{"id":"https://openalex.org/W4290875409","doi":"https://doi.org/10.1145/3534678.3539127","title":"NENYA: Cascade Reinforcement Learning for Cost-Aware Failure Mitigation at Microsoft 365","display_name":"NENYA: Cascade Reinforcement Learning for Cost-Aware Failure Mitigation at Microsoft 365","publication_year":2022,"publication_date":"2022-08-12","ids":{"openalex":"https://openalex.org/W4290875409","doi":"https://doi.org/10.1145/3534678.3539127"},"language":"en","primary_location":{"id":"doi:10.1145/3534678.3539127","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3534678.3539127","pdf_url":null,"source":{"id":"https://openalex.org/S4363608767","display_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100364381","display_name":"Lu Wang","orcid":"https://orcid.org/0000-0001-6345-3873"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lu Wang","raw_affiliation_strings":["Microsoft Research, Beijing, UNK, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Beijing, UNK, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024073253","display_name":"Pu Zhao","orcid":"https://orcid.org/0000-0002-4518-323X"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pu Zhao","raw_affiliation_strings":["Microsoft Research, Beijing, UNK, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Beijing, UNK, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101995509","display_name":"Chao Du","orcid":"https://orcid.org/0009-0008-2893-5461"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Du","raw_affiliation_strings":["Microsoft Research, Beijing, UNK, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Beijing, UNK, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006894386","display_name":"Chuan Luo","orcid":"https://orcid.org/0000-0001-5028-1064"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuan Luo","raw_affiliation_strings":["Microsoft Research, Beijing, UNK, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Beijing, UNK, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077738157","display_name":"Mengna Su","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mengna Su","raw_affiliation_strings":["Microsoft 365, Suzhou, UNK, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft 365, Suzhou, UNK, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101564849","display_name":"Fangkai Yang","orcid":"https://orcid.org/0000-0002-3089-0345"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fangkai Yang","raw_affiliation_strings":["Microsoft Research, Beijing, UNK, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Beijing, UNK, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107248181","display_name":"Yudong Liu","orcid":"https://orcid.org/0000-0002-2099-6090"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yudong Liu","raw_affiliation_strings":["Microsoft Research, Beijing, UNK, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Beijing, UNK, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088646345","display_name":"Qingwei Lin","orcid":"https://orcid.org/0000-0003-2559-2383"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingwei Lin","raw_affiliation_strings":["Microsoft Research, Beijing, UNK, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Beijing, UNK, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100340868","display_name":"Min Wang","orcid":"https://orcid.org/0000-0001-7838-8947"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Min Wang","raw_affiliation_strings":["Microsoft 365, Suzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft 365, Suzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086338440","display_name":"Yingnong Dang","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yingnong Dang","raw_affiliation_strings":["Microsoft Azure, Seattle, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Azure, Seattle, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100412598","display_name":"Hongyu Zhang","orcid":"https://orcid.org/0000-0002-3063-9425"},"institutions":[{"id":"https://openalex.org/I78757542","display_name":"University of Newcastle Australia","ror":"https://ror.org/00eae9z71","country_code":"AU","type":"education","lineage":["https://openalex.org/I78757542"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Hongyu Zhang","raw_affiliation_strings":["The University of Newcastle, Newcastle, UNK, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Newcastle, Newcastle, UNK, Australia","institution_ids":["https://openalex.org/I78757542"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108894474","display_name":"Saravan Rajmohan","orcid":"https://orcid.org/0009-0003-0204-7187"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Saravan Rajmohan","raw_affiliation_strings":["Microsoft 365, Seattle, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft 365, Seattle, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100331488","display_name":"Dongmei Zhang","orcid":"https://orcid.org/0000-0002-9230-2799"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongmei Zhang","raw_affiliation_strings":["Microsoft Research, Beijing, UNK, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Beijing, UNK, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4032","last_page":"4040"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.9943000078201294,"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":0.9943000078201294,"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.9753000140190125,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9745000004768372,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7317361831665039},{"id":"https://openalex.org/keywords/cascade","display_name":"Cascade","score":0.7252904176712036},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6781346797943115},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.260733962059021},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15587171912193298}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7317361831665039},{"id":"https://openalex.org/C34146451","wikidata":"https://www.wikidata.org/wiki/Q5048094","display_name":"Cascade","level":2,"score":0.7252904176712036},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6781346797943115},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.260733962059021},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15587171912193298},{"id":"https://openalex.org/C42360764","wikidata":"https://www.wikidata.org/wiki/Q83588","display_name":"Chemical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3534678.3539127","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3534678.3539127","pdf_url":null,"source":{"id":"https://openalex.org/S4363608767","display_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},{"id":"pmh:uon:53307","is_oa":false,"landing_page_url":"http://hdl.handle.net/1959.13/1492331","pdf_url":null,"source":{"id":"https://openalex.org/S4377196471","display_name":"NOVA (University of Newcastle Australia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I78757542","host_organization_name":"University of Newcastle Australia","host_organization_lineage":["https://openalex.org/I78757542"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/13","score":0.6700000166893005,"display_name":"Climate action"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2010805714","https://openalex.org/W2104167780","https://openalex.org/W2133943294","https://openalex.org/W2164598857","https://openalex.org/W2187089797","https://openalex.org/W2509298940","https://openalex.org/W2767346922","https://openalex.org/W2965702734","https://openalex.org/W3012544020","https://openalex.org/W3095983965","https://openalex.org/W4248659492"],"related_works":["https://openalex.org/W4210912933","https://openalex.org/W3005560120","https://openalex.org/W3094270515","https://openalex.org/W4255994452","https://openalex.org/W4226176818","https://openalex.org/W4206669594","https://openalex.org/W1986333311","https://openalex.org/W2891655128","https://openalex.org/W4210531367","https://openalex.org/W2898155611"],"abstract_inverted_index":{"Large-scale":[0],"distributed":[1],"systems,":[2],"such":[3,116,207],"as":[4,28,80,117,163],"Microsoft":[5,249],"365's":[6],"database":[7,147],"system,":[8],"require":[9,192],"timely":[10],"mitigation":[11,23,64,90,118,142,168,179,193,215,242],"solutions":[12],"to":[13,50,58,202],"address":[14,134],"failures":[15,53],"and":[16,20,35,120,170,181,209,222,241],"improve":[17],"service":[18],"availability":[19],"reliability.":[21],"Still,":[22],"actions":[24,41,91,169,216],"can":[25,42,101,230],"be":[26,43,102],"costly":[27],"they":[29],"may":[30],"cause":[31],"temporal":[32],"performance":[33],"degradation":[34],"even":[36],"incur":[37],"monetary":[38],"expenses.":[39],"Mitigation":[40],"either":[44],"administrated":[45],"in":[46,127,234],"a":[47,55,69,145,151,197,251],"reactive":[48],"fashion":[49,57],"contain":[51],"detected":[52],"or":[54,82,95],"proactive":[56,63],"reduce":[59],"potential":[60],"failures.":[61],"The":[62],"approach":[65],"typically":[66],"relies":[67],"on":[68,174,178,212],"two-stage":[70],"strategy:":[71],"the":[72,159,185,218],"prediction":[73],"model":[74,100],"will":[75],"firstly":[76,203],"identify":[77],"instances":[78,123],"(such":[79],"databases":[81,162,189,208,240],"disks)":[83],"with":[84,254],"high":[85],"failure":[86,182,237],"risk,":[87],"then":[88,210],"appropriate":[89,214],"chosen":[92],"by":[93,150],"engineers":[94],"an":[96,140],"automatic":[97],"bandit":[98],"learning":[99,155],"applied.":[103],"As":[104,184],"information":[105],"is":[106,171],"not":[107,191],"fully":[108],"shared":[109],"across":[110],"those":[111,130],"two":[112,131],"stages,":[113],"important":[114],"factors":[115],"costs":[119,180],"states":[121,160],"of":[122,129,161,188,239],"are":[124],"often":[125],"ignored":[126],"one":[128],"stages.":[132],"To":[133],"these":[135],"issues,":[136],"we":[137],"propose":[138],"NENYA,":[139],"end-to-end":[141],"solution":[143],"for":[144,217],"large-scale":[146],"system":[148],"powered":[149],"novel":[152,198],"cascade":[153,199],"reinforcement":[154],"model.":[156],"By":[157],"taking":[158],"input,":[164],"NENYA":[165,195,244],"directly":[166],"outputs":[167],"optimized":[172],"based":[173],"jointly":[175],"cumulative":[176],"feedback":[177],"rates.":[183],"overwhelming":[186],"majority":[187],"do":[190],"actions,":[194],"utilizes":[196],"decision":[200],"structure":[201],"reliably":[204],"filter":[205],"out":[206],"focus":[211],"choosing":[213],"rest.":[219],"Extensive":[220],"offline":[221],"online":[223],"experiments":[224],"have":[225],"shown":[226],"that":[227],"our":[228],"methods":[229],"outperform":[231],"existing":[232],"practices":[233],"reducing":[235],"both":[236],"rates":[238],"costs.":[243],"has":[245],"been":[246],"integrated":[247],"into":[248],"365,":[250],"productive":[252],"platform,":[253],"sounding":[255],"success.":[256]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}