Abstract
In the last two decades, the non-dominated sorting genetic algorithm II (NSGA-II) has been the most widely-used evolutionary multi-objective optimization (EMO) algorithm. However, its performance on a wide variety of many-objective test problems has not been examined in the literature. It has been implicitly assumed by EMO researchers that NSGA-II does not work well on many-objective problems. As a result, NSGA-II has always been excluded from performance comparison with recently proposed many-objective EMO algorithms. Recently, it was pointed out that the performance of NSGA-II on many-objective problems is not always bad. In fact, the poor performance of NSGA-II on many-objective problems is mainly due to the existence of dominance resistant solutions. In this article, we show that the negative effect of the dominance resistant solutions can be remedied by slightly modifying objective values of many-objective problems in NSGA-II. Experimental results show that the modified NSGA-II works well on a wide variety of many-objective test problems.
Highlights
Since the emergence of the research field of evolutionary multi-objective optimization (EMO), the non-dominated sorting genetic algorithm II (NSGA-II) [1] has been the most well-known and widely-used EMO algorithm in the literature
For inverted generational distance (IGD) calculation, the reference point set obtained from the PlatEMO is used
First we explained the relation between the cone-dominance and the objective value modification in NSGA-II
Summary
Since the emergence of the research field of evolutionary multi-objective optimization (EMO), the non-dominated sorting genetic algorithm II (NSGA-II) [1] has been the most well-known and widely-used EMO algorithm in the literature. They are far away from the Pareto front since they have very bad objective values Since they have very good objective values, they are hardly dominated by other solutions. They are usually non-dominated solutions in the current population They are evaluated as good solutions with respect to the diversity (i.e., crowding distance) since they are far away from other solutions due to their very bad objective values. NSGA-II has not been compared with recently proposed EMO algorithms for many-objective optimization This is because it is implicitly assumed by EMO researchers that NSGA-II does not work well on many-objective problems. It is necessary to examine the performance of NSGA-II in comparison with recently proposed EMO algorithms on a wide variety of many-objective test problems.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have