A multi-objective artificial sheep algorithm

In this paper, a novel multi-objective artificial sheep algorithm (MOASA) is proposed. The basic search idea of MOASA inherits from the BASA, which is inspired by the social behavior of sheep herd, while some modifications are made to extend the algorithm to multi-objective problems. The Pareto-based theory is adopted in the MOASA along with external archive and leader selection mechanism to bring about multi-objective optimization. Furthermore, a novel neighborhood search method is proposed and applied to the external archive to enhance the performance of the algorithm. The proposed MOASA is then tested on 17 multi-objective benchmark problems to verify its efficiency and effectiveness by comparing with six powerful multi-objective optimization algorithms (MOAs). Experimental results show that the MOASA is generally superior to its competitors in solving those benchmark problems in terms of convergence and Pareto front distribution.