期刊文献+

AI智能运维在5GC SA网络中的应用研究 被引量:5

Application Research of AI Technology in 5GC SA Network Operation and Maintenance
下载PDF
导出
摘要 5G带来通信网络能力提升的同时,全新的网络形态和网络规模也给运维工作带来了极大的挑战,而变化最大的5G核心网,由传统CT网络演变成NFV+SDN网络,传统的OSS工具已难以支撑。随着大数据和人工智能的发展,采用AI技术实现智能运维成为解决5GC网络监控、隐患发现、故障定位/修复的主要手段。重点探讨AI算法在5GC网络指标异常检测、KPI-告警关联中的应用。 While 5G brings about the improvement of communication network capability,the brand new network form and network scale also bring great challenges to the operation and maintenance work.5G core network,which has changed the most,has evolved from the traditional CT network to the NFV+SDN network,and the traditional OSS tools are no longer able to support it.With the development of big data and artificial intelligence,adopting AI technology to realize intelligent operation and maintenance has become the main means to solve 5GC network monitoring,hidden trouble discovery,and fault location/repair.It will focus on the application research of AI algorithm in 5GC network indicator anomaly detection and KPI-alarm association.
作者 张勉知 刘惜吾 叶晓斌 姚丽红 程亚锋 马丹丹 Zhang Mianzhi;Liu Xiwu;Ye Xiaobin;Yao Lihong;Cheng Yafeng;Ma Dandan(China Unicom Guangdong Branch,Guangzhou 510627,China)
出处 《邮电设计技术》 2020年第10期47-50,共4页 Designing Techniques of Posts and Telecommunications
关键词 智能运维 AI技术 5GC 异常检测 KPI-告警关联 Intelligence operations AI technology 5GC Anomaly detection KPI-Alarm correlation
  • 相关文献

参考文献4

二级参考文献38

  • 1姜吉发.一种跨语句汉语事件信息抽取方法[J].计算机工程,2005,31(2):27-29. 被引量:12
  • 2Ye Nong, Li Xiangyang, Chen Qiang, et al. Probabilistic Techniques for Intrusion Detection Based on Computer Audit Data[J]. IEEE Transaction on Systems, Man and Cybemetics, 2001, 31(4).
  • 3Zhang Zonghua, Shen Hong. Online Training of SVMs for Real-time Intrusion Detection[C]. Proc. of the 18th Intemational Conference on Advanced Information Networking and Application, Fukuoka, Japan,2004.
  • 4Scholkopf B. Estimating the Support of a High-dimensionaI Distribution[D]. Israel: Department of Computer Science, University of Haifa, 2001.
  • 5Lau K W, Wu Q H. Online Training of Support Vector Classifier[J].Pattern Recognition, 2003, 36(2): 1913-1920.
  • 6Alarcon-Aquino V, Barria J A. Muhiresolution FIR neural-network-based learning algorithm applied to network traffic prediction [ J ]. IEEE Transactions on Systems, Man and Cybernetics, Part C. Applications and Reviews, 2006, 36(2) . 208 -220.
  • 7Laner M, Svoboda P, Rupp M. Parsimonious fitting of long-range dependent network traffic using ARMA models [J]. IEEE 2ommumcatons Letters, 2013, 17 (12) . 2368 - 2371.
  • 8Wang J. A process level network traffic prediction algorithm based on ARIMA model in smart substation[ C]//1EEE International Conference on Signal Processing, Communications and Computing. Piscataway, NJ, USA . IEEE, 2013 . 1 - 5.
  • 9Yadav R K, Balakrishnan M. Comparative evaluation of ARIMA and ANFIS for modeling of wireless network traffic time series[ J]. EURASIP Journal on Wireless Communications and Networking, 2014(1) . 15.
  • 10Liao W J, Balzen Z. LSSVM network flow prediction based on the self-adaptive genetic algorithm optimization[ J]. Journal of Networks, 2013, 8(2) . 507 -512.

共引文献64

同被引文献47

引证文献5

二级引证文献6

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部