Sie befinden Sich nicht im Netzwerk der Universität Paderborn. Der Zugriff auf elektronische Ressourcen ist gegebenenfalls nur via VPN oder Shibboleth (DFN-AAI) möglich. mehr Informationen...
Dynamic multiobjective optimization problems (DMOPs) are characterized by their multiple objectives, constraints, and parameters that may change over time. The challenge in solving DMOPs is how to track the varying Pareto-optimal solution sets quickly and accurately. Therefore, an interindividual correlation and dimension-based dual-learning method is proposed in this article. Two learning strategies, decomposition-based interindividual correlation transfer learning (DICTL) and dimension-wise learning (DL), are developed to, respectively, generate one-half of the initial population in the new environment. More specifically, DICTL learns the interindividual correlation from the final population of the adjacent environment and then transfers it to the new environment, aiming to maintain the diversity and distribution of the predicted population. While DL extracts the changing pattern of dynamic environments from the high-quality solutions of historical environments in the perspective of variable dimension, trying to improve the quality of the population and accelerate the convergence. The designed two learning strategies (DICTL&DL) work complementarily and collaboratively to make the algorithm adapt to dynamic environments better and faster. Comprehensive experiments have been conducted by comparing the proposed method with four state-of-the-art algorithms on 14 benchmark problems. The results demonstrate the superiority of the proposed method.