Cooperative coevolutionary hybrid NSGA-II with Linkage Measurement Minimization for Large-scale Multi-objective optimization

TL;DR

This paper introduces a novel variable grouping method based on linkage measurement minimization and a hybrid NSGA-II with Gaussian sampling for large-scale multi-objective optimization, demonstrating improved performance over existing methods.

Contribution

The paper presents a new variable grouping technique using linkage measurement minimization and a hybrid NSGA-II with Gaussian sampling, tailored for large-scale multi-objective problems.

Findings

Variable grouping method outperforms popular methods.

Hybrid NSGA-II effectively explores the Pareto Front.

Numerical experiments validate the approach's superiority.

Abstract

In this paper, we propose a variable grouping method based on cooperative coevolution for large-scale multi-objective problems (LSMOPs), named Linkage Measurement Minimization (LMM). And for the sub-problem optimization stage, a hybrid NSGA-II with a Gaussian sampling operator based on an estimated convergence point is proposed. In the variable grouping stage, according to our previous research, we treat the variable grouping problem as a combinatorial optimization problem, and the linkage measurement function is designed based on linkage identification by the nonlinearity check on real code (LINC-R). We extend this variable grouping method to LSMOPs. In the sub-problem optimization stage, we hypothesize that there is a higher probability of existing better solutions around the Pareto Front (PF). Based on this hypothesis, we estimate a convergence point at every generation of optimization and perform Gaussian sampling around the convergence point. The samples with good objective value will participate in the optimization as elites. Numerical experiments show that our variable grouping method is better than some popular variable grouping methods, and hybrid NSGA-II has broad prospects for multi-objective problem optimization.