A Simple but Efficient Ranking-Based Differential Evolution
Jiayi Li, Lin Yang, Junyan Yi, Haichuan Yang, Yuki Todo, Shangce Gao · IEICE Transactions on Information and Systems · 2021
Differential Evolution (DE) algorithm is simple and effective. Since DE has been proposed, it has been widely used to solve various complex optimization problems. To further exploit the advantages of DE, we propose a new variant of DE, termed as ranking-based differential evolution (RDE), by performing ranking on the population. Progressively better individuals in the population are used for mutation operation, thus improving the algorithm's exploitation and exploration capability. Experimental results on a number of benchmark optimization functions show that RDE significantly outperforms the original DE and performs competitively in comparison with other two state-of-the-art DE variants.