Publication detail

Using Rule-Based Decision Trees for Automatic Passive Diagnostics of the Network Problems

HOLKOVIČ, M. RYŠAVÝ, O.

Original Title

Using Rule-Based Decision Trees for Automatic Passive Diagnostics of the Network Problems

Type

journal article - other

Language

English

Original Abstract

Network troubleshooting often requires a detailed analysis that may involve network packet capturing and a manual analysis using tools such as Wireshark. This is time-consuming and requires deep knowledge of communication protocols. Therefore this domain is a suitable candidate for the deployment of an expert system. In this paper, we consider a rule-based system integrating the expert knowledge that performs an automatic root cause analysis of network problems identifiable from network communications. The system is open, thus it is possible to add new rules as needed, e.g., for specific and recurring cases of a target environment. The rules are evaluated in a tree-based fashion, which enables us to collect additional information during the problem search to better explain the possible causes. We successfully deployed the tool as part of a commercial tool for network monitoring.

Keywords

Network diagnostics, passive network monitoring, rule-based diagnostics, fault tree analysis, event-based diagnostics, decision trees.

Authors

HOLKOVIČ, M.; RYŠAVÝ, O.

Released

30. 6. 2020

ISBN

1942-2644

Periodical

International Journal on Advances in Networks and Services

Year of study

2020

Number

1

State

United States of America

Pages from

1

Pages to

10

Pages count

10

URL

BibTex

@article{BUT163425,
  author="Martin {Holkovič} and Ondřej {Ryšavý}",
  title="Using Rule-Based Decision Trees for Automatic Passive Diagnostics of the Network Problems",
  journal="International Journal on Advances in Networks and Services",
  year="2020",
  volume="2020",
  number="1",
  pages="1--10",
  issn="1942-2644",
  url="http://www.iariajournals.org/networks_and_services/netser_v13_n12_2020_paged.pdf"
}

Documents