Forecasting Highly-Aggregate Internet Time Series Using Wavelet Techniques

Simple item page
dc.contributor.authorEdwards, Samuel Zacharyen
dc.contributor.committeechairMili, Lamine M.en
dc.contributor.committeememberDaSilva, Luiz A.en
dc.contributor.committeememberBell, Amy E.en
dc.contributor.departmentElectrical and Computer Engineeringen
dc.date.accessioned2014-03-14T20:38:33Zen
dc.date.adate2006-08-28en
dc.date.available2014-03-14T20:38:33Zen
dc.date.issued2006-05-15en
dc.date.rdate2006-08-28en
dc.date.sdate2006-05-25en
dc.description.abstractThe U.S. Coast Guard maintains a network structure to connect its nation-wide assets. This paper analyzes and models four highly aggregate traces of the traffic to/from the Coast Guard Data Network ship-shore nodes, so that the models may be used to predict future system demand. These internet traces (polled at 5â 40â intervals) are shown to adhere to a Gaussian distribution upon detrending, which imposes limits to the exponential distribution of higher time-resolution traces. Wavelet estimation of the Hurst-parameter is shown to outperform estimation by another common method (Sample-Variances). The First Differences method of detrending proved problematic to this analysis and is shown to decorrelate AR(1) processes where 0.65< phi1 <1.35 and correlate AR(1) processes with phi1 <-0.25. The Hannan-Rissanen method for estimating (phi,theta) is employed to analyze this series and a one-step ahead forecast is generated.en
dc.description.degreeMaster of Scienceen
dc.identifier.otheretd-05252006-085100en
dc.identifier.sourceurlhttp://scholar.lib.vt.edu/theses/available/etd-05252006-085100/en
dc.identifier.urihttp://hdl.handle.net/10919/33223en
dc.publisherVirginia Techen
dc.relation.haspartThesis_Edwards.pdfen
dc.rightsIn Copyrighten
dc.rights.urihttp://rightsstatements.org/vocab/InC/1.0/en
dc.subjectLong-range Dependenceen
dc.subjectSelf-Similarityen
dc.subjectShort-range Dependenceen
dc.subjectHurst parameteren
dc.subjectTime Series Analysisen
dc.subjectFractalsen
dc.subjectWaveletsen
dc.subjectForecasten
dc.titleForecasting Highly-Aggregate Internet Time Series Using Wavelet Techniquesen
dc.typeThesisen
thesis.degree.disciplineElectrical and Computer Engineeringen
thesis.degree.grantorVirginia Polytechnic Institute and State Universityen
thesis.degree.levelmastersen
thesis.degree.nameMaster of Scienceen

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Thesis_Edwards.pdf
Size:
3.1 MB
Format:
Adobe Portable Document Format
Download

Collections

Masters Theses