On the applicability of the use of the Kolmogorov–Wiener filter for prediction of heavy-tail stationary processes

Abstract

This work is devoted to the investigation of the applicability of the use of the Kolmogorov–Wiener filter for prediction of heavy-tail stationary processes. The motivation of the investigation is as follows. The problem of telecommunication traffic forecasting is important for telecommunications. There are a plenty of rather sophisticated approaches to the telecommunication traffic prediction in different cases. For example, the ARIMA models and the neural network approaches are used for traffic prediction for non-stationary traffic.