多策略融合的鱼鹰算法

Osprey Optimization Algorithm with Multi-Strategy Fusion

摘要: 针对鱼鹰算法易于陷入局部最优、收敛速度慢等问题，本文提出了一种多策略融合的鱼鹰算法。在鱼鹰捕猎的阶段，引入黄金正弦策略，加快算法从搜索空间中收敛到可行解的速度；在鱼鹰移动猎物阶段，引入灰狼围攻策略，增加精英个体的引导作用，有效提高算法寻优精度；对适应度值排序倒数5只鱼鹰个体采用较差个体放逐策略，利用莱维飞行特性，增强算法跳出局部极值的能力。在MATLAB中利用12个基准测试函数与9个算法进行对比测试，并且将改进前后的鱼鹰算法应用在光伏电池参数估计中，实验结果表明了本文所提改进鱼鹰算法是一种寻优精度高、稳定性强的算法。

Abstract: Aiming at the problems that the osprey optimization algorithm is easy to fall into the local optimum and slow convergence, this paper proposes a multi-strategy fusion osprey optimization algorithm. In the stage of osprey hunting, the golden sine strategy is introduced to accelerate the convergence of the algorithm from the search space to a feasible solution; in the stage of osprey moving prey, the grey wolf siege strategy is introduced to increase the guiding role of the elite individuals and effectively improve the algorithm to find the optimal precision; the poorer individual banishment strategy is adopted for the bottom five osprey individuals in the order of fitness value, and the Levy flight characteristics are used to enhance the ability of the algorithm to jump out of the local optimal value. Twelve benchmark functions and nine algorithms are used in MATLAB for comparative testing, and the osprey optimization algorithms before and after the improvement are applied in the estimation of photovoltaic cell parameters, and the experimental results show that the improved osprey optimization algorithm proposed in this paper is a kind of algorithm with high accuracy of optimization search and high stability.