Xidian University, Guangzhou Institute of Technology, Guangzhou 510555, China.
Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun 130012, China.
Math Biosci Eng. 2022 Apr 11;19(6):5968-5997. doi: 10.3934/mbe.2022279.
Many real-world problems can be classified as multimodal optimization problems (MMOPs), which require to locate global optima as more as possible and refine the accuracy of found optima as high as possible. When dealing with MMOPs, how to divide population and obtain effective niches is a key to balance population diversity and convergence during evolution. In this paper, a self-organizing map (SOM) based differential evolution with dynamic selection strategy (SOMDE-DS) is proposed to improve the performance of differential evolution (DE) in solving MMOPs. Firstly, a SOM based method is introduced as a niching technique to divide population reasonably by using the similarity information among different individuals. Secondly, a variable neighborhood search (VNS) strategy is proposed to locate more possible optimal regions by expanding the search space. Thirdly, a dynamic selection (DS) strategy is designed to balance exploration and exploitation of the population by taking advantages of both local search strategy and global search strategy. The proposed SOMDE-DS is compared with several widely used multimodal optimization algorithms on benchmark CEC'2013. The experimental results show that SOMDE-DS is superior or competitive with the compared algorithms.
许多实际问题可以被归类为多模态优化问题 (MMOPs)，这些问题需要尽可能找到全局最优解，并尽可能提高找到的最优解的准确性。在处理 MMOPs 时，如何划分种群并获得有效的小生境是在进化过程中平衡种群多样性和收敛性的关键。在本文中，提出了一种基于自组织映射 (SOM) 的差分进化与动态选择策略 (SOMDE-DS)，以提高差分进化 (DE) 在解决 MMOPs 方面的性能。首先，引入了一种基于 SOM 的方法作为小生境技术，通过利用不同个体之间的相似性信息来合理地划分种群。其次，提出了一种可变邻域搜索 (VNS) 策略，通过扩展搜索空间来定位更多可能的最优区域。第三，设计了一种动态选择 (DS) 策略，通过利用局部搜索策略和全局搜索策略的优势来平衡种群的探索和开发。将所提出的 SOMDE-DS 与几个广泛使用的多模态优化算法在基准 CEC'2013 上进行了比较。实验结果表明，SOMDE-DS 优于或与比较算法具有竞争力。
