Using the Modified Allan Variance for Accurate Estimation of the Hurst Parameter of Long-Range Dependent Traffic

TL;DR

This paper introduces a modified Allan Variance-based method for accurately estimating the Hurst parameter in long-range dependent network traffic, demonstrating superior accuracy and applicability compared to wavelet-based techniques.

Contribution

The paper adapts the Modified Allan Variance for Hurst parameter estimation, providing a novel, more accurate method for analyzing long-range dependence in network traffic.

Findings

MAVAR outperforms wavelet-based methods in accuracy

MAVAR is effective on real IP traffic data

The method is robust against nonstationary signals

Abstract

Internet traffic exhibits self-similarity and long-range dependence (LRD) on various time scales. A well studied issue is the estimation of statistical parameters characterizing traffic self-similarity and LRD, such as the Hurst parameter H. In this paper, we propose to adapt the Modified Allan Variance (MAVAR), a time-domain quantity originally conceived to discriminate fractional noise in frequency stability measurement, to estimate the Hurst parameter of LRD traffic traces and, more generally, to identify fractional noise components in network traffic. This novel method is validated by comparison to one of the best techniques for analyzing self-similar and LRD traffic: the logscale diagram based on wavelet analysis. Both methods are applied to pseudo-random LRD data series, generated with assigned values of H. The superior spectral sensitivity of MAVAR achieves outstanding accuracy in estimating H, even better than the logscale method. The behaviour of MAVAR with most common deterministic signals that yield nonstationarity in data under analysis is also studied. Finally, both techniques are applied to a real IP traffic trace, providing a sound example of the usefulness of MAVAR also in traffic characterization, to complement other established techniques as the logscale method.