Improved strength Pareto evolutionary algorithm based on reference direction and coordinated selection strategy

In the field of evolutionary algorithms, Pareto-based algorithms are less effective when more than three objectives are encountered, due to the lack of sufficient selection pressure. In this paper, a Pareto-based many-objective evolutionary algorithm with reference direction and coordinated selection strategy, abbreviated as SPEACSS, is proposed. The algorithm inherits the fitness calculation strategy of the strength Pareto evolutionary algorithm, while it applied an efficient reference direction-based density estimator and a novel selection strategy. Moreover, mating selection and environmental selection are complementary and coordinated in the evolutionary process and have better performance than be used alone. In the criteria of mating selection, a method is given to improve the effectiveness of the parent combination. Experimental results on benchmark functions show that the proposed algorithm is superior to several state-of-the-art designs, and demonstrate the effectiveness of the improved algorithm in balancing diversity and convergence.