An Generational SDE based Indicator for Multi and Many-objective optimization

Recently, the study of designing multi-objective evolutionary algorithms (MOEAs) to solve multi and many-objective optimization has received lot of recognition. In this paper, we have proposed an indicator based MOEA (I
_gSDE
-MOEA) in which the information from the shift based density estimation is utilized to a greater extent. In the past, the shift based density estimation (SDE) is employed in conjunction with the other indicators and metrics. However, in this work, we employ the indicator based on SDE solely to approximate the Pareto front. The indicator proposed in this paper is adaptively controlled over the generations. The performance of the proposed I
_gSDE
-MOEA is evaluated by performing experiments on 14 benchmark problems and 7 real-world problems. The experimental results demonstrate that the proposed I
_gSDE
-MOEA exhibits better performance in comparison with the state-of-art algorithms.