计算机工程与应用 ›› 2024, Vol. 60 ›› Issue (10): 88-104.DOI: 10.3778/j.issn.1002-8331.2310-0117

• 理论与研发 • 上一篇    下一篇

融入小生境和混合变异策略的鲸鱼优化算法

于涛,高岳林   

  1. 1.北方民族大学 计算机科学与工程学院,银川 750021
    2.宁夏智能信息与大数据处理重点实验室(北方民族大学),银川 750021
  • 出版日期:2024-05-15 发布日期:2024-05-15

Whale Optimization Algorithm Integrating Niche and Hybrid Mutation Strategy

YU Tao, GAO Yuelin   

  1. 1.School of Computer Science and Engineering, North Minzu University, Yinchuan 750021, China
    2.Ningxia Key Laboratory of Intelligent Information and Big Data Processing (North Minzu University), Yinchuan 750021, China
  • Online:2024-05-15 Published:2024-05-15

摘要: 鲸鱼优化算法作为一种结构简单的先进优化算法,被用于解决各类学科问题。通过对鲸鱼优化算法进行深入研究,发现该算法存在收敛速度慢、无法跳出局部最优、收敛精度低以及无法平衡全局勘探与局部开发能力等问题。为解决上述问题,提出一种融入小生境和混合变异策略的鲸鱼优化算法(whale optimization algorithm integrating niche and hybrid mutation strategy,NHWOA)。该算法通过引入自适应权重,平衡算法全局勘探与局部开发能力,并加快收敛速度;将种群按照相同规模划分成三个小生境并独立寻优,提高种群多样性;采用混合变异策略对种群进行随机扰动,帮助算法跳出局部最优。通过在CEC2017测试套件上对NHWOA进行仿真实验,并将其应用于特征选择问题,验证了NHWOA的先进性和有效性。NHWOA的收敛速度更快,收敛精度更高,并且鲁棒性更好。

关键词: 鲸鱼优化算法, 小生境, 混合变异, 自适应权重, 特征选择

Abstract: As an advanced optimization algorithm with a simple structure, the whale optimization algorithm is used to solve problems in many disciplines. Through in-depth research on the whale optimization algorithm, it is found that the algorithm has problems such as slow convergence speed, inability to escape local optima, low convergence accuracy, and inability to balance global exploration and local exploitation capabilities. To address these issues, a whale optimization algorithm integrating niche and hybrid mutation strategy (NHWOA) is proposed. NHWOA introduces adaptive weights to balance the global exploration and local exploitation capabilities of the algorithm and accelerate its convergence speed. It divides the population into three niches of the same size, and independently optimizes them to increase population diversity. It uses a hybrid mutation strategy to randomly perturb the population, helping the algorithm escape local optima. Simulation experiments on the CEC2017 benchmark suite and application to feature selection problems validate the superiority and effectiveness of NHWOA. NHWOA exhibits faster convergence speed, higher convergence accuracy, and better robustness.

Key words: whale optimization algorithm, niche, hybrid mutation, adaptive weight, feature selection