Using External Archive for Improved Performance in Multi-Objective Optimization

TL;DR

This paper demonstrates that using an external archive with a new management scheme can significantly enhance the quality of Pareto-optimal solutions in multi-objective optimization, especially when objective evaluations are costly.

Contribution

A novel archive management scheme is proposed and integrated with NSGA-II, improving solution quality without significant computational overhead.

Findings

Enhanced Pareto front quality with external archive

Significant improvements in solution sets for two problems

Minimal additional computational cost when evaluations are expensive

Abstract

It is shown that the use of an external archive, purely for storage purposes, can bring substantial benefits in multi-objective optimization. A new scheme for archive management for the above purpose is described. The new scheme is combined with the NSGA-II algorithm for solving two multi-objective optimization problems, and it is demonstrated that this combination gives significantly improved sets of Pareto-optimal solutions. The additional computational effort because of the external archive is found to be insignificant when the objective functions are expensive to evaluate.