基于用户位置及流量变化监测室分质量的研究  

A study of monitoring indoor distribution quality based on user location and traffic changes

在线阅读下载全文

作  者:靳剑东 李倩倩 方媛 岑尧 薛世锋 JIN Jian-dong;LI Qian-qian;FANG Yuan;CEN Yao;XUE Shi-feng(China Mobile Group Shanxi Co.,Ltd.,Taiyuan 030032,China;Coal Geological Geophysical Exploration Surveying&Mapping Institute of Shanxi Province,Jinzhong 030600,China;China Mobile Group Design Institute Co.,Ltd.,Beijing 100080,China)

机构地区:[1]中国移动通信集团山西有限公司,太原030032 [2]山西省煤炭地质物探测绘院有限公司,晋中030600 [3]中国移动通信集团设计院有限公司,北京100080

出  处:《电信工程技术与标准化》2025年第3期68-72,共5页Telecom Engineering Technics and Standardization

摘  要:传统室分分布系统多节点且无源,无法监控,隐性故障难发现。日常监控室分小区业务量骤降去判定室分问题时,无法准确定位是人流减少还是隐性故障导致。为此,本文提出了一种基于用户位置及流量变化监控室分质量的方法,通过时序聚类算法和时段感知常驻小区识别算法,构建室分小区常驻用户画像,结合业务情况,实现用户变化情况的监控,识别非人员变动引起的突发业务骤降情况,发现室分分布系统隐性故障,提升网络运维的效率,减少故障处理时间,保障网络服务的稳定性和可靠性,提高用户感知。Traditional indoor distribution systems have multiple nodes and are passive,making it difficult to monitor and detect hidden faults.When the daily monitoring room detects a sudden drop in business volume in a residential area,it is difficult to accurately determine whether the problem is caused by a decrease in pedestrian flow or an implicit fault.Therefore,a method based on user location and traffic changes to monitor the quality of residential areas is proposed.By using time series clustering algorithm and time period perception resident area recognition algorithm,a resident user profile of residential areas is constructed.Combined with business situations,user changes are monitored to identify sudden business drops caused by non personnel changes,discover implicit faults in the residential distribution system,improve network operation and maintenance efficiency,reduce fault handling time,ensure the stability and reliability of network services,and enhance user perception.

关 键 词:室分小区 常驻用户画像 时序聚类算法 隐性故障 

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