PROJECT TITLE :

A Knee Point-Driven Evolutionary Algorithm for Many-Objective Optimization

ABSTRACT:

Evolutionary algorithms (EAs) have shown to be promising in solving many-objective optimization problems (MaOPs), where the performance of those algorithms heavily depends on whether or not solutions that can accelerate convergence toward the Pareto front and maintaining a high degree of diversity will be selected from a collection of nondominated solutions. During this paper, we have a tendency to propose a knee point-driven EA to solve MaOPs. Our basic plan is that knee points are naturally most most well-liked among nondominated solutions if no specific user preferences are given. A bias toward the knee points within the nondominated solutions in the present population is shown to be an approximation of a bias toward a massive hypervolume, thereby enhancing the convergence performance in several-objective optimization. Also, as at most one solution will be identified as a knee purpose inside the neighborhood of every answer within the nondominated front, no extra diversity maintenance mechanisms would like to be introduced in the proposed algorithm, significantly reducing the computational complexity compared to many existing multiobjective EAs for several-objective optimization. Experimental results on 16 test problems demonstrate the competitiveness of the proposed algorithm in terms of both resolution quality and computational potency.