{"id":377,"date":"2013-05-27T15:51:15","date_gmt":"2013-05-27T22:51:15","guid":{"rendered":"http:\/\/ant.isi.edu\/blog\/?p=377"},"modified":"2020-10-19T10:23:35","modified_gmt":"2020-10-19T17:23:35","slug":"377","status":"publish","type":"post","link":"https:\/\/ant.isi.edu\/blog\/?p=377","title":{"rendered":"new conference paper “Trinocular: Understanding Internet Reliability Through Adaptive Probing” in SIGCOMM 2013"},"content":{"rendered":"

The paper “Trinocular: Understanding Internet Reliability Through Adaptive Probing” was accepted by SIGCOMM’13 in Hong Kong, China (available at\u00a0http:\/\/www.isi.edu\/~johnh\/PAPERS\/Quan13c<\/a>\u00a0with cite and pdf, or direct pdf<\/a>).<\/p>\n

\"100%<\/a>
100% detection of outages one round or longer (figure 3 from the paper)<\/figcaption><\/figure>\n

From the abstract:<\/p>\n

Natural and human factors cause Internet outages—from big events\u00a0like Hurricane Sandy in 2012 and the Egyptian Internet shutdown in\u00a0Jan. 2011 to small outages every day that go unpublicized. We\u00a0describe Trinocular, an outage detection system that uses active\u00a0probing to understand reliability of edge networks. Trinocular is\u00a0principled: deriving a simple model of the Internet that captures the\u00a0information pertinent to outages, and populating that model through\u00a0long-term data, and learning current network state through ICMP\u00a0probes. It is parsimonious, using Bayesian inference to determine how\u00a0many probes are needed. On average, each Trinocular instance sends\u00a0fewer than 20 probes per hour to each \/24 network block under study,\u00a0increasing Internet “background radiation” by less than 0.7%.\u00a0Trinocular is also predictable and precise: we provide known precision\u00a0in outage timing and duration. Probing in rounds of 11 minutes, we\u00a0detect 100% of outages one round or longer, and estimate outage\u00a0duration within one-half round. Since we require little traffic, a\u00a0single machine can track 3.4M \/24 IPv4 blocks, all of the Internet\u00a0currently suitable for analysis. We show that our approach is\u00a0significantly more accurate than the best current methods, with about\u00a0one-third fewer false conclusions, and about 30% greater coverage at\u00a0constant accuracy. We validate our approach using controlled\u00a0experiments, use Trinocular to analyze two days of Internet outages\u00a0observed from three sites, and re-analyze three years of existing data\u00a0to develop trends for the Internet.<\/p><\/blockquote>\n

Citation: Lin Quan, John Heidemann and Yuri Pradkin. Trinocular:\u00a0Understanding Internet Reliability Through Adaptive Probing. In\u00a0Proceedings of the ACM SIGCOMM Conference<\/em>. Hong Kong, China, ACM. August, 2013. <http:\/\/www.isi.edu\/~johnh\/PAPERS\/Quan13c<\/a>>.<\/p>\n

Datasets (listed here)<\/a> used in generating this paper are available or will be available before the conference presentation.<\/p>\n","protected":false},"excerpt":{"rendered":"

The paper “Trinocular: Understanding Internet Reliability Through Adaptive Probing” was accepted by SIGCOMM’13 in Hong Kong, China (available at\u00a0http:\/\/www.isi.edu\/~johnh\/PAPERS\/Quan13c\u00a0with cite and pdf, or direct pdf). From the abstract: Natural and human factors cause Internet outages—from big events\u00a0like Hurricane Sandy in 2012 and the Egyptian Internet shutdown in\u00a0Jan. 2011 to small outages every day that go […]<\/p>\n","protected":false},"author":36,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[284,282],"tags":[34,24,58,8,22,10,44,5,41,45,28,57],"class_list":["post-377","post","type-post","status-publish","format-standard","hentry","category-papers-publications","category-publications","tag-algorithms","tag-conference","tag-isi","tag-lander","tag-measurement-systems","tag-network-datasets","tag-outage-detection","tag-papers","tag-predict","tag-reliability","tag-sigcomm","tag-usc"],"_links":{"self":[{"href":"https:\/\/ant.isi.edu\/blog\/index.php?rest_route=\/wp\/v2\/posts\/377","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/ant.isi.edu\/blog\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/ant.isi.edu\/blog\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/ant.isi.edu\/blog\/index.php?rest_route=\/wp\/v2\/users\/36"}],"replies":[{"embeddable":true,"href":"https:\/\/ant.isi.edu\/blog\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=377"}],"version-history":[{"count":9,"href":"https:\/\/ant.isi.edu\/blog\/index.php?rest_route=\/wp\/v2\/posts\/377\/revisions"}],"predecessor-version":[{"id":381,"href":"https:\/\/ant.isi.edu\/blog\/index.php?rest_route=\/wp\/v2\/posts\/377\/revisions\/381"}],"wp:attachment":[{"href":"https:\/\/ant.isi.edu\/blog\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=377"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/ant.isi.edu\/blog\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=377"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/ant.isi.edu\/blog\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=377"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}