A model-based many-objective evolutionary algorithm with multiple reference vectors

In order to estimate the Pareto front, most of the existing evolutionary algorithms apply the discovery of non-dominated solutions in search space, and most algorithms need appropriate diversity. Sometimes the Pareto front is so much thin and several dominated solutions exist beside the Pareto front. This paper proposes a new inverse model-based evolutionary algorithm with multiple reference vectors in order to exact place of possible Pareto front and then a collection of the exact places of vectors are produced and through this collection, the solutions which are beside the Pareto front mapping to the hyperplane and clustered in order to produce more effective reference vectors point to Pareto front which ultimately leads to the proper guide of diversity and convergence of population. The suggested method has been experimented on the benchmark test suite for CEC’2018 Competition (MaF1–15) and Walking Fish Group (WFG)) and expresses that the suggested strategy is encouraging