基于无监督聚类和频繁子图挖掘的电力通信网缺陷诊断与自动派单

吴季桦; 朱鹏宇; 吴子辰; 顾彬; 洪涛; 郭波; 王晶; 王敬宇

doi:10.11959/j.issn.1000-0801.2021253

您当前的位置：

首页 >

文章列表页 >

基于无监督聚类和频繁子图挖掘的电力通信网缺陷诊断与自动派单

研究与开发 | 更新时间：2024-06-05

- 基于无监督聚类和频繁子图挖掘的电力通信网缺陷诊断与自动派单
- Fault diagnosis and auto dispatchin of power communication network based on unsupervised clustering and frequent subgraph mining
- 电信科学 2021年37卷第11期页码：51-63
- 作者机构：
  
  1. 北京邮电大学网络与交换国家重点实验室，北京 100876
  2. 国网电力科学研究院有限公司，江苏南京 210012
  3. 国网江苏省电力有限公司信息通信分公司，江苏南京 210024
- 作者简介：
  
  [ "吴季桦（1998− ），女，北京邮电大学计算机学院硕士生，主要研究方向为云原生、知识图谱、子图挖掘" ]
  [ "朱鹏宇（1992− ），男，国网电力科学研究院有限公司工程师，主要研究方向为电力通信、人工智能、知识图谱" ]
  [ "吴子辰（1988− ），男，国网江苏省电力有限公司信息通信分公司高级工程师、信通调控中心副主任，主要研究方向为电力通信技术" ]
  [ "顾彬（1983− ），男，博士，国网江苏省电力有限公司信息通信分公司高级工程师，主要研究方向为电力通信技术" ]
  [ "洪涛（1994− ），男，国网江苏省电力有限公司信息通信分公司工程师，主要研究方向为电力光纤通信、计算机网络安全、人工智能技术等" ]
  [ "郭波（1977− ），男，国网江苏省电力有限公司信息通信分公司高级工程师、副总工程师，主要研究方向为电力信息通信技术" ]
  [ "王晶（1974− ），女，北京邮电大学计算机学院副教授，主要研究方向为业务网络、云网络、网络智能等" ]
  [ "王敬宇（1978− ），男，博士，北京邮电大学计算机学院教授、博士生导师，主要研究方向为智能网络、智能运维、边缘计算等" ]
- 基金信息：
  
  国家电网公司科技项目;Science and Technology Project of State Grid Corporation(5700-202040367A-0-0-00)
- DOI：10.11959/j.issn.1000-0801.2021253
  中图分类号： TP393
- 网络出版日期：2021-11，
  
  纸质出版日期：2021-11-20
- 稿件说明：
移动端阅览
吴季桦, 朱鹏宇, 吴子辰, 等. 基于无监督聚类和频繁子图挖掘的电力通信网缺陷诊断与自动派单[J]. 电信科学, 2021,37(11):51-63.

Jihua WU, Pengyu ZHU, Zichen WU, et al. Fault diagnosis and auto dispatchin of power communication network based on unsupervised clustering and frequent subgraph mining[J]. Telecommunications science, 2021, 37(11): 51-63.
吴季桦, 朱鹏宇, 吴子辰, 等. 基于无监督聚类和频繁子图挖掘的电力通信网缺陷诊断与自动派单[J]. 电信科学, 2021,37(11):51-63. DOI： 10.11959/j.issn.1000-0801.2021253.

Jihua WU, Pengyu ZHU, Zichen WU, et al. Fault diagnosis and auto dispatchin of power communication network based on unsupervised clustering and frequent subgraph mining[J]. Telecommunications science, 2021, 37(11): 51-63. DOI： 10.11959/j.issn.1000-0801.2021253.

摘要

缺陷诊断一直是电力通信领域研究的难点之一。基于人工规则的缺陷诊断已经无法应对告警数据的海量增长。基于有监督学习的智能方法需要大量的标注数据和较长的系统构建时间，且大多面向指标性数据，实现部署缺乏可行性。面向告警数据，提出一种基于无监督聚类和频繁子图挖掘实现告警归并和缺陷模式发现的自学习算法，设计了一个自动化完成缺陷诊断及处置的架构。该架构具有良好的可扩展性和迭代更新能力，并部署于实际缺陷自动派单系统中。通过真实场景数据集进行实验验证，结果显示出良好的性能表现，实现了对缺陷的及时发现及精准派单维护。

Abstract

Fault diagnosis is one of the most challenging tasks in power communication.The fault diagnosis based on rules can no longer meet the demand of massive alarms processing.The existing approaches based on the supervised learning need large sets of the labeled data and sufficient time to train models for processing continuous data instead of alarms

which are far behind the feasibility of deployment.As for alarm correlation and fault pattern discovery

a self-learning algorithm based on the density-based clustering and frequent subgraph mining was proposed.A novel approach for automatic fault diagnosis and dispatch were also introduced

which provided the scalable and self-renewing ability and had been deployed to the automatic fault dispatch system.Experiments in the real-world datasets authorized the effectiveness for timely fault discovery and targeted fault dispatch.

关键词

Keywords

references

GARDNER R D , HARLE D A . Methods and systems for alarm correlation [C ] // Proceedings of Proceedings of GLOBECOM'96.1996 IEEE Global Telecommunications Conference . Piscataway:IEEE Press , 1996 : 136 - 140 .

MAZDZIARZ A . Alarm correlation in mobile telecommunications networks based on k-means cluster analysis method [J ] . Journal of Telecommunications and Information Technology , 2018 ( 2 ): 95 - 102 .

WEN L , LI X Y , GAO L , et al . A new convolutional neural network-based data-driven fault diagnosis method [J ] . IEEE Transactions on Industrial Electronics , 2018 , 65 ( 7 ): 5990 - 5998 .

XIAO F , ZHAO Y , WEN J , et al . Bayesian network based FDD strategy for variable air volume terminals [J ] . Automation in Construction , 2014 ( 41 ): 106 - 118 .

WANG J Y , JING Y H , QI Q , et al . ALSR:an adaptive label screening and relearning approach for interval-oriented anomaly detection [J ] . Expert Systems With Applications , 2019 ( 136 ): 94 - 104 .

QI Q , SHEN R Y , WANG J Y , et al . Spatial-temporal learning-based artificial intelligence for IT operations in the edge network [J ] . IEEE Network , 2021 , 35 ( 1 ): 197 - 203 .

JAKOBSON G , WEISSMAN M . Alarm correlation [J ] . IEEE Network , 1993 , 7 ( 6 ): 52 - 59 .

SCHUBERT E , SANDER J , ESTER M , et al . DBSCAN revisited,revisited [J ] . ACM Transactions on Database Systems , 2017 , 42 ( 3 ): 1 - 21 .

YANG Y C , WANG Y P , WEI Y . Adaptive density peak clustering for determinging cluster center [C ] // Proceedings of 2019 15th International Conference on Computational Intelligence and Security (CIS) . Piscataway:IEEE Press , 2019 : 182 - 186 .

BOULOUTAS A T , CALO S , FINKEL A . Alarm correlation and fault identification in communication networks [J ] . IEEE Transactions on Communications , 1994 , 42 ( 234 ): 523 - 533 .

YOUSUF H , ZAINAL A Y , ALSHURIDEH M , et al . Artificial intelligence models in power system analysis [M ] // Artificial Intelligence for Sustainable Development:Theory,Practice and Future Applications . Cham : Springer International Publishing , 2020 : 231 - 242 .

DARRAB S , ERGENC B . Vertical pattern mining algorithm for multiple support thresholds [J ] . Procedia Computer Science , 2017 ( 112 ): 417 - 426 .

HARTMANIS J . Computers and Intractability [EB ] . SIAM Review , 1982 .

YAN X F , HAN J W . gSpan:graph-based substructure pattern mining [C ] // Proceedings of 2002 IEEE International Conference on Data Mining . Piscataway:IEEE Press , 2002 : 721 - 724 .

XIONG H , LI Z M . Clustering validation measures [M ] // Data Clustering : Chapman and Hall/CRC , 2018 : 571 - 606 .

HOU J , LIU W X . Evaluating the density parameter in density peak based clustering [C ] // Proceedings of 2016 Seventh International Conference on Intelligent Control and Information Processing (ICICIP) . Piscataway:IEEE Press , 2016 : 68 - 72 .

NOWOSAD J , STEPINSKI T F . Spatial association between regionalizations using the information-theoretical V-measure [J ] . International Journal of Geographical Information Science , 2018 , 32 ( 12 ): 2386 - 2401 .

浏览量

338

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

数模混合交织调制的电力通信专网研究

基于数据感知融合的电力通信网络智能运维

电力PTN设备网管安全性