An Improved Two-Archive Evolutionary Algorithm for Constrained Multi-Objective Optimization

TL;DR

This paper introduces C-TAEA-II, an enhanced evolutionary algorithm for constrained multi-objective optimization that improves collaboration between archives, demonstrating superior performance over existing algorithms.

Contribution

The paper presents C-TAEA-II, an improved version of C-TAEA with better archive update and adaptive mating mechanisms for more effective constrained multi-objective optimization.

Findings

C-TAEA-II outperforms five benchmark algorithms in empirical tests.

The improved update mechanism enhances convergence and diversity.

Adaptive mating selection promotes better archive collaboration.

Abstract

Constrained multi-objective optimization problems (CMOPs) are ubiquitous in real-world engineering optimization scenarios. A key issue in constrained multi-objective optimization is to strike a balance among convergence, diversity and feasibility. A recently proposed two-archive evolutionary algorithm for constrained multi-objective optimization (C-TAEA) has be shown as a latest algorithm. However, due to its simple implementation of the collaboration mechanism between its two co-evolving archives, C-TAEA is struggling when solving problems whose \textit{pseudo} Pareto-optimal front, which does not take constraints into consideration, dominates the \textit{feasible} Pareto-optimal front. In this paper, we propose an improved version C-TAEA, dubbed C-TAEA-II, featuring an improved update mechanism of two co-evolving archives and an adaptive mating selection mechanism to promote a better collaboration between co-evolving archives. Empirical results demonstrate the competitiveness of the proposed C-TAEA-II in comparison with five representative constrained evolutionary multi-objective optimization algorithms.