ZTE

ZTE Communications ›› 2016, Vol. 14 ›› Issue (2): 47-55.DOI: 10.3969/j.issn.1673-5188.2016.02.006

• Review • Previous Articles     Next Articles

A Survey on Event Mining for ICT Network Infrastructure Management

LIU Zheng, LI Tao, WANG Junchang   

  1. Nanjing University of Posts and Telecommunications, Nanjing 210023, China
  • Received:2016-01-05 Online:2016-04-01 Published:2019-11-27
  • About author:LIU Zheng (zliu@njupt.edu.cn) is an assistant professor at the school of computer science and technology, the Nanjing University of Posts and Telecommunications, China. He obtained his PhD from the Chinese University of Hong Kong, China in 2011. He was a research engineer with Huawei Technologies from 2011 to 2015. His research interests include mining and querying large graph data, mining multimedia data and mining event logs in network management. He has published research papers in major conferences including ICDE, ICDM, DASFAA, and PAKDD. He is an IEEE member.
    LI Tao (taoli@cs.fiu.edu) is dean and professor at the school of computer science and technology, the Nanjing University of Posts and Telecommunications, China. He received his PhD in computer science from the University of Rochester, USA in 2004. His research interests are in data mining, information retrieval, and computing system management. He was a recipient of an NSF CAREER Award and multiple IBM Faculty Research Awards. He is on the editorial boards of ACM Transactions on Knowledge Discovery from Data, IEEE Transactions on Knowledge and Data Engineering, and Knowledge and Information System Journal.
    WANG Junchang (wangjc@njupt.edu.cn) is a lecturer at Nanjing University of Posts and Telecommunications, China. He received a Ph.D. degree in computer science from University of Science and Technology of China. His research focuses on software defined networking (SDN), network management, and high - performance computing (HPC). Biographies Review A Survey on Event Mining for ICT Network Infrastructure Management LIU Zheng, LI Tao, and WANG Junchang April
  • Supported by:
    This work was supported in part by Ministry of Education/China Mobile joint research grant under Project No.5-10; and Nanjing University of Posts and Telecommunications under Grants No. NY214135 and NY215045

A Survey on Event Mining for ICT Network Infrastructure Management

LIU Zheng, LI Tao, WANG Junchang   

  1. Nanjing University of Posts and Telecommunications, Nanjing 210023, China
  • 作者简介:LIU Zheng (zliu@njupt.edu.cn) is an assistant professor at the school of computer science and technology, the Nanjing University of Posts and Telecommunications, China. He obtained his PhD from the Chinese University of Hong Kong, China in 2011. He was a research engineer with Huawei Technologies from 2011 to 2015. His research interests include mining and querying large graph data, mining multimedia data and mining event logs in network management. He has published research papers in major conferences including ICDE, ICDM, DASFAA, and PAKDD. He is an IEEE member.
    LI Tao (taoli@cs.fiu.edu) is dean and professor at the school of computer science and technology, the Nanjing University of Posts and Telecommunications, China. He received his PhD in computer science from the University of Rochester, USA in 2004. His research interests are in data mining, information retrieval, and computing system management. He was a recipient of an NSF CAREER Award and multiple IBM Faculty Research Awards. He is on the editorial boards of ACM Transactions on Knowledge Discovery from Data, IEEE Transactions on Knowledge and Data Engineering, and Knowledge and Information System Journal.
    WANG Junchang (wangjc@njupt.edu.cn) is a lecturer at Nanjing University of Posts and Telecommunications, China. He received a Ph.D. degree in computer science from University of Science and Technology of China. His research focuses on software defined networking (SDN), network management, and high - performance computing (HPC). Biographies Review A Survey on Event Mining for ICT Network Infrastructure Management LIU Zheng, LI Tao, and WANG Junchang April
  • 基金资助:
    This work was supported in part by Ministry of Education/China Mobile joint research grant under Project No.5-10; and Nanjing University of Posts and Telecommunications under Grants No. NY214135 and NY215045

PDF

Abstract: Managing largescale complex network infrastructures is challenging due to the huge number of heterogeneous network elements. The goal of this survey is to provide an overview of event mining techniques applied in the network management domain. Event mining includes a series of techniques for automatically and effectively discovering valuable knowledge from historical event/log data. We present three research challenges (i.e., event generation, root cause analysis, and failure prediction) for event mining in network management and introduce the corresponding solutions. Event generation (i.e., converting messages in log files into structured events) is the first step in many event mining applications. Automatic root cause analysis can locate the faulty elements/components without the help of experienced domain experts. Failure prediction in proactive fault management improves network reliability. The representative studies to address the three aforementioned challenges are reviewed and their main ideas are summarized in the survey. In addition, our survey shows that using event mining techniques can improve the network management efficiency and reduce the management cost.

Key words: event mining, failure prediction, log analysis, network infra-structure management, root cause analysis

摘要： Managing largescale complex network infrastructures is challenging due to the huge number of heterogeneous network elements. The goal of this survey is to provide an overview of event mining techniques applied in the network management domain. Event mining includes a series of techniques for automatically and effectively discovering valuable knowledge from historical event/log data. We present three research challenges (i.e., event generation, root cause analysis, and failure prediction) for event mining in network management and introduce the corresponding solutions. Event generation (i.e., converting messages in log files into structured events) is the first step in many event mining applications. Automatic root cause analysis can locate the faulty elements/components without the help of experienced domain experts. Failure prediction in proactive fault management improves network reliability. The representative studies to address the three aforementioned challenges are reviewed and their main ideas are summarized in the survey. In addition, our survey shows that using event mining techniques can improve the network management efficiency and reduce the management cost.

关键词: event mining, failure prediction, log analysis, network infra-structure management, root cause analysis