Intelligent Monitoring Method Using Time Varying Binomial Distribution Models for Pseudo-Periodic Communication Traffic

Abstract

In this paper, we deal with the degradation detection problem for telecommunication network gateways. The time series to be monitored is non-stationary but almost periodic (pseudo-periodic). The authors propose a technique called “optimization of partition model” which generates local stationary models for a pseudo-periodic time series. The optimization is based on the minimal AIC principle. The technique called SPRT is also applied to make efficient decisions. Experiments to evaluate methods for optimization, incremental model update, and the comparison with the conventional method are conducted with real data. The result shows the proposed method is effective and makes more precises decision than the conventional one.