Towards the improvement of performance anomaly prediction

Marat Zhanikeev, Yoshiaki Tanaka

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Growing demand for pro-active abilities in network management requires performance monitoring agents not only to be able to monitor the anomalies, but also to predict future occurrences. Recent research in this area would usually apply a neural network algorithm on raw SNMP or NetFlow data to obtain the knowledge about the patterns in performance data. The results are not always satisfactory due to highly unpredictable nature of cross-traffic in the network. This paper attempts to improve the prediction quality by using data obtained from end-to-end probing. The results prove higher resilience to cross-traffic interference and better pattern recognition.

Original languageEnglish
Title of host publicationFirst IEEE and IFIP International Conference in Central Asia on Internet, 2005
DOIs
Publication statusPublished - 2005 Dec 1
EventFirst IEEE and IFIP International Conference in Central Asia on Internet, 2005 - Bishkek, Kyrgyzstan
Duration: 2005 Sep 262005 Sep 28

Publication series

NameFirst IEEE and IFIP International Conference in Central Asia on Internet, 2005
Volume2005

Conference

ConferenceFirst IEEE and IFIP International Conference in Central Asia on Internet, 2005
CountryKyrgyzstan
CityBishkek
Period05/9/2605/9/28

ASJC Scopus subject areas

  • Engineering(all)

Fingerprint Dive into the research topics of 'Towards the improvement of performance anomaly prediction'. Together they form a unique fingerprint.

Cite this