{"id":"https://openalex.org/W3041766799","doi":"https://doi.org/10.1109/tnsm.2021.3092939","title":"Self-Healing Dilemmas in Distributed Systems: Fault Correction vs. Fault Tolerance","display_name":"Self-Healing Dilemmas in Distributed Systems: Fault Correction vs. Fault Tolerance","publication_year":2021,"publication_date":"2021-06-28","ids":{"openalex":"https://openalex.org/W3041766799","doi":"https://doi.org/10.1109/tnsm.2021.3092939","mag":"3041766799"},"language":"en","primary_location":{"id":"doi:10.1109/tnsm.2021.3092939","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnsm.2021.3092939","pdf_url":null,"source":{"id":"https://openalex.org/S173527311","display_name":"IEEE Transactions on Network and Service Management","issn_l":"1932-4537","issn":["1932-4537","2373-7379"],"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 Network and Service Management","raw_type":"journal-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2007.05261","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051372377","display_name":"Jovan Nikoli\u0107","orcid":null},"institutions":[{"id":"https://openalex.org/I4210100430","display_name":"Google (Switzerland)","ror":"https://ror.org/014f9c269","country_code":"CH","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210100430","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["CH","US"],"is_corresponding":true,"raw_author_name":"Jovan Nikolic","raw_affiliation_strings":["Google, Zurich, Z\u00fcrich, Switzerland","Google,,,,,"],"affiliations":[{"raw_affiliation_string":"Google, Zurich, Z\u00fcrich, Switzerland","institution_ids":["https://openalex.org/I4210100430"]},{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055801301","display_name":"Nursultan Jubatyrov","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Nursultan Jubatyrov","raw_affiliation_strings":["Facebook, London, U.K","Facebook"],"affiliations":[{"raw_affiliation_string":"Facebook, London, U.K","institution_ids":[]},{"raw_affiliation_string":"Facebook","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035070413","display_name":"Evangelos Pournaras","orcid":"https://orcid.org/0000-0003-3900-2057"},"institutions":[{"id":"https://openalex.org/I130828816","display_name":"University of Leeds","ror":"https://ror.org/024mrxd33","country_code":"GB","type":"education","lineage":["https://openalex.org/I130828816"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Evangelos Pournaras","raw_affiliation_strings":["School of Computing, University of Leeds, Leeds, U.K","University of Leeds"],"affiliations":[{"raw_affiliation_string":"School of Computing, University of Leeds, Leeds, U.K","institution_ids":["https://openalex.org/I130828816"]},{"raw_affiliation_string":"University of Leeds","institution_ids":["https://openalex.org/I130828816"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5051372377"],"corresponding_institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I4210100430"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.01175911,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"18","issue":"3","first_page":"2728","last_page":"2741"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9994999766349792,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9976999759674072,"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/T12127","display_name":"Software System Performance and Reliability","score":0.9969000220298767,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6976155638694763},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.6873560547828674},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.6390420794487},{"id":"https://openalex.org/keywords/fault","display_name":"Fault (geology)","score":0.5519409775733948},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.5332388877868652},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4668971002101898},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.4542470872402191},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.4257761538028717},{"id":"https://openalex.org/keywords/reliability-engineering","display_name":"Reliability engineering","score":0.385578453540802},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.3639700412750244},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.20027664303779602},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.19416853785514832},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.11071246862411499}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6976155638694763},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.6873560547828674},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.6390420794487},{"id":"https://openalex.org/C175551986","wikidata":"https://www.wikidata.org/wiki/Q47089","display_name":"Fault (geology)","level":2,"score":0.5519409775733948},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.5332388877868652},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4668971002101898},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.4542470872402191},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.4257761538028717},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.385578453540802},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3639700412750244},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.20027664303779602},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.19416853785514832},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.11071246862411499},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C165205528","wikidata":"https://www.wikidata.org/wiki/Q83371","display_name":"Seismology","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/tnsm.2021.3092939","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnsm.2021.3092939","pdf_url":null,"source":{"id":"https://openalex.org/S173527311","display_name":"IEEE Transactions on Network and Service Management","issn_l":"1932-4537","issn":["1932-4537","2373-7379"],"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 Network and Service Management","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2007.05261","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2007.05261","pdf_url":"https://arxiv.org/pdf/2007.05261","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:eprints.whiterose.ac.uk:179226","is_oa":true,"landing_page_url":null,"pdf_url":"https://eprints.whiterose.ac.uk/179226/1/DIAS.pdf","source":{"id":"https://openalex.org/S4306400854","display_name":"White Rose Research Online (University of Leeds, The University of Sheffield, University of York)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2800616092","host_organization_name":"White Rose University Consortium","host_organization_lineage":["https://openalex.org/I2800616092"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"},{"id":"mag:3041766799","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2007.05261.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2007.05261","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2007.05261","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2007.05261","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2007.05261","pdf_url":"https://arxiv.org/pdf/2007.05261","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W914875445","https://openalex.org/W1503941011","https://openalex.org/W1530248740","https://openalex.org/W1547655765","https://openalex.org/W1609618519","https://openalex.org/W1775201033","https://openalex.org/W1813794978","https://openalex.org/W1968670446","https://openalex.org/W1977159600","https://openalex.org/W1983426708","https://openalex.org/W1991407706","https://openalex.org/W2035362408","https://openalex.org/W2046415899","https://openalex.org/W2050606644","https://openalex.org/W2071099085","https://openalex.org/W2077240273","https://openalex.org/W2087317232","https://openalex.org/W2115050196","https://openalex.org/W2123845384","https://openalex.org/W2126147068","https://openalex.org/W2127467730","https://openalex.org/W2131629153","https://openalex.org/W2132865505","https://openalex.org/W2138830906","https://openalex.org/W2139547970","https://openalex.org/W2139587243","https://openalex.org/W2226714091","https://openalex.org/W2285129881","https://openalex.org/W2462445791","https://openalex.org/W2509785985","https://openalex.org/W2511421375","https://openalex.org/W2515452363","https://openalex.org/W2555979770","https://openalex.org/W2603808788","https://openalex.org/W2611876927","https://openalex.org/W2612337273","https://openalex.org/W2654909105","https://openalex.org/W2748994727","https://openalex.org/W2756635781","https://openalex.org/W2762989164","https://openalex.org/W2790957846","https://openalex.org/W2795237059","https://openalex.org/W2797816609","https://openalex.org/W2887576654","https://openalex.org/W2903799441","https://openalex.org/W2910001620","https://openalex.org/W2912391240","https://openalex.org/W2964740386","https://openalex.org/W2966264890","https://openalex.org/W2998286180","https://openalex.org/W3007177528","https://openalex.org/W3043631994","https://openalex.org/W4232338303","https://openalex.org/W4244585506","https://openalex.org/W4245147131","https://openalex.org/W6632572979"],"related_works":["https://openalex.org/W3173203101","https://openalex.org/W2148398645","https://openalex.org/W2170457584","https://openalex.org/W2509865514","https://openalex.org/W2966774415","https://openalex.org/W2137754267","https://openalex.org/W103794388","https://openalex.org/W2404265005","https://openalex.org/W48771824","https://openalex.org/W62186976","https://openalex.org/W3104793771","https://openalex.org/W1995461270","https://openalex.org/W156133708","https://openalex.org/W235511181","https://openalex.org/W2794330152","https://openalex.org/W2156883646","https://openalex.org/W1981764178","https://openalex.org/W2897452464","https://openalex.org/W139699131","https://openalex.org/W1016026621"],"abstract_inverted_index":{"Large-scale":[0],"decentralized":[1,160,190,236],"systems":[2,83,161],"of":[3,34,68,102,109,126,146,158,177,192,199,213,223,235,255],"autonomous":[4],"agents":[5],"interacting":[6],"via":[7],"asynchronous":[8],"communication":[9],"often":[10],"experience":[11],"the":[12,32,66,100,107,143,153,163,210,224,253,273],"following":[13],"self-healing":[14,90,157,267],"dilemma:":[15],"fault":[16,40,55,73,127,147,150,179,181,184,226],"detection":[17,185],"inherits":[18],"network":[19,191],"uncertainties":[20],"making":[21],"a":[22,28,35,59,93,121,188,204,231,246],"remote":[23],"faulty":[24,71],"process":[25,37],"indistinguishable":[26],"from":[27,245],"slow":[29,36],"process.":[30],"In":[31],"case":[33,67],"without":[38,76],"fault,":[39],"correction":[41,148],"is":[42,58,92,170,228,276],"undesirable":[43,144],"as":[44,152,279],"it":[45],"can":[46,81,218],"trigger":[47],"new":[48,262],"faults":[49,80],"that":[50,57,172],"could":[51],"be":[52],"prevented":[53],"with":[54],"tolerance":[56,74,151],"more":[60],"proactive":[61],"system":[62,130],"maintenance.":[63],"But":[64],"in":[65,111,187,203,230],"an":[69,269],"actual":[70],"process,":[72],"alone":[75],"eventually":[77],"correcting":[78],"persistent":[79],"make":[82],"underperforming.":[84],"Measuring,":[85],"understanding":[86],"and":[87,96,115,123,138,149,183,237,260,284],"resolving":[88],"such":[89],"dilemmas":[91],"timely":[94],"challenge":[95],"critical":[97],"requirement":[98],"given":[99],"rise":[101],"distributed":[103],"ledgers,":[104],"edge":[105],"computing,":[106],"Internet":[108],"Things":[110],"several":[112],"energy,":[113],"transport":[114],"health":[116,211],"applications.":[117],"This":[118],"paper":[119],"contributes":[120],"novel":[122],"general-purpose":[124],"modeling":[125],"scenarios":[128,227],"during":[129],"runtime.":[131],"They":[132],"are":[133],"used":[134],"to":[135,155,265],"accurately":[136],"measure":[137],"predict":[139],"inconsistencies":[140,200,256],"generated":[141],"by":[142,281],"outcomes":[145],"means":[154],"improve":[156],"large-scale":[159],"at":[162,257,268],"design":[164,258],"phase.":[165],"A":[166],"rigorous":[167],"experimental":[168,175],"methodology":[169],"designed":[171],"evaluates":[173],"696":[174],"settings":[176],"different":[178],"scales,":[180],"profiles":[182],"thresholds":[186],"prototyped":[189],"3000":[193],"nodes.":[194],"Almost":[195],"9":[196],"million":[197],"measurements":[198],"were":[201],"collected":[202],"network,":[205],"where":[206],"each":[207],"node":[208],"monitors":[209],"status":[212],"another":[214],"node,":[215],"while":[216],"both":[217],"defect.":[219],"The":[220],"prediction":[221],"performance":[222],"modeled":[225],"validated":[229],"challenging":[232],"application":[233],"scenario":[234],"dynamic":[238],"in-network":[239],"data":[240,244],"aggregation":[241,274],"using":[242],"real-world":[243],"Smart":[247],"Grid":[248],"pilot":[249],"project.":[250],"Findings":[251],"confirm":[252],"origin":[254],"phase":[259],"provide":[261],"insights":[263],"how":[264],"tune":[266],"early":[270],"stage.":[271],"Strikingly,":[272],"accuracy":[275],"well":[277],"predicted":[278],"shown":[280],"high":[282],"correlations":[283],"low":[285],"root":[286],"mean":[287],"square":[288],"errors.":[289]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-21T08:13:44.787528","created_date":"2022-07-26T00:00:00"}