On the feasibility of utilizing correlations between user populations for traffic inference. Lan, K. & Heidemann, J. In Proceedings of the 30thIEEE International Conference on Local Computer Networks, pages 132–139, Sydney, Australia, November, 2005. IEEE. ![On the feasibility of utilizing correlations between user populations for traffic inference [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper abstract bibtex Previous studies of Internet traffic have shown that a very small percentage of flows consume most of the network bandwidth. It is important to understand the characteristics of such flows for traffic monitoring and modelling purposes. Several prior researchers have characterized such flows using different classification schemes: by size as elephant and mice; by duration as tortoise and dragonfly; and by burstiness as alpha and beta traffic. However, it is not clear how these different definitions of flows are related to each other. In our work, we study these ``heavy-hitter'' flows in four orthogonal dimensions, namely size, duration, rate and burstiness, and examine how they are correlated. This paper makes three contributions: First, we systematically characterize prior definitions for the properties of such heavy-hitter traffic. Second, we show that there are strong correlations between some combinations of size, rate and burstiness. Finally, we show that these correlations can be explained by transport and application-level protocol mechanisms.
@InProceedings{Lan05a,
author = "Kun-chan Lan and John Heidemann",
title = "On the feasibility of utilizing correlations between user populations for traffic inference",
booktitle = "Proceedings of the " # "30th" # " IEEE International Conference on Local Computer Networks",
year = 2005,
sortdate = "2005-11-01",
project = "ant, nocredit, saman",
jsubject = "traffic_modeling",
publisher = "IEEE",
address = "Sydney, Australia",
month = nov,
pages = "132--139",
jlocation = "johnh: pafile",
url = "https://ant.isi.edu/%7ejohnh/PAPERS/Lan05a.html",
pdfurl = "https://ant.isi.edu/%7ejohnh/PAPERS/Lan05a.pdf",
myorganization = "USC/Information Sciences Institute",
abstract = "
Previous studies of Internet traffic have shown that a very small
percentage of flows consume most of the network bandwidth. It is
important to understand the characteristics of such flows for traffic
monitoring and modelling purposes. Several prior researchers have
characterized such flows using different classification schemes: by
size as elephant and mice; by duration as tortoise and dragonfly; and
by burstiness as alpha and beta traffic. However, it is not clear
how these different definitions of flows are related to each other. In
our work, we study these ``heavy-hitter'' flows in four orthogonal
dimensions, namely size, duration, rate and burstiness, and examine
how they are correlated. This paper makes three contributions: First,
we systematically characterize prior definitions for the properties
of such heavy-hitter traffic. Second, we show that there are strong
correlations between some combinations of size, rate and
burstiness. Finally, we show that these correlations can be
explained by transport and application-level protocol mechanisms.
",
}
Downloads: 0
{"_id":"7uZDv8NGnfZuHms6p","bibbaseid":"lan-heidemann-onthefeasibilityofutilizingcorrelationsbetweenuserpopulationsfortrafficinference-2005","author_short":["Lan, K.","Heidemann, J."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"firstnames":["Kun-chan"],"propositions":[],"lastnames":["Lan"],"suffixes":[]},{"firstnames":["John"],"propositions":[],"lastnames":["Heidemann"],"suffixes":[]}],"title":"On the feasibility of utilizing correlations between user populations for traffic inference","booktitle":"Proceedings of the 30thIEEE International Conference on Local Computer Networks","year":"2005","sortdate":"2005-11-01","project":"ant, nocredit, saman","jsubject":"traffic_modeling","publisher":"IEEE","address":"Sydney, Australia","month":"November","pages":"132–139","jlocation":"johnh: pafile","url":"https://ant.isi.edu/%7ejohnh/PAPERS/Lan05a.html","pdfurl":"https://ant.isi.edu/%7ejohnh/PAPERS/Lan05a.pdf","myorganization":"USC/Information Sciences Institute","abstract":"Previous studies of Internet traffic have shown that a very small percentage of flows consume most of the network bandwidth. It is important to understand the characteristics of such flows for traffic monitoring and modelling purposes. Several prior researchers have characterized such flows using different classification schemes: by size as elephant and mice; by duration as tortoise and dragonfly; and by burstiness as alpha and beta traffic. However, it is not clear how these different definitions of flows are related to each other. In our work, we study these ``heavy-hitter'' flows in four orthogonal dimensions, namely size, duration, rate and burstiness, and examine how they are correlated. This paper makes three contributions: First, we systematically characterize prior definitions for the properties of such heavy-hitter traffic. Second, we show that there are strong correlations between some combinations of size, rate and burstiness. Finally, we show that these correlations can be explained by transport and application-level protocol mechanisms. ","bibtex":"@InProceedings{Lan05a,\n\tauthor = \"Kun-chan Lan and John Heidemann\",\n\ttitle = \t\"On the feasibility of utilizing correlations between user populations for traffic inference\",\n\tbooktitle = \t\"Proceedings of the \" # \"30th\" # \" IEEE International Conference on Local Computer Networks\",\n\tyear = \t\t2005,\n\tsortdate = \t\t\"2005-11-01\", \n\tproject = \"ant, nocredit, saman\",\n\tjsubject = \"traffic_modeling\",\n\tpublisher =\t\"IEEE\",\n\taddress =\t\"Sydney, Australia\",\n\tmonth =\t\tnov,\n\tpages =\t\t\"132--139\",\n\tjlocation =\t\"johnh: pafile\",\n\turl =\t\t\"https://ant.isi.edu/%7ejohnh/PAPERS/Lan05a.html\",\n\tpdfurl =\t\"https://ant.isi.edu/%7ejohnh/PAPERS/Lan05a.pdf\",\n\tmyorganization =\t\"USC/Information Sciences Institute\",\n\tabstract = \"\nPrevious studies of Internet traffic have shown that a very small\npercentage of flows consume most of the network bandwidth. It is\nimportant to understand the characteristics of such flows for traffic\nmonitoring and modelling purposes. Several prior researchers have\ncharacterized such flows using different classification schemes: by\nsize as elephant and mice; by duration as tortoise and dragonfly; and\nby burstiness as alpha and beta traffic. However, it is not clear\nhow these different definitions of flows are related to each other. In\nour work, we study these ``heavy-hitter'' flows in four orthogonal\ndimensions, namely size, duration, rate and burstiness, and examine\nhow they are correlated. This paper makes three contributions: First,\nwe systematically characterize prior definitions for the properties\nof such heavy-hitter traffic. Second, we show that there are strong\ncorrelations between some combinations of size, rate and\nburstiness. Finally, we show that these correlations can be\nexplained by transport and application-level protocol mechanisms.\n\",\n}\n\n","author_short":["Lan, K.","Heidemann, J."],"bibbaseid":"lan-heidemann-onthefeasibilityofutilizingcorrelationsbetweenuserpopulationsfortrafficinference-2005","role":"author","urls":{"Paper":"https://ant.isi.edu/%7ejohnh/PAPERS/Lan05a.html"},"metadata":{"authorlinks":{}}},"bibtype":"inproceedings","biburl":"https://bibbase.org/f/dHevizJoWEhWowz8q/johnh-2023-2.bib","dataSources":["YLyu3mj3xsBeoqiHK","fLZcDgNSoSuatv6aX","fxEParwu2ZfurScPY","7nuQvtHTqKrLmgu99"],"keywords":[],"search_terms":["feasibility","utilizing","correlations","between","user","populations","traffic","inference","lan","heidemann"],"title":"On the feasibility of utilizing correlations between user populations for traffic inference","year":2005}