Title :
Internet delay statistics: Measuring internet feel using a dichotomous Hurst parameter
Author :
DeVirgilio, Mark ; Pan, W.D. ; Joiner, Laurie L. ; Dongsheng Wu
Author_Institution :
Dept. of Electr. & Comput. Eng., Univ. of Alabama in Huntsville, Huntsville, AL, USA
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; statistical analysis; Internet delay statistics; Internet delay times; Internet feel; Internet sites; LRD process; average packet delays; dichotomous hurst parameter; diurnal human activity; long-range dependent process; segmented day and night delay data; user perceptions; Delays; Frequency measurement; IP networks; Internet; Servers; Time series analysis; Hurst parameter; Internet delays; fingerprinting; network feel;
Conference_Titel :
Southeastcon, 2013 Proceedings of IEEE
Conference_Location :
Jacksonville, FL
Print_ISBN :
978-1-4799-0052-7
DOI :
10.1109/SECON.2013.6567481