{"id":"https://openalex.org/W4313563618","doi":"https://doi.org/10.1145/3551349.3559503","title":"A fault injection platform for learning AIOps models","display_name":"A fault injection platform for learning AIOps models","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4313563618","doi":"https://doi.org/10.1145/3551349.3559503"},"language":"en","primary_location":{"id":"doi:10.1145/3551349.3559503","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3551349.3559503","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 37th IEEE/ACM International Conference on Automated Software Engineering","raw_type":"proceedings-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/A5062165845","display_name":"Frank Bagehorn","orcid":null},"institutions":[{"id":"https://openalex.org/I4210126328","display_name":"IBM Research - Zurich","ror":"https://ror.org/02js37d36","country_code":"CH","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126328"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Frank Bagehorn","raw_affiliation_strings":["IBM Research, Switzerland"],"affiliations":[{"raw_affiliation_string":"IBM Research, Switzerland","institution_ids":["https://openalex.org/I4210126328"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033405256","display_name":"Jesus Rios","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jesus Rios","raw_affiliation_strings":["IBM Research, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016778130","display_name":"Saurabh Jha","orcid":"https://orcid.org/0000-0003-0926-0776"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Saurabh Jha","raw_affiliation_strings":["IBM Research, United States of America"],"affiliations":[{"raw_affiliation_string":"IBM Research, United States of America","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051305740","display_name":"Robert Filepp","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Robert Filepp","raw_affiliation_strings":["IBM Research, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037060213","display_name":"Larisa Shwartz","orcid":"https://orcid.org/0000-0001-5878-0765"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Larisa Shwartz","raw_affiliation_strings":["IBM Research, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109000913","display_name":"Naoki Abe","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Naoki Abe","raw_affiliation_strings":["IBM Research, United States of America"],"affiliations":[{"raw_affiliation_string":"IBM Research, United States of America","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100355603","display_name":"Xi Yang","orcid":"https://orcid.org/0000-0003-1445-1745"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xi Yang","raw_affiliation_strings":["IBM Research, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5062165845"],"corresponding_institution_ids":["https://openalex.org/I4210126328"],"apc_list":null,"apc_paid":null,"fwci":0.9664,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.77206797,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.9997000098228455,"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/T12127","display_name":"Software System Performance and Reliability","score":0.9997000098228455,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9787999987602234,"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":0.9767000079154968,"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/computer-science","display_name":"Computer science","score":0.7326872944831848},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.6857869029045105},{"id":"https://openalex.org/keywords/fault-injection","display_name":"Fault injection","score":0.6734033226966858},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.652916669845581},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5875698924064636},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4176165759563446},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40957799553871155},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3745657205581665},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.3445153832435608},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3356704115867615},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.3055263161659241},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.13126343488693237}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7326872944831848},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.6857869029045105},{"id":"https://openalex.org/C2775928411","wikidata":"https://www.wikidata.org/wiki/Q2041312","display_name":"Fault injection","level":3,"score":0.6734033226966858},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.652916669845581},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5875698924064636},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4176165759563446},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40957799553871155},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3745657205581665},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3445153832435608},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3356704115867615},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3055263161659241},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.13126343488693237},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3551349.3559503","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3551349.3559503","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 37th IEEE/ACM International Conference on Automated Software Engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.6399999856948853,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W95608104","https://openalex.org/W2089745089","https://openalex.org/W2966971704","https://openalex.org/W3168937343"],"related_works":["https://openalex.org/W4244478748","https://openalex.org/W4223488648","https://openalex.org/W4205786897","https://openalex.org/W2134969820","https://openalex.org/W2251605416","https://openalex.org/W3150465815","https://openalex.org/W1997222214","https://openalex.org/W2070395303","https://openalex.org/W3020139090","https://openalex.org/W2100170515"],"abstract_inverted_index":{"In":[0,39,154],"today\u2019s":[1],"IT":[2,65],"environment":[3,189],"with":[4,108],"a":[5,24,99,112,177,183,187],"growing":[6],"number":[7],"of":[8,13,18,55,69,75,179],"costly":[9],"outages,":[10],"increasing":[11],"complexity":[12],"the":[14,53,73,77,87,91,135,142,158,191],"systems,":[15],"and":[16,32,51,84,118,121,144,198],"availability":[17],"massive":[19],"operational":[20],"data,":[21],"there":[22],"is":[23,173,196],"strengthening":[25],"demand":[26],"to":[27,49,62,79,85,175],"effectively":[28],"leverage":[29],"Artificial":[30],"Intelligence":[31],"Machine":[33],"Learning":[34],"(AI/ML)":[35],"towards":[36],"enhanced":[37],"resiliency.":[38],"this":[40],"paper,":[41],"we":[42,97,156],"present":[43],"an":[44],"automatic":[45],"fault":[46,82,100,106,138,210],"injection":[47,101,107],"platform":[48,71,148],"enable":[50],"optimize":[52,86],"generation":[54,89],"data":[56,88,109],"needed":[57],"for":[58,90,128,203],"building":[59],"AI/ML":[60],"models":[61],"support":[63],"modern":[64],"operations.":[66],"The":[67,147],"merits":[68],"our":[70,166,171],"include":[72],"ease":[74],"use,":[76],"possibility":[78],"orchestrate":[80],"complex":[81],"scenarios":[83],"modeling":[92],"task":[93],"at":[94,141],"hand.":[95],"Specifically,":[96],"designed":[98],"service":[102],"that":[103],"(i)":[104],"combines":[105],"collection":[110],"in":[111,165,182,186,205],"unified":[113],"framework,":[114],"(ii)":[115],"supports":[116],"hybrid":[117],"multi-cloud":[119],"environments,":[120],"(iii)":[122],"does":[123],"not":[124],"require":[125],"programming":[126],"skills":[127],"its":[129],"use.":[130],"Our":[131],"current":[132],"implementation":[133],"covers":[134],"most":[136],"common":[137],"types":[139],"both":[140],"application":[143,185],"infrastructure":[145],"levels.":[146],"also":[149],"includes":[150],"some":[151],"AI":[152],"capabilities.":[153],"particular,":[155],"demonstrate":[157],"interventional":[159],"causal":[160],"learning":[161],"capability":[162],"currently":[163],"available":[164],"platform.":[167],"We":[168],"show":[169],"how":[170],"system":[172],"able":[174],"learn":[176],"model":[178],"error":[180],"propagation":[181],"micro-service":[184],"cloud":[188],"(when":[190],"communication":[192],"graph":[193],"among":[194],"micro-services":[195],"unknown":[197],"only":[199],"logs":[200],"are":[201],"available)":[202],"use":[204],"subsequent":[206],"applications":[207],"such":[208],"as":[209],"localization.":[211]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}