Orca predation algorithm: A novel bio-inspired algorithm for global optimization problems
Orca predation algorithm: A novel bio-inspired algorithm for global optimization problems
复制标题
DOI：
10.1016/j.eswa.2021.116026
复制
发表时间：
2021-10-21
影响因子：
8.5
通讯作者：
Zhang, Luke
中科院分区：
文献类型：
--
作者：
Jiang, Yuxin;Wu, Qing;Zhang, Luke
本文提出了一种称为ORCA捕食算法（OPA）的新型生物启发算法。 OPA模拟了Orcas的狩猎行为，并将其抽象成几个数学模型：包括驾驶，环绕和攻击猎物。该算法将不同的权重分配给猎物驾驶和环绕参数调整的阶段，以平衡算法的剥削和探索阶段。在攻击阶段，在考虑了几个上级逆戟鲸和一些随机选择的逆戟鲸的位置之后，可以在不失去颗粒的多样性的情况下接近最好的解决方案。为了估计OPA的性能，首先采用了67个无约束的基准功能，然后在五个受约束的工程优化问题上进一步评估了该算法的效率。此外，分析了OPA的计算复杂性，参数灵敏度和四个定性指标，以评估该算法的适用性。实验结果表明，相对于不同搜索景观的其他测试算法，OPA可以产生更有希望的结果。
A novel bio-inspired algorithm called Orca Predation Algorithm (OPA) is proposed in this paper. OPA simulates the hunting behavior of orcas and abstracts it into several mathematical models: including driving, encircling and attacking of prey. The algorithm assigns different weights to the phases of prey driving and encircling through parameter adjustment to balance the exploitation and exploration stages of the algorithm. In the attacking phase, after considering the positions of several superior orcas and some randomly selected orcas, the optimal solution can be approached without losing the diversity of the particles. In order to estimate the performance of OPA, 67 unconstrained benchmark functions were first employed, and then the efficiency of the algorithm was further evaluated on five constrained engineering optimization problems. Besides, the computational complexity, parameter sensitivity and four qualitative metrics of OPA were analyzed to evaluate the applicability of the algorithm. The experimental results demonstrate that OPA can generate more promising results with superior performance relative to other test algorithms on different search landscapes.