A dynamic multi-objective evolutionary algorithm based on decision variable classification

In recent years, dynamic multi-objective optimization problems (DMOPs) have drawn increasing interest. Many dynamic multi-objective evolutionary algorithms (DMOEAs) have been put forward to solve DMOPs mainly by incorporating diversity introduction or prediction approaches with conventional multi-objective evolutionary algorithms. Maintaining good balance of population diversity and convergence is critical to the performance of DMOEAs. To address the above issue, a dynamic multi-objective evolutionary algorithm based on decision variable classification (DMOEA-DVC) is proposed in this study. DMOEA-DVC divides the decision variables into two and three different groups in static optimization and change response stages, respectively. In static optimization, two different crossover operators are used for the two decision variable groups to accelerate the convergence while maintaining good diversity. In change response, DMOEA-DVC reinitializes the three decision variable groups by maintenance, prediction, and diversity introduction strategies, respectively. DMOEA-DVC is compared with the other six state-of-the-art DMOEAs on 33 benchmark DMOPs. Experimental results demonstrate that the overall performance of the DMOEA-DVC is superior or comparable to that of the compared algorithms.