Trinocular: Understanding Internet Reliability Through Adaptive Probing. Quan, L., Heidemann, J., & Pradkin, Y. In Proceedings of the ACM SIGCOMM Conference , pages 255–266, Hong Kong, China, August, 2013. ACM. ![Trinocular: Understanding Internet Reliability Through Adaptive Probing [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper doi abstract bibtex Natural and human factors cause Internet outages—from big events like Hurricane Sandy in 2012 and the Egyptian Internet shutdown in Jan. 2011 to small outages every day that go unpublicized. We describe \emphTrinocular, an outage detection system that uses active probing to understand reliability of edge networks. Trinocular is \emphprincipled: deriving a simple model of the Internet that captures the information pertinent to outages, and populating that model through long-term data, and learning current network state through ICMP probes. It is \emphparsimonious, using Bayesian inference to determine how many probes are needed. On average, each Trinocular instance sends fewer than 20 probes per hour to each /24 network block under study, increasing Internet ``background radiation'' by less than 0.7%. Trinocular is also \emphpredictable and \emphprecise: we provide known precision in outage timing and duration. Probing in \emphrounds of 11 minutes, we detect 100% of outages one round or longer, and estimate outage duration within one-half round. Since we require little traffic, a single machine can track 3.4M /24 IPv4 blocks, all of the Internet currently suitable for analysis. We show that our approach is \emphsignificantly more accurate than the best current methods, with about one-third fewer false conclusions, and about 30% greater coverage at constant accuracy. We validate our approach using controlled experiments, use Trinocular to analyze two days of Internet outages observed from three sites, and re-analyze three years of existing data to develop trends for the Internet.
@InProceedings{Quan13c,
author = "Lin Quan and John Heidemann and Yuri Pradkin",
title = "Trinocular: Understanding Internet Reliability Through Adaptive Probing",
booktitle = "Proceedings of the " # " ACM SIGCOMM Conference ",
year = 2013,
sortdate = "2013-08-01",
pages = "255--266",
month = aug,
address = "Hong Kong, China",
publisher = "ACM",
jlocation = "johnh: pafile",
keywords = "internet outage detection, hurricane sandy,
bayesian inference",
copyrightholder = "ACM",
copyrightterms = " Permission to make digital or hard copies of portions of this work for personal or classroom use is granted without fee provided that the copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page in print or the first screen in digital media. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. otherwise, to republish, to post on servers, or to redistribute to lists, requires prior specific permission and/or a fee. Send written requests for republication to ACM Publications, Copyright & Permissions at the address above or fax +1 (212) 869-0481 or email permissions@acm.org." ,
url = "https://ant.isi.edu/%7ejohnh/PAPERS/Quan13c.html",
pdfurl = "https://ant.isi.edu/%7ejohnh/PAPERS/Quan13c.pdf",
myorganization = "USC/Information Sciences Institute",
doi = "http://doi.acm.org/10.1145/2486001.2486017",
project = "ant, lacrend, duoi",
abstract = "
Natural and human factors cause Internet outages---from big events
like Hurricane Sandy in 2012 and the Egyptian Internet shutdown in
Jan. 2011 to small outages every day that go unpublicized. We
describe \emph{Trinocular}, an outage detection system that uses
active probing to understand reliability of edge networks. Trinocular
is \emph{principled}: deriving a simple model of the Internet that
captures the information pertinent to outages, and populating that
model through long-term data, and learning current network state
through ICMP probes. It is \emph{parsimonious}, using Bayesian
inference to determine how many probes are needed. On average, each
Trinocular instance sends fewer than 20 probes per hour to
each /24 network block under study, increasing Internet ``background
radiation'' by less than 0.7\%. Trinocular is
also \emph{predictable} and \emph{precise}: we provide known precision in
outage timing and duration. Probing in \emph{rounds} of 11 minutes,
we detect 100\% of outages one round or longer, and estimate outage
duration within one-half round. Since we require little traffic, a
single machine can track 3.4M /24 IPv4 blocks, all of the Internet
currently suitable for analysis. We show that our approach
is \emph{significantly more accurate} than the best current methods, with
about one-third fewer false conclusions, and about 30\% greater
coverage at constant accuracy. We validate our approach using
controlled experiments, use Trinocular to analyze two days of Internet
outages observed from three sites, and re-analyze three years of
existing data to develop trends for the Internet.
",
}
Downloads: 0
{"_id":"gguS4K9wcw6ZDyako","bibbaseid":"quan-heidemann-pradkin-trinocularunderstandinginternetreliabilitythroughadaptiveprobing-2013","author_short":["Quan, L.","Heidemann, J.","Pradkin, Y."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"firstnames":["Lin"],"propositions":[],"lastnames":["Quan"],"suffixes":[]},{"firstnames":["John"],"propositions":[],"lastnames":["Heidemann"],"suffixes":[]},{"firstnames":["Yuri"],"propositions":[],"lastnames":["Pradkin"],"suffixes":[]}],"title":"Trinocular: Understanding Internet Reliability Through Adaptive Probing","booktitle":"Proceedings of the ACM SIGCOMM Conference ","year":"2013","sortdate":"2013-08-01","pages":"255–266","month":"August","address":"Hong Kong, China","publisher":"ACM","jlocation":"johnh: pafile","keywords":"internet outage detection, hurricane sandy, bayesian inference","copyrightholder":"ACM","copyrightterms":"Permission to make digital or hard copies of portions of this work for personal or classroom use is granted without fee provided that the copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page in print or the first screen in digital media. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. otherwise, to republish, to post on servers, or to redistribute to lists, requires prior specific permission and/or a fee. Send written requests for republication to ACM Publications, Copyright & Permissions at the address above or fax +1 (212) 869-0481 or email permissions@acm.org.","url":"https://ant.isi.edu/%7ejohnh/PAPERS/Quan13c.html","pdfurl":"https://ant.isi.edu/%7ejohnh/PAPERS/Quan13c.pdf","myorganization":"USC/Information Sciences Institute","doi":"http://doi.acm.org/10.1145/2486001.2486017","project":"ant, lacrend, duoi","abstract":"Natural and human factors cause Internet outages—from big events like Hurricane Sandy in 2012 and the Egyptian Internet shutdown in Jan. 2011 to small outages every day that go unpublicized. We describe \\emphTrinocular, an outage detection system that uses active probing to understand reliability of edge networks. Trinocular is \\emphprincipled: deriving a simple model of the Internet that captures the information pertinent to outages, and populating that model through long-term data, and learning current network state through ICMP probes. It is \\emphparsimonious, using Bayesian inference to determine how many probes are needed. On average, each Trinocular instance sends fewer than 20 probes per hour to each /24 network block under study, increasing Internet ``background radiation'' by less than 0.7%. Trinocular is also \\emphpredictable and \\emphprecise: we provide known precision in outage timing and duration. Probing in \\emphrounds of 11 minutes, we detect 100% of outages one round or longer, and estimate outage duration within one-half round. Since we require little traffic, a single machine can track 3.4M /24 IPv4 blocks, all of the Internet currently suitable for analysis. We show that our approach is \\emphsignificantly more accurate than the best current methods, with about one-third fewer false conclusions, and about 30% greater coverage at constant accuracy. We validate our approach using controlled experiments, use Trinocular to analyze two days of Internet outages observed from three sites, and re-analyze three years of existing data to develop trends for the Internet. ","bibtex":"@InProceedings{Quan13c,\n\tauthor = \t\"Lin Quan and John Heidemann and Yuri Pradkin\",\n\ttitle = \t\"Trinocular: Understanding Internet Reliability Through Adaptive Probing\",\n\tbooktitle = \t\"Proceedings of the \" # \" ACM SIGCOMM Conference \",\n\tyear = \t\t2013,\n\tsortdate = \t\t\"2013-08-01\", \n\tpages = \t\"255--266\",\n\tmonth = \taug,\n\taddress = \t\"Hong Kong, China\",\n\tpublisher = \t\"ACM\",\n\tjlocation = \t\"johnh: pafile\",\n\tkeywords = \t\"internet outage detection, hurricane sandy,\n bayesian inference\",\n copyrightholder = \"ACM\",\n\tcopyrightterms = \"\tPermission to make digital or hard \tcopies of portions of this work for personal or \tclassroom use is granted without fee provided that \tthe copies are not made or distributed for profit or \tcommercial advantage and that copies bear this \tnotice and the full citation on the first page in \tprint or the first screen in digital \tmedia. Copyrights for components of this work owned \tby others than ACM must be honored. Abstracting with \tcredit is permitted. \totherwise, to republish, to post on servers, or to \tredistribute to lists, requires prior specific \tpermission and/or a fee. Send written requests for \trepublication to ACM Publications, Copyright & \tPermissions at the address above or fax +1 (212) \t869-0481 or email permissions@acm.org.\" ,\n\turl =\t\t\"https://ant.isi.edu/%7ejohnh/PAPERS/Quan13c.html\",\n\tpdfurl =\t\"https://ant.isi.edu/%7ejohnh/PAPERS/Quan13c.pdf\",\n\tmyorganization =\t\"USC/Information Sciences Institute\",\n\tdoi = \t\"http://doi.acm.org/10.1145/2486001.2486017\",\n\tproject = \"ant, lacrend, duoi\",\n\tabstract = \"\nNatural and human factors cause Internet outages---from big events\nlike Hurricane Sandy in 2012 and the Egyptian Internet shutdown in\nJan. 2011 to small outages every day that go unpublicized. We\ndescribe \\emph{Trinocular}, an outage detection system that uses\nactive probing to understand reliability of edge networks. Trinocular\nis \\emph{principled}: deriving a simple model of the Internet that\ncaptures the information pertinent to outages, and populating that\nmodel through long-term data, and learning current network state\nthrough ICMP probes. It is \\emph{parsimonious}, using Bayesian\ninference to determine how many probes are needed. On average, each\nTrinocular instance sends fewer than 20 probes per hour to\neach /24 network block under study, increasing Internet ``background\nradiation'' by less than 0.7\\%. Trinocular is \nalso \\emph{predictable} and \\emph{precise}: we provide known precision in\noutage timing and duration. Probing in \\emph{rounds} of 11 minutes,\nwe detect 100\\% of outages one round or longer, and estimate outage\nduration within one-half round. Since we require little traffic, a\nsingle machine can track 3.4M /24 IPv4 blocks, all of the Internet\ncurrently suitable for analysis. We show that our approach \nis \\emph{significantly more accurate} than the best current methods, with\nabout one-third fewer false conclusions, and about 30\\% greater\ncoverage at constant accuracy. We validate our approach using\ncontrolled experiments, use Trinocular to analyze two days of Internet\noutages observed from three sites, and re-analyze three years of\nexisting data to develop trends for the Internet.\n\",\n}\n\n","author_short":["Quan, L.","Heidemann, J.","Pradkin, Y."],"bibbaseid":"quan-heidemann-pradkin-trinocularunderstandinginternetreliabilitythroughadaptiveprobing-2013","role":"author","urls":{"Paper":"https://ant.isi.edu/%7ejohnh/PAPERS/Quan13c.html"},"keyword":["internet outage detection","hurricane sandy","bayesian inference"],"metadata":{"authorlinks":{}}},"bibtype":"inproceedings","biburl":"https://bibbase.org/f/dHevizJoWEhWowz8q/johnh-2023-2.bib","dataSources":["YLyu3mj3xsBeoqiHK","fLZcDgNSoSuatv6aX","fxEParwu2ZfurScPY","7nuQvtHTqKrLmgu99"],"keywords":["internet outage detection","hurricane sandy","bayesian inference"],"search_terms":["trinocular","understanding","internet","reliability","through","adaptive","probing","quan","heidemann","pradkin"],"title":"Trinocular: Understanding Internet Reliability Through Adaptive Probing","year":2013}