{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T13:57:26Z","timestamp":1774965446501,"version":"3.50.1"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"CAREER","award":["CNS-1350766"],"award-info":[{"award-number":["CNS-1350766"]}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1320226"],"award-info":[{"award-number":["1320226"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2016]]},"DOI":"10.1109\/tpds.2016.2571281","type":"journal-article","created":{"date-parts":[[2016,5,22]],"date-time":"2016-05-22T00:51:32Z","timestamp":1463878292000},"page":"1-1","source":"Crossref","is-referenced-by-count":20,"title":["Elastic Reliability Optimization Through Peer-to-Peer Checkpointing in Cloud Computing"],"prefix":"10.1109","author":[{"given":"Juzi","family":"Zhao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Xiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tian","family":"Lan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"H. Howie","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Suresh","family":"Subramaniam","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TR.2012.2220711"},{"key":"ref38","first-page":"257","author":"fu","year":"0","journal-title":"Proc 2nd Int Conf Availability Rel Security"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-011-0578-4"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/SOCA.2013.44"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/2536430.2536432"},{"key":"ref30","doi-asserted-by":"crossref","DOI":"10.1145\/2745844.2745873","article-title":"Reducing latency via redundant requests: Exact analysis","author":"gardner","year":"2015","journal-title":"SIGMETRICS &#x2019;15"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICIS.2013.6607860"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/HPCS.2010.5547140"},{"key":"ref35","article-title":"Energy-aware adaptive checkpointing in embedded real-time systems","author":"chakrabarty","year":"0","journal-title":"Proc Des Autom Test Eur Conf Exhib"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/24.974127"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CLOUD.2010.35"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICWS.2011.77"},{"key":"ref11","article-title":"Flyways to De-Congest Data Center Networks","author":"padhye","year":"0","journal-title":"Proc of 8th ACM Workshop on Hot Topics in Networks"},{"key":"ref12","author":"boyd","year":"2005","journal-title":"Convex optimization"},{"key":"ref13","article-title":"When The Power Goes Out at Google","author":"miller","year":"2010"},{"key":"ref14","article-title":"Amazon cloud outage was triggered by configuration error","author":"thibodeau","year":"2011"},{"key":"ref15","first-page":"8","article-title":"Failure recovery: When the cure is worse than the disease","author":"guo","year":"0","journal-title":"Proc Workshop Hot Topics in Operating Systems"},{"key":"ref16","first-page":"199","article-title":"Edge-coloring and f-coloring for various classes of graphs","author":"zhou","year":"0","journal-title":"Proc 5th Int Symp AlgorithmsComput"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/BFb0015243"},{"key":"ref18","first-page":"39","article-title":"Portland: A scalable fault-tolerant layer 2 data center network fabric","author":"mysore","year":"0","journal-title":"Proc ACM SIGCOMM Conf Data Commun"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2007.90"},{"key":"ref28","article-title":"Colocation demand response: Why do i turn off my servers?","author":"ren","year":"0"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/1341312.1341341"},{"key":"ref27","first-page":"142","article-title":"Yank: Enabling green data centers to pull the plug","author":"singh","year":"0","journal-title":"Proc 10th USENIX Symp Netw Syst Des Implementation"},{"key":"ref3","article-title":"Protecting mission-critical workloads with VMware fault tolerance","year":"0"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICPADS.2007.4447844"},{"key":"ref29","article-title":"Zoolander: Efficiently meeting very strict, low-latency SLOs","author":"stewart","year":"0"},{"key":"ref5","first-page":"4","article-title":"Parallax: Managing storage for a million machines","author":"warfield","year":"0","journal-title":"Proc Workshop Hot Topics in Operating Systems"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICPADS.2010.125"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/NOMS.2010.5488493"},{"key":"ref2","article-title":"Software as a service perceptions survey","year":"2007"},{"key":"ref9","first-page":"1","article-title":"An optimal checkpoint\/restart model for a large scale high performance computing system","author":"liu","year":"0","journal-title":"Proc Int Symp Parallel Distrib Process"},{"key":"ref1","article-title":"We promise our EC2 cloud will only crash once a week","year":"2008"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1145\/1773394.1773400","article-title":"Towards characterizing cloud backend workloads: Insights from Google compute clusters","volume":"37","author":"mishra","year":"2010","journal-title":"SIGMETRICS Perform Eval Rev"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/800221.806726"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/1592681.1592692"},{"key":"ref42","article-title":"An efficient distributed burst buffer for Linux","author":"wang","year":"0","journal-title":"Proc Conf Lustre User Group"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/PDGC.2014.7030723"},{"key":"ref41","first-page":"284","author":"prabhat","year":"2014","journal-title":"High Performance Parallel I\/O"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/BF01940882"},{"key":"ref44","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1109\/JSACOCN.2008.030607","article-title":"Elastic service availability: Utility framework optimal provisioning","volume":"26","author":"xu","year":"2008","journal-title":"IEEE J Sel Areas Commun"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/DSN.2014.101"},{"key":"ref43","year":"0"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCC.2014.2369421"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/71\/4359390\/07475901.pdf?arnumber=7475901","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,8]],"date-time":"2022-04-08T18:48:37Z","timestamp":1649443717000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7475901\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/tpds.2016.2571281","relation":{},"ISSN":["1045-9219"],"issn-type":[{"value":"1045-9219","type":"print"}],"subject":[],"published":{"date-parts":[[2016]]}}}