Scholarlink

<p>This paper introduces a novel Multi-Objective extension of Artificial Rabbits Optimization (ARO), termed MOARO, designed to tackle large-scale multi-objective optimization problems. The proposed approach integrates two key strategies in its environmental selection process: non-dominated sorting and Shift-Based Density Estimation (SDE). Non-dominated sorting is employed to identify and select the elitist solutions, while SDE is used to maintain diversity among the solutions. This combination ensures a balanced trade-off between convergence and diversity, which is essential for generating high-quality Pareto-optimal fronts. Furthermore, MOARO incorporates an external repository and solution leaders to steer the search process, facilitating better exploration and promoting convergence towards a well-distributed Pareto front. The effectiveness of the algorithm is evaluated on seven bi-objective and fourteen three-objective benchmark test functions, and its performance is compared with three well established multi-objective metaheuristics. Experimental results demonstrate that MOARO outperforms competing algorithms, exhibiting superior convergence behavior and enhanced solution diversity.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

MOARO: An improved artificial rabbits optimization using shift-based density estimation for solving multi-objective optimization problems

  • 期刊论文

  • 发表日期：

    2026年6月29日

查看全文
  • Djaafar Zouache,
  • Fouad Ben Abelaziz,
  • Farid Boumaza,
  • Meriem Hemici

摘要

This paper introduces a novel Multi-Objective extension of Artificial Rabbits Optimization (ARO), termed MOARO, designed to tackle large-scale multi-objective optimization problems. The proposed approach integrates two key strategies in its environmental selection process: non-dominated sorting and Shift-Based Density Estimation (SDE). Non-dominated sorting is employed to identify and select the elitist solutions, while SDE is used to maintain diversity among the solutions. This combination ensures a balanced trade-off between convergence and diversity, which is essential for generating high-quality Pareto-optimal fronts. Furthermore, MOARO incorporates an external repository and solution leaders to steer the search process, facilitating better exploration and promoting convergence towards a well-distributed Pareto front. The effectiveness of the algorithm is evaluated on seven bi-objective and fourteen three-objective benchmark test functions, and its performance is compared with three well established multi-objective metaheuristics. Experimental results demonstrate that MOARO outperforms competing algorithms, exhibiting superior convergence behavior and enhanced solution diversity.