In order to estimate the Hurst parameter of Internet traffic data, it has been recently proposed a log-regression estimator based on the so-called modified Allan variance (MAVAR). Simulations have shown that this estimator achieves higher accuracy and better confidence when compared with an other method of common use based on wavelet analysis. Here we link it to the wavelets setting and stress why a different analysis for the two approaches is required. We then focus on the asymptotic analysis of the MAVAR log-regression estimator and provide new formulas for the related confidence intervals. By numerical evaluation, we analyze these formulas and make a comparison between three suitable choices on the regression weights, also optimizing over different choices on the data progression.

Analysis of a Hurst Parameter Estimator Based on the Modified Allan Variance

BREGNI, STEFANO;
2012-01-01

Abstract

In order to estimate the Hurst parameter of Internet traffic data, it has been recently proposed a log-regression estimator based on the so-called modified Allan variance (MAVAR). Simulations have shown that this estimator achieves higher accuracy and better confidence when compared with an other method of common use based on wavelet analysis. Here we link it to the wavelets setting and stress why a different analysis for the two approaches is required. We then focus on the asymptotic analysis of the MAVAR log-regression estimator and provide new formulas for the related confidence intervals. By numerical evaluation, we analyze these formulas and make a comparison between three suitable choices on the regression weights, also optimizing over different choices on the data progression.
2012
2012 IEEE Global Communications Conference (GLOBECOM)
9781467309219
telecommunication traffic; self-similarity; modified Allan variance; scaling, multifractal, self-affine, fractional Brownian motion, heavy-tailed distribution, Levy-stable distribution
File in questo prodotto:
File Dimensione Formato  
06503362.pdf

Accesso riservato

: Post-Print (DRAFT o Author’s Accepted Manuscript-AAM)
Dimensione 1.45 MB
Formato Adobe PDF
1.45 MB Adobe PDF   Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11311/765604
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 2
  • ???jsp.display-item.citation.isi??? 1
social impact