Towards the improvement of performance anomaly prediction

Author

Zhanikeev, Marat ; Tanaka, Yoshiaki

Author_Institution

Global Inf. & Telecommun. Inst., Waseda Univ., Tokyo, Japan

fYear

2005

fDate

26-29 Sept. 2005

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.

Keywords

neural nets; pattern recognition; performance evaluation; telecommunication network management; NetFlow data; anomaly monitoring; anomaly prediction; cross-traffic interference; end-to-end probing; network cross-traffic; network management; neural network; pattern recognition; performance improvement; performance monitoring agents; prediction quality; pro-active abilities; raw SNMP; Counting circuits; Decision making; Engineering management; Interference; Monitoring; Neural networks; Pattern recognition; Resilience; Scalability; Telecommunication network management;

fLanguage

English

Publisher

ieee

Conference_Titel

Internet, 2005.The First IEEE and IFIP International Conference in Central Asia on

Print_ISBN

0-7803-9179-9

Type

conf

DOI

10.1109/CANET.2005.1598205

Filename

1598205