{"id":"https://openalex.org/W2929462679","doi":"https://doi.org/10.1109/tr.2019.2901194","title":"Improving Failure Tolerance in Large-Scale Cloud Computing Systems","display_name":"Improving Failure Tolerance in Large-Scale Cloud Computing Systems","publication_year":2019,"publication_date":"2019-03-27","ids":{"openalex":"https://openalex.org/W2929462679","doi":"https://doi.org/10.1109/tr.2019.2901194","mag":"2929462679"},"language":"en","primary_location":{"id":"doi:10.1109/tr.2019.2901194","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tr.2019.2901194","pdf_url":null,"source":{"id":"https://openalex.org/S87725633","display_name":"IEEE Transactions on Reliability","issn_l":"0018-9529","issn":["0018-9529","1558-1721"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Reliability","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101809829","display_name":"Liang Luo","orcid":"https://orcid.org/0000-0003-4222-7986"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Luo","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0003-4222-7986","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045772822","display_name":"Sa Meng","orcid":"https://orcid.org/0000-0001-7573-7822"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sa Meng","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075710908","display_name":"Xiwei Qiu","orcid":"https://orcid.org/0000-0002-4657-2843"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiwei Qiu","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113616242","display_name":"Yuanshun Dai","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanshun Dai","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":5.8553,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.96251279,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"68","issue":"2","first_page":"620","last_page":"632"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9970999956130981,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11614","display_name":"Cloud Data Security Solutions","score":0.9930999875068665,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.897709846496582},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7774438858032227},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.696090042591095},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.5529645681381226},{"id":"https://openalex.org/keywords/cloud-testing","display_name":"Cloud testing","score":0.5326257348060608},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.4874734878540039},{"id":"https://openalex.org/keywords/reliability-engineering","display_name":"Reliability engineering","score":0.4776405394077301},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4535532593727112},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.4288962483406067},{"id":"https://openalex.org/keywords/utility-computing","display_name":"Utility computing","score":0.42340725660324097},{"id":"https://openalex.org/keywords/cloud-computing-security","display_name":"Cloud computing security","score":0.25616490840911865},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.15719833970069885},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1428120732307434}],"concepts":[{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.897709846496582},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7774438858032227},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.696090042591095},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.5529645681381226},{"id":"https://openalex.org/C120115606","wikidata":"https://www.wikidata.org/wiki/Q5135723","display_name":"Cloud testing","level":4,"score":0.5326257348060608},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.4874734878540039},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.4776405394077301},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4535532593727112},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.4288962483406067},{"id":"https://openalex.org/C85106507","wikidata":"https://www.wikidata.org/wiki/Q1188445","display_name":"Utility computing","level":4,"score":0.42340725660324097},{"id":"https://openalex.org/C184842701","wikidata":"https://www.wikidata.org/wiki/Q370563","display_name":"Cloud computing security","level":3,"score":0.25616490840911865},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.15719833970069885},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1428120732307434},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tr.2019.2901194","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tr.2019.2901194","pdf_url":null,"source":{"id":"https://openalex.org/S87725633","display_name":"IEEE Transactions on Reliability","issn_l":"0018-9529","issn":["0018-9529","1558-1721"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Reliability","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G960990459","display_name":null,"funder_award_id":"61602094","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W22021617","https://openalex.org/W94784130","https://openalex.org/W806409524","https://openalex.org/W943882595","https://openalex.org/W1487498606","https://openalex.org/W1556922398","https://openalex.org/W1759704466","https://openalex.org/W1859314164","https://openalex.org/W1891209413","https://openalex.org/W1967738308","https://openalex.org/W1971023268","https://openalex.org/W1977367431","https://openalex.org/W1994546692","https://openalex.org/W2004590586","https://openalex.org/W2006307164","https://openalex.org/W2010658059","https://openalex.org/W2015218975","https://openalex.org/W2019672983","https://openalex.org/W2024273674","https://openalex.org/W2026453648","https://openalex.org/W2029100038","https://openalex.org/W2031748519","https://openalex.org/W2045287414","https://openalex.org/W2045737546","https://openalex.org/W2047922079","https://openalex.org/W2048402506","https://openalex.org/W2066395229","https://openalex.org/W2109026747","https://openalex.org/W2114296561","https://openalex.org/W2118471598","https://openalex.org/W2118676041","https://openalex.org/W2119738171","https://openalex.org/W2121883877","https://openalex.org/W2126969025","https://openalex.org/W2131646073","https://openalex.org/W2139416291","https://openalex.org/W2159081109","https://openalex.org/W2218919311","https://openalex.org/W2277449158","https://openalex.org/W2324571613","https://openalex.org/W2326627146","https://openalex.org/W2388510220","https://openalex.org/W2418874772","https://openalex.org/W2483144311","https://openalex.org/W2523146812","https://openalex.org/W2576936530","https://openalex.org/W2600306771","https://openalex.org/W2726443204","https://openalex.org/W2751808730","https://openalex.org/W2770960012","https://openalex.org/W2792281126","https://openalex.org/W3021588640","https://openalex.org/W3103243695","https://openalex.org/W3103361075","https://openalex.org/W6651775265","https://openalex.org/W6662649148","https://openalex.org/W6680446466"],"related_works":["https://openalex.org/W2798934447","https://openalex.org/W2186962052","https://openalex.org/W2366587698","https://openalex.org/W3139579311","https://openalex.org/W4298004498","https://openalex.org/W2339937136","https://openalex.org/W4285160398","https://openalex.org/W2610826928","https://openalex.org/W2157044008","https://openalex.org/W2297738780"],"abstract_inverted_index":{"Large-scale":[0],"cloud":[1,59,84,95,101,177],"computing":[2,60,85,96,102,178],"systems":[3,32],"have":[4,63],"served":[5],"as":[6],"the":[7,22,26,123,137,150,165],"fundamental":[8],"supporting":[9],"platform":[10],"for":[11,21,89],"big":[12],"data,":[13],"Internet":[14],"of":[15,30,58,110,167,174],"Things,":[16],"and":[17,28,37,43,48,113,130],"artificial":[18],"intelligence":[19],"applications":[20],"past":[23],"decade.":[24],"With":[25],"scale":[27],"complexity":[29],"these":[31,73],"increasing":[33],"dramatically,":[34],"various":[35],"hardware":[36],"software":[38],"failures":[39],"will":[40],"inevitably":[41],"occur":[42],"may":[44,61],"not":[45],"be":[46,154],"detected":[47],"repaired":[49],"in":[50,93,170],"a":[51,78,99,107,160,175],"timely":[52],"manner.":[53],"Besides,":[54],"sophisticated":[55],"architectural":[56],"features":[57],"also":[62,158],"an":[64],"adverse":[65],"impact":[66],"on":[67,82],"system":[68,86],"reliability.":[69],"In":[70],"response":[71],"to":[72,121,145,163],"challenges,":[74],"this":[75,135],"paper":[76],"proposes":[77],"simulation-driven":[79],"framework":[80],"based":[81],"real":[83],"operation":[87,114],"logs":[88],"improving":[90,171],"failure":[91,172],"tolerance":[92,173],"large-scale":[94,176],"systems.":[97],"For":[98],"given":[100],"system,":[103],"we":[104],"first":[105],"conduct":[106],"systematic":[108],"analysis":[109],"its":[111],"structure":[112],"characteristics.":[115],"A":[116],"Markov-based":[117],"model":[118],"is":[119,143],"used":[120],"examine":[122],"system's":[124,151],"potential":[125],"failures,":[126],"assess":[127],"their":[128],"severities,":[129],"suggest":[131],"quick":[132],"recoveries.":[133],"During":[134],"process,":[136],"proposed":[138],"reliability-aware":[139],"resource":[140],"scheduling":[141],"algorithm":[142,169],"adopted":[144],"optimize":[146],"resources":[147],"so":[148],"that":[149],"reliability":[152],"can":[153],"improved":[155],"cost-effectively.":[156],"We":[157],"report":[159],"case":[161],"study":[162],"demonstrate":[164],"application":[166],"our":[168],"system.":[179]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
