Network-wide Statistical Modeling and Prediction of Computer Traffic

TL;DR

This paper presents a probabilistic modeling approach for network-wide traffic prediction that leverages limited measurements to improve accuracy and detect shifts in traffic patterns.

Contribution

It introduces a physically interpretable probabilistic model that uses expensive measurements to enhance traffic prediction with inexpensive data, applicable over multiple periods.

Findings

Model improves traffic prediction accuracy over using only inexpensive measurements.

The learned model remains effective across different traffic periods.

Application of the model enables detection and isolation of traffic shifts.

Abstract

In order to maintain consistent quality of service, computer network engineers face the task of monitoring the traffic fluctuations on the individual links making up the network. However, due to resource constraints and limited access, it is not possible to directly measure all the links. Starting with a physically interpretable probabilistic model of network-wide traffic, we demonstrate how an expensively obtained set of measurements may be used to develop a network-specific model of the traffic across the network. This model may then be used in conjunction with easily obtainable measurements to provide more accurate prediction than is possible with only the inexpensive measurements. We show that the model, once learned may be used for the same network for many different periods of traffic. Finally, we show an application of the prediction technique to create relevant control charts for detection and isolation of shifts in network traffic.