D-MEANDS: a novel evolutionary approach to dynamic many-objective optimization problems

Several real-world optimization problems manipu-late discrete variables, involve with many objectives and vary along the time, that is, they are dynamic. Recent works have focused on investigate dynamic multiobjective optimization prob-lems (DMOPs), which adds an additional challenge to the search convergence. Some evolutionary strategies have emerged based on the adaptation of consagrated multiobjective algorithms previ-ously proposed for static continuous optimization problems, such as, NSGA-II and MOEA/D. This work presents a novel evolu-tionary algorithm for dynamic discrete many-objective problems named D-MEANDS. It uses the subjacent search proposed in MEANDS. This algorithm has been successfully investigated in static MOPs and herein we propose some adaptations to be used in DMOPs. A comparative analysis of the new proposal is made using two DMOP evolutionary algorithms from the literature: DNSGA-II and MS-MOEA. A dynamic many-objective version of the knapsack problem (KP), known as dynamic multiobjective knapsack problem (DMKP), was explored. Results using DMKP formulations with 4 and 6 objectives sugest that D-MEANDS is a promising algorithm to deal with DMOPs with many objectives.