DocumentCode
2037657
Title
Internet delay statistics: Measuring Internet feel using a dichotomous Hurst parameter
Author
DeVirgilio, Mark ; Pan, W. David ; Joiner, Laurie L. ; Wu, Dongsheng
Author_Institution
Dept. of Electr. & Comput. Eng., Univ. of Alabama in Huntsville, Huntsville, AL, USA
fYear
2012
fDate
15-18 March 2012
Firstpage
1
Lastpage
6
Abstract
As Internet delay times affect the perceptions of users, the ability to differentiate the feel of Internet sites using statistical measures beyond average packet delays may be of commercial value. One such statistical measure is the Hurst parameter of a long-range dependent (LRD) process. A dichotomous Hurst parameter derived from segmented day and night delay data suggests that variations in Internet delay statistics are real and may be caused by diurnal human activity.
Keywords
Internet; delays; social networking (online); statistical analysis; Internet delay statistics; Internet sites; LRD process; dichotomous Hurst parameter; diurnal human activity; long range dependent process; packet delay; statistical measure; Delay; Frequency measurement; IP networks; Internet; Servers; Time series analysis; Hurst parameter; Internet delays; fingerprinting; network feel;
fLanguage
English
Publisher
ieee
Conference_Titel
Southeastcon, 2012 Proceedings of IEEE
Conference_Location
Orlando, FL
ISSN
1091-0050
Print_ISBN
978-1-4673-1374-2
Type
conf
DOI
10.1109/SECon.2012.6196995
Filename
6196995
Link To Document