基于加权K-means聚类算法的机动通信网络自动划分方法  

Automatic Division method of Maneuver Communication Network Based on Combined Weighted K-means Clustering

作　　者：王均春 冀云刚 WANG Junchun;JI Yungang(School ofInformation Communication,National University of Defense Technology,Wuhan 430019,China;The 54th Research Institute of CETC,Shijiazhuang 050081,China)

机构地区：[1]国防科技大学信息通信学院,湖北武汉430019 [2]中国电子科技集团公司第五十四研究所,河北石家庄050081

出　　处：《计算机与网络》2022年第2期56-59,共4页Computer & Network

摘　　要：针对机动通信网络规划中的网络划分需求,提出了一种基于加权K-means聚类算法的网络自动划分方法。算法通过采用Elbow方法确定聚类数量,并在初始聚类中心选择中考虑了节点连通度,克服了传统K-means算法初始聚类中心的不确定性,通过对不同特征分配相应权重,进一步提升了聚类效果。实验结果说明该算法在机动通信网络自动划分中具有良好的准确率,为后续网络规划提供了基础支撑。Aiming at the requirements of division of the planning on maneuver communication network,a method on automatic division of maneuver communication network based on combined weighted multi-feature K-means clustering is put forward.The clustering number is determined through Elbow and the node connectivity is considered in choosing initial clustering center.The method avoids the uncertainty of initial clustering center in the traditional K-means clustering.Lastly allocating weighed value between different characteristics improves the effectiveness of clustering.The test shows that the method has good accuracy in automatic division of maneuver communication network and provides basic support for future network planning.

关 键 词：网络划分 加权K-means 网络规划 节点联通度 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]