计算机工程与应用 ›› 2024, Vol. 60 ›› Issue (20): 96-115.DOI: 10.3778/j.issn.1002-8331.2312-0390

• 理论与研发 • 上一篇    下一篇

种群熵竞争粒子群算法

王霞,王卓然,张珊,王勇   

  1. 1.云南民族大学 云南省无人自主系统重点实验室,昆明 650504
    2.云南民族大学 电气信息工程学院,昆明 650504
  • 出版日期:2024-10-15 发布日期:2024-10-15

Population Entropy Competitive Particle Swarm Optimization Algorithm

WANG Xia, WANG Zhuoran, ZHANG Shan, WANG Yong   

  1. 1.Key Laboratory of Unmanned Autonomous Systems in Yunnan Province, Yunnan Minzu University, Kunming 650504, China
    2.School of Electrical Information Engineering, Yunnan Minzu University, Kunming 650504, China
  • Online:2024-10-15 Published:2024-10-15

摘要: 为进一步提高竞争粒子群优化算法的收敛性和求解精度,提出一种种群熵竞争粒子群算法(population entropy competitive particle swarm optimization algorithm,CSOPE);提出非线性惯性权重调整策略,以均衡粒子的全局勘探能力和局部开采能力;提出一种基于熵模型的种群状态检测策略,根据种群的标准化四分位差和标准化中位数差计算种群熵,通过相邻两代种群的熵值之差监测种群状态,当种群处于收敛状态时,对赢家粒子利用灰狼搜索进行局部开采,以提高算法的收敛精度。在CEC2008和CEC2013共21个测试函数上将所提算法与其他8种优化算法进行对比,实验结果表明,CSOPE算法的求解精度和收敛性得到了显著提高。将CSOPE算法应用到无线传感器网络节点定位问题,结果表明CSOPE算法具有较高的定位精度。

关键词: 竞争粒子群算法, 种群状态, 种群熵, 惯性权重, 灰狼搜索

Abstract: To further improve the convergence and solution accuracy of competitive swarm optimizer, a variety of population entropy competitive particle swarm optimization algorithm (CSOPE) is proposed. Firstly, a nonlinear inertia weight adjustment strategy is proposed to balance the global exploration ability and local exploitation ability of particles. Secondly, a population state detection strategy based on entropy model is proposed, which calculates the population entropy by the standardized quartile difference and standardized median difference of the population. The population state is monitored by the difference in entropy values between adjacent generations of the population. When the population is in a convergence state, it uses gray wolf search to exploit winner particle locally to improve the convergence accuracy of the algorithm. The proposed CSOPE algorithm is compared with other 8 optimization algorithms on 21 test functions in CEC2008 and CEC2013, and the experimental results show that the solving accuracy and convergence of the CSOPE algorithm are significantly improved. The CSOPE algorithm is applied to the node localization problem in wireless sensor networks, and the results show that the CSOPE algorithm has high localization accuracy.

Key words: competitive particle swarm optimization algorithm, population status, population entropy, inertial weight, grey wolf search