensemble of mutation strategies for numerical optimization
Xiangping Li, Yingqi Huang · 2025
For about two decades Differential Evolution (DE) algorithms have become one of the most successful optimization meta-heuristics. However, solving single objective real-parameter problem is still a challenging task. In the work, an enhanced differential evolution with ensemble of mutation strategies is proposed, referred to as EDEM. In EDEM, three mutation strategies are used to simultaneously execute evolution, namely “current-to-pbest/1”, “current-to-pbad/1” and “rand-to mbest/1”. To balance the exploration and exploitation, a linear reduction method is used to adapt memory size and coefficient scale. To verify the feasibility and effectiveness of EDEM, 25 test functions from CEC2005 were simulated. The numerical results indicate that the proposed approach is competitive with the other state-of-the-art DE variants.