混合随机反向学习和高斯变异的混沌松鼠搜索算法

Hybrid random opposition-based learning and Gaussian mutation of chaotic squirrel search algorithm

针对松鼠搜索算法(SSA)易陷入局部最优、过早收敛等问题,提出一种混合随机反向学习和高斯变异的混沌松鼠搜索算法(RGCSSA)。该算法通过Tent混沌映射初始化策略生成混沌初始种群,增强初始种群分布的均匀性,实现对解空间更高效的搜索;采用非线性递减的捕食者概率策略,平衡SSA的全局搜索和局部开发能力;利用位置贪婪选择策略在迭代过程中不断保留种群中的优势个体,以提升算法收敛速度;引入随机反向学习和高斯变异策略,在增加种群多样性的同时提高算法跳出局部最优的能力。使用10个不同的基准测试函数进行仿真实验,并利用Wilcoxon符号秩检验验证所提算法的寻优性能,结果表明,RGCSSA算法在求解精度、收敛速度和稳定性等方面均有极大提升。

To address the problems such as easy to fall into local optimum and premature convergence of Squirrel Search Algorithm(SSA), a hybrid Random opposition-based learning and Gaussian mutation of Chaotic Squirrel Search Algorithm(RGCSSA) was proposed. The chaotic initial population was generated by the Tent chaotic mapping initialization strategy to enhance the uniformity of the initial population distribution and achieve a more efficient search of the solution space. Then, a nonlinear decreasing predator probability strategy was used to balance the global search and local exploitation capabilities of SSA. The positional greedy selection strategy was utilized to increase the convergence speed of the algorithm by continuously retaining the dominant individuals in the population during the iterative process. The random opposition-based learning and Gaussian variation strategies were introduced to increase the population diversity and improve the ability of the algorithm to jump out of the local optimum. The optimization performance of the proposed algorithm was verified by simulation experiments and Wilcoxon’s signed rank test on 10 different benchmark functions. The results showed that the RGCSSA algorithm had greatly improved in terms of solution accuracy and convergence speed as well as stability.