Abstract: A novel intelligent optimization algorithm inspired by nature, called sea otter optimization algorithm (SOOA), is proposed. The SOOA simulates the natural behaviors of sea otters, such as using tactile senses to search for food in seawater, grooming their fur, feeding with the aid of stones, and escaping from danger. In the exploration stage, a wetness factor is introduced to control the behavior of sea otters in foraging and grooming; a danger factor is introduced to control the behavior of sea otters in feeding and avoiding dangers in the exploitation stage, and the behaviors of sea otters in responding to different dangers are mathematically modeled. The proposed algorithm is compared with 9 well-known intelligent optimization algorithms, and evaluated in 13 benchmark functions as well as wireless sensor network coverage optimization problems to verify the effectiveness of the proposed algorithm. The experimental results show that the node coverage after SOOA optimization reaches 91.2% in 2D environment and 90.47% in 3D environment. Compared with other algorithms, SOOA is superior and possesses the ability to solve complex optimization problems.

Key words: sea otter optimization algorithm (SOOA), swarm intelligence optimization, wireless sensor network, coverage optimization

摘要： 提出了一种受大自然启发的新型智能优化算法，海獭优化算法（SOOA）。SOOA模拟了海獭在海水中运用触觉进行觅食，梳理毛发，运用石头进食以及逃离危险等自然行为。在探索阶段，引入湿度因子来控制海獭觅食和梳理毛发的行为；在开发阶段，引入危险因子来控制海獭进食和躲避危险的行为，并对海獭应对不同危险的行为进行数学建模。将所提算法与9种著名的智能优化算法进行了比较，并在13个基准函数以及无线传感器网络覆盖优化问题中进行了评估，以验证所提算法的有效性。实验结果表明：SOOA优化后的节点覆盖率在二维环境下达到91.2%，在三维环境下达到90.47%，与其他算法相比，SOOA更胜一筹，具有解决复杂优化问题的能力。

关键词: 海獭优化算法，群体智能优化，无线传感器网络，覆盖优化