{"id":"https://openalex.org/W4396709412","doi":"https://doi.org/10.1145/3629526.3645047","title":"InstantOps: A Joint Approach to System Failure Prediction and Root Cause Identification in Microserivces Cloud-Native Applications","display_name":"InstantOps: A Joint Approach to System Failure Prediction and Root Cause Identification in Microserivces Cloud-Native Applications","publication_year":2024,"publication_date":"2024-05-06","ids":{"openalex":"https://openalex.org/W4396709412","doi":"https://doi.org/10.1145/3629526.3645047"},"language":"en","primary_location":{"id":"doi:10.1145/3629526.3645047","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3629526.3645047","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3629526.3645047","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th ACM/SPEC International Conference on Performance Engineering","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3629526.3645047","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013718133","display_name":"Raphael Rouf","orcid":"https://orcid.org/0009-0004-8849-4873"},"institutions":[{"id":"https://openalex.org/I192455969","display_name":"York University","ror":"https://ror.org/05fq50484","country_code":"CA","type":"education","lineage":["https://openalex.org/I192455969"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Raphael Rouf","raw_affiliation_strings":["York University, Toronto, ON, Canada"],"raw_orcid":"https://orcid.org/0009-0004-8849-4873","affiliations":[{"raw_affiliation_string":"York University, Toronto, ON, Canada","institution_ids":["https://openalex.org/I192455969"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036112588","display_name":"Mohammadreza Rasolroveicy","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113654","display_name":"IBM (Canada)","ror":"https://ror.org/025sxka56","country_code":"CA","type":"company","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210113654"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Mohammadreza Rasolroveicy","raw_affiliation_strings":["IBM Canada Lab, Markham, ON, Canada"],"raw_orcid":"https://orcid.org/0000-0002-7231-7889","affiliations":[{"raw_affiliation_string":"IBM Canada Lab, Markham, ON, Canada","institution_ids":["https://openalex.org/I4210113654"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051000791","display_name":"Marin Litoiu","orcid":"https://orcid.org/0000-0003-0383-920X"},"institutions":[{"id":"https://openalex.org/I192455969","display_name":"York University","ror":"https://ror.org/05fq50484","country_code":"CA","type":"education","lineage":["https://openalex.org/I192455969"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Marin Litoiu","raw_affiliation_strings":["York University, Toronto, ON, Canada"],"raw_orcid":"https://orcid.org/0000-0003-0383-920X","affiliations":[{"raw_affiliation_string":"York University, Toronto, ON, Canada","institution_ids":["https://openalex.org/I192455969"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078509468","display_name":"Seema Nagar","orcid":"https://orcid.org/0009-0000-5076-7734"},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Seema Nagar","raw_affiliation_strings":["IBM Research, Banglore, India"],"raw_orcid":"https://orcid.org/0009-0000-5076-7734","affiliations":[{"raw_affiliation_string":"IBM Research, Banglore, India","institution_ids":["https://openalex.org/I4210103279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014553424","display_name":"Prateeti Mohapatra","orcid":"https://orcid.org/0009-0005-1418-0414"},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Prateeti Mohapatra","raw_affiliation_strings":["IBM Research, Banglore, India"],"raw_orcid":"https://orcid.org/0009-0005-1418-0414","affiliations":[{"raw_affiliation_string":"IBM Research, Banglore, India","institution_ids":["https://openalex.org/I4210103279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085636385","display_name":"Pranjal Gupta","orcid":"https://orcid.org/0000-0003-2172-1889"},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Pranjal Gupta","raw_affiliation_strings":["IBM Research, Banglore, India"],"raw_orcid":"https://orcid.org/0000-0003-2172-1889","affiliations":[{"raw_affiliation_string":"IBM Research, Banglore, India","institution_ids":["https://openalex.org/I4210103279"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067753511","display_name":"Ian Watts","orcid":"https://orcid.org/0009-0008-2126-9232"},"institutions":[{"id":"https://openalex.org/I4210113654","display_name":"IBM (Canada)","ror":"https://ror.org/025sxka56","country_code":"CA","type":"company","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210113654"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ian Watts","raw_affiliation_strings":["IBM Canada Lab, Markham, ON, Canada"],"raw_orcid":"https://orcid.org/0009-0008-2126-9232","affiliations":[{"raw_affiliation_string":"IBM Canada Lab, Markham, ON, Canada","institution_ids":["https://openalex.org/I4210113654"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"119","last_page":"129"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.9998999834060669,"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":0.9998999834060669,"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/T10400","display_name":"Network Security and Intrusion Detection","score":0.947700023651123,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9154999852180481,"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":0.804050087928772},{"id":"https://openalex.org/keywords/root-cause","display_name":"Root cause","score":0.6362349987030029},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.6346662640571594},{"id":"https://openalex.org/keywords/observability","display_name":"Observability","score":0.6279590129852295},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5414928793907166},{"id":"https://openalex.org/keywords/root-cause-analysis","display_name":"Root cause analysis","score":0.5283570885658264},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.44814369082450867},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.4428645074367523},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.428838312625885},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38995301723480225},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3813815712928772},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.2385772168636322},{"id":"https://openalex.org/keywords/reliability-engineering","display_name":"Reliability engineering","score":0.1712796986103058},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12071183323860168}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.804050087928772},{"id":"https://openalex.org/C84945661","wikidata":"https://www.wikidata.org/wiki/Q7366567","display_name":"Root cause","level":2,"score":0.6362349987030029},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.6346662640571594},{"id":"https://openalex.org/C36299963","wikidata":"https://www.wikidata.org/wiki/Q1369844","display_name":"Observability","level":2,"score":0.6279590129852295},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5414928793907166},{"id":"https://openalex.org/C130963320","wikidata":"https://www.wikidata.org/wiki/Q1401207","display_name":"Root cause analysis","level":2,"score":0.5283570885658264},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.44814369082450867},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4428645074367523},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.428838312625885},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38995301723480225},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3813815712928772},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2385772168636322},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.1712796986103058},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12071183323860168},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3629526.3645047","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3629526.3645047","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3629526.3645047","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th ACM/SPEC International Conference on Performance Engineering","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3629526.3645047","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3629526.3645047","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3629526.3645047","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th ACM/SPEC International Conference on Performance Engineering","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4396709412.pdf"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W1418477825","https://openalex.org/W1922735843","https://openalex.org/W2026453187","https://openalex.org/W2288664677","https://openalex.org/W2734941459","https://openalex.org/W2754665629","https://openalex.org/W2821372324","https://openalex.org/W2887408574","https://openalex.org/W2900100055","https://openalex.org/W2903799441","https://openalex.org/W2959716986","https://openalex.org/W2965838158","https://openalex.org/W2966971704","https://openalex.org/W3008645556","https://openalex.org/W3022004659","https://openalex.org/W3093789645","https://openalex.org/W3100178186","https://openalex.org/W3115649824","https://openalex.org/W3137919061","https://openalex.org/W3155331679","https://openalex.org/W3161850060","https://openalex.org/W3198081460","https://openalex.org/W3216549012","https://openalex.org/W4206201823","https://openalex.org/W4226214891","https://openalex.org/W4308643313","https://openalex.org/W4382203537","https://openalex.org/W4383898422","https://openalex.org/W4385568016"],"related_works":["https://openalex.org/W2030594396","https://openalex.org/W2754538212","https://openalex.org/W2490884653","https://openalex.org/W4200610016","https://openalex.org/W2183996497","https://openalex.org/W129587375","https://openalex.org/W2110363179","https://openalex.org/W2056250485","https://openalex.org/W2535098331","https://openalex.org/W4255366506"],"abstract_inverted_index":{"As":[0],"microservice":[1],"and":[2,16,33,47,61,94,114,166,185,203],"cloud":[3],"computing":[4],"operations":[5],"increasingly":[6],"adopt":[7],"automation,":[8],"the":[9,68,72,131,141,150,155,175,189,195,209,212],"importance":[10],"of":[11,41,133,143,154,197,211],"models":[12],"for":[13],"fostering":[14],"resilient":[15],"efficient":[17],"adaptive":[18],"architectures":[19],"becomes":[20],"paramount.":[21],"This":[22],"paper":[23],"presents":[24],"InstantOps,":[25,144],"a":[26,38,80,108,117],"novel":[27],"approach":[28],"to":[29,57,66,97,106,125],"system":[30,99,176],"failure":[31],"prediction":[32],"root":[34,134,198],"cause":[35,199],"analysis":[36,200],"leveraging":[37],"three-fold":[39],"modality":[40],"IT":[42],"observability":[43],"data:":[44],"logs,":[45,85],"metrics,":[46],"traces.":[48],"The":[49,102,169],"proposed":[50],"methodology":[51],"integrates":[52],"Graph":[53],"Neural":[54],"Networks":[55],"(GNN)":[56],"capture":[58],"spatial":[59],"information":[60],"Gated":[62],"Recurrent":[63],"Units":[64],"(GRU)":[65],"encapsulate":[67],"temporal":[69],"aspects":[70],"within":[71],"data.":[73],"A":[74],"key":[75],"emphasis":[76],"lies":[77],"in":[78,130,173],"utilizing":[79],"stitched":[81],"representation":[82],"derived":[83],"from":[84,149,178],"microservices":[86],"events(e.g.":[87],"Image":[88],"Pull":[89],"Back":[90],"Off,":[91],"PVC":[92],"Pending),":[93],"resource":[95],"metrics":[96],"predict":[98],"failures":[100,177],"proactively.":[101],"traces":[103],"are":[104],"aggregated":[105],"construct":[107],"comprehensive":[109],"service":[110],"call":[111],"flow":[112],"graph":[113],"represented":[115],"as":[116,158,160],"dynamic":[118],"graph.":[119],"Furthermore,":[120],"permutation":[121],"testing":[122],"is":[123],"applied":[124],"harness":[126],"node":[127],"scores,":[128],"aiding":[129],"identification":[132],"causes":[135],"behind":[136],"these":[137,179],"failures.":[138],"To":[139],"evaluate":[140],"efficiency":[142,196],"we":[145,192],"utilized":[146],"in-house":[147],"data":[148,180],"open-source":[151],"application":[152],"Quote":[153],"Day":[156],"(QoTD)":[157],"well":[159],"two":[161],"publicly":[162],"available":[163],"datasets,":[164],"MicroSS":[165],"Train":[167],"Ticket.":[168],"F1":[170],"scores":[171],"obtained":[172],"predicting":[174],"sets":[181],"were":[182],"0.96,":[183],"0.98,":[184],"0.97,":[186],"respectively,":[187],"beating":[188],"stateof-the-art.":[190],"Additionally,":[191],"further":[193],"evaluated":[194],"using":[201],"MAR":[202],"MFR.":[204],"These":[205],"results":[206],"also":[207],"outperform":[208],"state":[210],"art.":[213]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
