Title :
Detection of Anomalous Behaviors in Networks From Traffic Measurements
Author :
Giorgi, Giada ; Narduzzi, Claudio
Author_Institution :
Dept. of Inf. Eng., Univ. of Padova, Padova
Abstract :
Analysis and monitoring of traffic measurements can provide a useful tool for diagnostics, troubleshooting, and performance analysis in networks. This paper presents a method for traffic analysis based on the theory of extreme values. Numerical time series obtained from traffic measurements are processed to compute statistical indicators and analyze them to detect significant local features, which may point to some critical network behavior.
Keywords :
statistical distributions; telecommunication network management; telecommunication traffic recording; Gumbel distribution; anomaly detection; extreme value theory; network measurement; traffic measurement; Anomaly detection; Gumbel distribution; extreme value theory; network measurement; probability paper;
Journal_Title :
Instrumentation and Measurement, IEEE Transactions on
DOI :
10.1109/TIM.2008.926046
