A dual-stage large-scale multi-objective evolutionary algorithm with dynamic learning strategy

Large-scale multi-objective optimization problems (LSMOPs) bring significant challenges due to their large number of decision variables. Most of the existing algorithms fail to obtain high-quality solutions for the LSMOPs. To remedy this issue, an algorithm named dual-stage large-scale multi-objective evolutionary algorithm with dynamic learning strategy (DLMOEA-DLS) is proposed in this paper. In the DLMOEA-DLS, the entire evo-lution process mainly includes two stages, and each stage plays a different role in the searching process. In the first stage, the decision variables are clustering into two categories to be optimized independently for the convergence of the population. In the second stage, a dynamic learning strategy is designed to generate new offspring, in which each solution learns from a leader with better fitness and coupled control parameter for each solution is adaptively updated by learning from the historical behaviors of the solution. Moreover, an envi-ronmental selection operator is adopted to reserve promising solutions for the next iteration. To verify the performance of the DLMOEA-DLS, five state-of-the-art algorithms are used for comparison on 36 LSMOP benchmark instances, 48 LMF benchmark instances, and 6 real-world TREE benchmark instances. The experi-mental results demonstrate the superiority of the DLMOEA-DLS over the five state-of-the-art algorithms.