Adaptive grey wolf optimizer
Adaptive grey wolf optimizer
复制标题
DOI：
10.1007/s00521-021-06885-9
复制
发表时间：
2022-01-11
影响因子：
6
通讯作者：
Farimani, Amir Barati
中科院分区：
文献类型：
--
作者：
Meidani, Kazem;Hemmasian, AmirPouya;Farimani, Amir Barati
基于群的元启发式优化算法在科学和工业领域的广泛优化问题上都表现出了出色的性能。尽管它们有优点，但这些技术的主要限制来自非自动化参数调优和缺乏系统停止标准，这通常会导致计算资源的低效使用。在这项工作中，我们提出了一种改进版本的灰狼优化器（GWO），称为自适应GWO，它通过在优化过程中根据候选解的适应度历史自适应调整勘探/开发参数来解决这些问题。AGWO通过根据优化过程中适应度改善的显著性来控制停止准则，可以在最短时间内自动收敛到一个足够好的最优。此外，我们提出了一种扩展的自适应GWO(AGWO(Delta))，它根据三点适应度历史调整收敛参数。在一项全面的比较研究中，我们表明AGWO是一种比GWO更有效的优化算法，它减少了达到与GWO统计相同的解决方案所需的迭代次数，并且优于许多现有的GWO变体。
Swarm-based metaheuristic optimization algorithms have demonstrated outstanding performance on a wide range of optimization problems in both science and industry. Despite their merits, a major limitation of such techniques originates from non-automated parameter tuning and lack of systematic stopping criteria that typically leads to inefficient use of computational resources. In this work, we propose an improved version of grey wolf optimizer (GWO) named adaptive GWO which addresses these issues by adaptive tuning of the exploration/exploitation parameters based on the fitness history of the candidate solutions during the optimization. By controlling the stopping criteria based on the significance of fitness improvement in the optimization, AGWO can automatically converge to a sufficiently good optimum in the shortest time. Moreover, we propose an extended adaptive GWO (AGWO(Delta)) that adjusts the convergence parameters based on a three-point fitness history. In a thorough comparative study, we show that AGWO is a more efficient optimization algorithm than GWO by decreasing the number of iterations required for reaching statistically the same solutions as GWO and outperforming a number of existing GWO variants.