NETradamus: A forecasting system for system event messages

Author

Clemm, Alexander ; Hartwig, Malte

Author_Institution

Cisco Syst., San Jose, CA, USA

fYear

2010

fDate

19-23 April 2010

Firstpage

623

Lastpage

630

Abstract

Proactive service assurance depends on the ability to anticipate problems in a network. This paper presents a system to forecast high-severity system event messages before they occur. Forecasts are based on a stream of syslog messages from devices, which is compared and scored against a set of codes that are representative of known problem event patterns. The system includes a component to mine relevant event patterns from past problem occurrences. In addition to describing the techniques and algorithms that the system is based on, the paper also provides an assessment of the effectiveness of those techniques.

Keywords

computer network management; data mining; forecasting theory; NETradamus; event forecasting system; proactive service assurance; problem event patterns; syslog messages; system event messages; Character recognition; Computer crashes; Degradation; Fault diagnosis; Monitoring; Network servers; Pattern recognition; Prediction methods; Robustness; Weather forecasting; Forecasting; Network Fault Diagnosis; Networks; Prediction Methods;

fLanguage

English

Publisher

ieee

Conference_Titel

Network Operations and Management Symposium (NOMS), 2010 IEEE

Conference_Location

Osaka

ISSN

1542-1201

Print_ISBN

978-1-4244-5366-5

Electronic_ISBN

1542-1201

Type

conf

DOI

10.1109/NOMS.2010.5488430

Filename

5488430