基于机器学习的射灯天线监控方法研究和应用  

Research and application of monitoring method for spotlight antenna based on machine learning

在线阅读下载全文

作  者:谌晓明 许清 CHEN Xiao-ming;XU Qing(China Mobile Group Hunan Co.,Ltd.,Changsha 410001,China;China Mobile Group Design Institute Co.,Ltd.Hunan Branch,Changsha 410003,China)

机构地区:[1]中国移动通信集团湖南有限公司,长沙410001 [2]中国移动通信集团设计院有限公司湖南分公司,长沙410003

出  处:《电信工程技术与标准化》2023年第1期56-61,共6页Telecom Engineering Technics and Standardization

摘  要:目前,4G和5G网络室分系统对天线等无源器件缺乏实时有效的监控手段,本文通过采集UE MR数据并进行聚类训练获得室分小区的多个类簇,利用Boxplot函数计算类簇的波动阈值区间,结合工参建立每个射灯天线与类簇的初始映射覆盖关系模型,最后判断波动是否在阈值区间,实现监控射灯天线等无源器件是否存在异常的目的。At present,the indoor distribution systems of 4G and 5G networks lack real-time and effective monitoring means for passive devices such as antennas.In this paper,multiple clusters of indoor distribution cells are obtained by collecting UE MR data for clustering training,using Boxplot function to calculate the fl uctuation threshold range of multiple clusters,and combined with engineering parameters,the initial mapping coverage relationship model between each spotlight antenna and cluster is established.Finally,judge whether the fl uctuation is in the threshold range,so as to realize the purpose of monitoring whether the passive components such as spotlight antenna are abnormal.

关 键 词:室分系统 无源器件 大数据 DBSCAN算法 Boxplot函数 

分 类 号:TN929.5[电子电信—通信与信息系统]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象