Time Series Analysis of Computer Network Traffic in a Dedicated Link Aggregation

TL;DR

This study applies fractal analysis to high-speed network traffic, confirming that such traffic exhibits fractal behavior and long-range dependence, which is crucial for understanding and modeling network performance.

Contribution

It demonstrates the presence of fractal behavior and long-range dependence in high-speed network traffic using specific fractal analysis techniques.

Findings

Traffic exhibits fractal behavior with Hurst exponent between 0.5 and 1.

Fractal dimension ranges from 1 to 1.5.

Correlation coefficient between -0.5 and 0.

Abstract

Fractal behavior and long-range dependence are widely observed in measurements and characterization of traffic flow in high-speed computer networks of different technologies and coverage levels. This paper presents the results obtained when applying fractal analysis techniques on a time series obtained from traffic captures coming from an application server connected to the Internet through a high-speed link. The results obtained show that traffic flow in the dedicated high-speed network link have fractal behavior when the Hurst exponent is in the range of 0.5, 1, the fractal dimension between 1, 1.5, and the correlation coefficient between -0.5, 0. Based on these results, it is ideal to characterize both the singularities of the traffic and its impulsiveness during a fractal analysis of temporal scales. Finally, based on the results of the time series analyses, the fact that the traffic flows of current computer networks exhibit fractal behavior with a long-range dependency is reaffirmed.