{"id":"https://openalex.org/W4404386839","doi":"https://doi.org/10.1145/3698038.3698534","title":"Deoxys: A Causal Inference Engine for Unhealthy Node Mitigation in Large-scale Cloud Infrastructure","display_name":"Deoxys: A Causal Inference Engine for Unhealthy Node Mitigation in Large-scale Cloud Infrastructure","publication_year":2024,"publication_date":"2024-11-14","ids":{"openalex":"https://openalex.org/W4404386839","doi":"https://doi.org/10.1145/3698038.3698534"},"language":"en","primary_location":{"id":"doi:10.1145/3698038.3698534","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3698038.3698534","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Symposium on Cloud Computing","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/A5030520880","display_name":"Chaoyun Zhang","orcid":"https://orcid.org/0000-0002-1304-6839"},"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":true,"raw_author_name":"Chaoyun Zhang","raw_affiliation_strings":["Microsoft, China"],"affiliations":[{"raw_affiliation_string":"Microsoft, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016532602","display_name":"Randolph Yao","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":"Randolph Yao","raw_affiliation_strings":["Microsoft, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027659574","display_name":"Si Qin","orcid":"https://orcid.org/0000-0002-8698-1860"},"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":"Si Qin","raw_affiliation_strings":["Microsoft, China"],"affiliations":[{"raw_affiliation_string":"Microsoft, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115602606","display_name":"Ze Li","orcid":"https://orcid.org/0000-0003-4789-0170"},"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":"Ze Li","raw_affiliation_strings":["Microsoft, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001596025","display_name":"Srishti Shekhar Agrawal","orcid":"https://orcid.org/0009-0006-8745-6271"},"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":"Shekhar Agrawal","raw_affiliation_strings":["Microsoft, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111179255","display_name":"B Mishra","orcid":"https://orcid.org/0009-0002-9923-6701"},"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":"Binit R. Mishra","raw_affiliation_strings":["Microsoft, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033955384","display_name":"Tri Minh Tran","orcid":"https://orcid.org/0000-0002-9913-0117"},"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":"Tri Tran","raw_affiliation_strings":["Microsoft, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070950193","display_name":"Minghua Ma","orcid":"https://orcid.org/0000-0002-6303-1731"},"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":"Minghua Ma","raw_affiliation_strings":["Microsoft, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"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, China"],"affiliations":[{"raw_affiliation_string":"Microsoft, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114652451","display_name":"Murali Chintalapati","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":"Murali Chintalapati","raw_affiliation_strings":["Microsoft, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, 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, China"],"affiliations":[{"raw_affiliation_string":"Microsoft, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5030520880"],"corresponding_institution_ids":["https://openalex.org/I4210113369"],"apc_list":null,"apc_paid":null,"fwci":1.0911,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.82156803,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"361","last_page":"379"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.992900013923645,"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"}},"topics":[{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.992900013923645,"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"}},{"id":"https://openalex.org/T10917","display_name":"Smart Grid Security and Resilience","score":0.9922000169754028,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12879","display_name":"Distributed Sensor Networks and Detection Algorithms","score":0.9890999794006348,"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/cloud-computing","display_name":"Cloud computing","score":0.8199671506881714},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7114089727401733},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6492483615875244},{"id":"https://openalex.org/keywords/causal-inference","display_name":"Causal inference","score":0.6451648473739624},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5806713700294495},{"id":"https://openalex.org/keywords/inference-engine","display_name":"Inference engine","score":0.5238518714904785},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.5015501976013184},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.3437000513076782},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.32870787382125854},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3268219828605652},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22413671016693115},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.13675454258918762},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12515640258789062},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.08258113265037537},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07159218192100525}],"concepts":[{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.8199671506881714},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7114089727401733},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6492483615875244},{"id":"https://openalex.org/C158600405","wikidata":"https://www.wikidata.org/wiki/Q5054566","display_name":"Causal inference","level":2,"score":0.6451648473739624},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5806713700294495},{"id":"https://openalex.org/C46743427","wikidata":"https://www.wikidata.org/wiki/Q1341685","display_name":"Inference engine","level":3,"score":0.5238518714904785},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.5015501976013184},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.3437000513076782},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.32870787382125854},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3268219828605652},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22413671016693115},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.13675454258918762},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12515640258789062},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.08258113265037537},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07159218192100525},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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},{"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:10.1145/3698038.3698534","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3698038.3698534","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Symposium on Cloud Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.6299999952316284}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W95608104","https://openalex.org/W340056678","https://openalex.org/W1513969590","https://openalex.org/W1971790785","https://openalex.org/W2008572484","https://openalex.org/W2043439509","https://openalex.org/W2098106282","https://openalex.org/W2118676041","https://openalex.org/W2125283600","https://openalex.org/W2167425257","https://openalex.org/W2208550830","https://openalex.org/W2209887231","https://openalex.org/W2319471676","https://openalex.org/W2624816748","https://openalex.org/W2767686712","https://openalex.org/W2884697754","https://openalex.org/W2887912472","https://openalex.org/W2890118063","https://openalex.org/W2914209329","https://openalex.org/W2959236513","https://openalex.org/W2962727190","https://openalex.org/W2962883549","https://openalex.org/W2965960151","https://openalex.org/W2969376268","https://openalex.org/W3001202326","https://openalex.org/W3006227140","https://openalex.org/W3041564249","https://openalex.org/W3083560262","https://openalex.org/W3088381833","https://openalex.org/W3092103025","https://openalex.org/W3095564427","https://openalex.org/W3101748363","https://openalex.org/W3124999902","https://openalex.org/W3160031425","https://openalex.org/W3164548985","https://openalex.org/W3168738558","https://openalex.org/W3175922078","https://openalex.org/W3204398858","https://openalex.org/W4206275166","https://openalex.org/W4226214891","https://openalex.org/W4249440929","https://openalex.org/W4285145620","https://openalex.org/W4289528791","https://openalex.org/W4290875409","https://openalex.org/W4290927765","https://openalex.org/W4292216049","https://openalex.org/W4293569092","https://openalex.org/W4308643468","https://openalex.org/W4385567765","https://openalex.org/W4385762090","https://openalex.org/W4389209173","https://openalex.org/W4394946189"],"related_works":["https://openalex.org/W2057057690","https://openalex.org/W2368184788","https://openalex.org/W2358964818","https://openalex.org/W2359535128","https://openalex.org/W2381332051","https://openalex.org/W2321443665","https://openalex.org/W2375699995","https://openalex.org/W2043719711","https://openalex.org/W2364072231","https://openalex.org/W2140069467"],"abstract_inverted_index":{"The":[0],"presence":[1],"of":[2,12,22,126],"unhealthy":[3,32,57,70,98],"nodes":[4],"in":[5,26,59],"cloud":[6,23,40,60],"infrastructure":[7],"signals":[8],"the":[9,18,96,102,124,127,143],"potential":[10],"failure":[11],"machines,":[13],"which":[14],"can":[15],"significantly":[16],"impact":[17],"availability":[19],"and":[20,67,84,117,129,138],"reliability":[21,125],"services,":[24],"resulting":[25],"negative":[27],"customer":[28],"experiences.":[29],"Effectively":[30],"addressing":[31],"node":[33,58],"mitigation":[34,54,86],"is":[35],"therefore":[36],"vital":[37],"for":[38,56],"sustaining":[39],"system":[41,145],"performance.":[42,146],"This":[43],"paper":[44],"introduces":[45],"Deoxys,":[46],"a":[47,109,132],"causal":[48,79,103],"inference":[49,104],"engine":[50],"tailored":[51],"to":[52,62,81,121],"recommending":[53],"actions":[55],"systems":[61],"minimize":[63],"virtual":[64],"machine":[65,75],"downtime":[66,136],"interruptions":[68],"during":[69],"events.":[71,99],"It":[72],"employs":[73],"double":[74],"learning":[76],"combined":[77],"with":[78],"forest":[80],"produce":[82],"precise":[83],"reliable":[85],"recommendations":[87],"based":[88,113],"solely":[89],"on":[90,114],"limited":[91],"observational":[92],"data":[93],"collected":[94],"from":[95],"historical":[97],"To":[100],"enhance":[101],"model,":[105],"Deoxys":[106],"further":[107],"incorporates":[108],"policy":[110],"fallback":[111],"mechanism":[112],"model":[115],"uncertainty":[116],"action":[118],"overriding":[119],"mechanisms":[120],"(i)":[122],"improve":[123],"system,":[128],"(ii)":[130],"strike":[131],"good":[133],"tradeoff":[134],"between":[135],"reduction":[137],"resource":[139],"utilization,":[140],"thereby":[141],"enhancing":[142],"overall":[144]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}