基于改进PSO的无线传感器网络数据自适应聚类算法  

Improved PSO based adaptive clustering algorithm for wireless sensor network data

作　　者：原大明[1] YUAN Daming(Department of Electrical Information Engineering,Northeast Petroleum University Qinhuangdao,Qinhuangdao 066004,China)

机构地区：[1]东北石油大学秦皇岛校区电气信息工程系,河北秦皇岛066004

出　　处：《现代电子技术》2023年第11期99-102,共4页Modern Electronics Technique

基　　金：2019年黑龙江省省属本科高校引导性创新基金项目(面上项目):移动无线传感器网络容错定位及坐标求精方法研究(2019QNQ⁃02)。

摘　　要：为解决无线传感器网络数据类项过于繁杂的问题,将相似信息参量整合成独立的簇类对象集合,提出基于改进PSO的无线传感器网络数据自适应聚类算法。按照改进PSO算法的作用机制,确定欧氏距离指标的计算数值,实现对网络数据的处理。在无线传感器网络体系中定义聚类排序原则,结合相关数据样本求解自适应期望熵,完成无线传感器网络数据自适应聚类算法研究。实验结果表明,在改进PSO算法作用下,无线传感器网络数据经过整合后的簇类对象集合数量由20个减少到6个,能够解决无线传感器网络数据类项过于繁杂的问题,满足按需整合相似信息参量的实际应用需求。In order to solve the problem of too many data categories in wireless sensor networks,the similar information parameters are integrated into an independent cluster object set,and an adaptive clustering algorithm for wireless sensor network data based on improved PSO is proposed.According to the mechanism of the improved PSO algorithm,the calculation value of Euclidean distance index is determined to realize the processing of network data.In the system of wireless sensor networks,the principle of clustering and sorting is defined,and the adaptive expected entropy is solved in combination with relevant data samples to complete the research of adaptive clustering algorithm for wireless sensor network data.The experimental results show that under the effect of the improved PSO algorithm,the number of cluster object sets after the integration of wireless sensor network data is reduced from 20 to 6,which can solve the problem of too complex data class items in wireless sensor network and meet the practical application requirements of integrating similar information parameters on demand.

关 键 词：改进PSO算法 无线传感器网络 自适应聚类 惯性权重 测试函数 欧氏距离 期望熵 簇类对象集合 

分 类 号：TN711-34[电子电信—电路与系统] TP393[自动化与计算机技术—计算机应用技术]