基于混沌搜索策略的鲸鱼优化算法

Whale optimization algorithm based on chaotic search strategy

针对鲸鱼优化算法存在探索和开发能力难以协调、易陷入局部最优的不足,提出一种基于混沌搜索策略的鲸鱼优化算法(CWOA).首先,采用混沌反向学习策略产生初始种群,为全局搜索多样性奠定基础;其次,设计收敛因子和惯性权重的非线性混沌扰动协同更新策略以平衡全局探索和局部开发能力;最后,将种群进化更新与最优个体的混沌搜索机制相结合,以减小算法陷入局部最优的概率.对10个基准测试函数和6个复合测试函数进行优化,实验结果表明, CWOA在收敛速度、收敛精度、鲁棒性方面均较对比算法有较大提升.

A whale optimization algorithm based on the chaotic search strategy(CWOA) is proposed to overcome the drawbacks of being difficult to coordinate the exploration and exploitation ability, and easily trapped into local optimum.In the proposed algorithm, the chaotic opposition-based learning strategy is used to generate initial population, which strengthens the diversity of population in the global searching process. Then, a nonlinearly chaotic disturbance cooperative updating strategy for the convergence factor and inertia weight is designed to balance the exploration and exploitation ability. Finally, the chaotic search strategy for optimum individual is combined with evolutionary population updating to avoid the possibility of being trapped into local optimum. The optimization experiments are conducted on the 10 benchmark functions and 6 composite functions. Simulation results show that the proposed CWOA has fast convergence and more precise convergence than other comparison algorithms.