arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2404.16280cs.NEcs.AIcs.LG
收藏

一种通过组合当前最先进策略重构的高效差分进化变体,用于求解单目标边界约束问题

An Efficient Reconstructed Differential Evolution Variant by Some of the Current State-of-the-art Strategies for Solving Single Objective Bound Constrained Problems

Faculty of Engineering University of Toyama Toyama, Japan;School of Mechanical Engineering Tongji University Shanghai, China

Sichen Tao, Ruihan Zhao, Kaiyu Wang, Shangce Gao

AI总结:

本文针对单目标边界约束问题,提出一种组合当前最先进策略的重构差分进化算法(RDE),基于CEC2024基准测试验证了其优越性能。

摘要:

复杂的单目标边界约束问题通常难以求解。在进化计算方法中,自1997年提出差分进化算法以来,因其简单高效而得到广泛研究与发展。这些发展包括各种自适应策略、算子改进以及其他搜索方法的引入。2010年之后,基于LSHADE的研究也被研究人员广泛探讨。然而,尽管近期提出的改进策略相比其前代的首次表现展现出优越性,但添加所有新策略未必能带来最强性能。因此,我们重新组合了近年来基于先进差分进化变体的一些有效进展,并最终确定了一种有效的组合方案以进一步提升差分进化的性能。在本文中,我们提出了一种策略重组与重构的差分进化算法,称为重构差分进化(RDE),用于解决单目标边界约束优化问题。基于2024年IEEE进化计算大会(CEC2024)的基准测试套件,我们对RDE及其他几种先进的差分进化变体进行了测试。实验结果表明,RDE在求解复杂优化问题时具有优越的性能。

英文摘要:

Complex single-objective bounded problems are often difficult to solve. In evolutionary computation methods, since the proposal of differential evolution algorithm in 1997, it has been widely studied and developed due to its simplicity and efficiency. These developments include various adaptive strategies, operator improvements, and the introduction of other search methods. After 2014, research based on LSHADE has also been widely studied by researchers. However, although recently proposed improvement strategies have shown superiority over their previous generation's first performance, adding all new strategies may not necessarily bring the strongest performance. Therefore, we recombine some effective advances based on advanced differential evolution variants in recent years and finally determine an effective combination scheme to further promote the performance of differential evolution. In this paper, we propose a strategy recombination and reconstruction differential evolution algorithm called reconstructed differential evolution (RDE) to solve single-objective bounded optimization problems. Based on the benchmark suite of the 2024 IEEE Congress on Evolutionary Computation (CEC2024), we tested RDE and several other advanced differential evolution variants. The experimental results show that RDE has superior performance in solving complex optimization problems.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑