电信科学 ›› 2022, Vol. 38 ›› Issue (11): 113-122.doi: 10.11959/j.issn.1000-0801.2022269

• 研究与开发 • 上一篇    下一篇

跨专业承载网络智能运维研究与应用

韩赛1, 张冬月1, 王泽林1, 王光全1, 李奥1, 方遒铿2, 马红兵3   

  1. 1 中国联合网络通信有限公司研究院,北京 100048
    2 中国联合网络通信有限公司广东省分公司,广东 广州 510660
    3 中国联合网络通信集团有限公司,北京 100032
  • 修回日期:2022-10-08 出版日期:2022-11-20 发布日期:2022-11-01
  • 作者简介:韩赛(1988- ),女,博士,中国联合网络通信有限公司研究院高级工程师,主要研究方向为网络智能、自智网络等
    张冬月(1995- ),女,中国联合网络通信有限公司研究院助理工程师,主要研究方向为网络智能等
    王泽林(1983- ),男,中国联合网络通信有限公司研究院高级工程师,主要研究方向为IP、云网、白盒、SDN技术等
    王光全(1968- ),男,中国联合网络通信有限公司研究院教授级高级工程师,主要研究方向为通信网络的规划、新技术演进、标准制定等
    李奥(1994- ),女,中国联合网络通信有限公司研究院助理工程师,主要研究方向为网络智能等
    方遒铿(1980- ),男,中国联合网络通信有限公司广东省分公司工程师,主要研究方向为光网络、IP承载等
    马红兵(1967- ),男,中国联合网络通信集团有限公司科技创新部总经理、正高级工程师,主要研究方向为无线通信领域新技术研究、标准制定、技术试验等

Research and applications on intelligent operations of cross-professional carrying network

Sai HAN1, Dongyue ZHANG1, Zelin WANG1, Guangquan WANG1, Ao LI1, Qiukeng FANG2, Hongbing MA3   

  1. 1 Research Institute of China United Network Communications Co., Ltd., Beijing 100048, China
    2 China United Network Communications Company Limited Guangdong Branch, Guangzhou 510660, China
    3 China United Network Communications Group Co., Ltd., Beijing 100032, China
  • Revised:2022-10-08 Online:2022-11-20 Published:2022-11-01

摘要:

随着人工智能技术和网络日趋紧密地融合,未来网络的运营和生产应该是全面数字化、自动化和智能化的。目前跨专业网络故障定位主要依赖各专业运维人员分别进行分析和派单,导致排障时间长、重复派单等问题。为了节省人力工作,借助自动化和人工智能技术,研发了一套应用于实际现网的跨专业网络智能运维系统。该系统可对IPRAN和OTN关联的拓扑信息以及实时的IPRAN和OTN告警数据进行综合分析,精准定位根因告警,确定故障位置,实现自动派单。该系统构建了跨专业的故障自动诊断能力,将故障定位时间由传统的2 min缩短为几十毫秒,极大减少故障处理时间和人工工作,可覆盖现网大部分故障种类。

关键词: 跨专业网络, 故障定位, 智能运维

Abstract:

With the increasingly close integration of artificial intelligence technology and networks, the operation and production of networks in the future should be fully digitalized, automated and intelligent.At present, fault locating of cross-professional network mainly relies on operation and maintenance staff of each professional network to analyze and dispatch orders, resulting in long trouble clearing time and repeated orders.In order to save manual work, with the help of automation and artificial intelligent technologies, a cross-professional network intelligent operation and maintenance system was developed and applied in real network.The associated topology information of IPRAN and OTN, along with the real-time IPRAN and OTN alarm data were analyzed, the root cause alarm was located accurately, the fault location was determined, and dispatch order was achieved automatically.A automatic cross-professional fault diagnosis capability was built by the system, which reduced the fault locating time from traditional two minutes to tens of milliseconds, therefore, the manual work was reduced by more than 90%, and 95% fault types of the existing network could be covered.

Key words: cross-professional network, fault location, intelligent operation

中图分类号: 

No Suggested Reading articles found!