Evolutionary Multi-objective Optimization Algorithm Based on Global Crowding Diversity Maintenance Strategy


This paper presents an improved multi-objective evolutionary algorithm based on global crowding diversity maintenance strategy and diversity initialization population strategy. In selection process, the global crowding strategy is applied to be a part of crowding operator which is used to select survival individuals. In the initialization process, one kind of diversity initialization population strategy is used to guarantee that the population can be widely spread at the beginning of evolutionary process. Numerical experiment results show that the proposed scheme improves diversity maintenance in evolutionary process. The results also demonstrate that the proposed algorithms can speed up the convergence and guide the solutions to be widely spread on the true Panto optimal front.