{"id":"https://openalex.org/W4416004364","doi":"https://doi.org/10.1145/3731599.3767471","title":"From Exploration to Explanation: ML-Driven Causal Discovery for Datacenter Reliability at Scale","display_name":"From Exploration to Explanation: ML-Driven Causal Discovery for Datacenter Reliability at Scale","publication_year":2025,"publication_date":"2025-11-07","ids":{"openalex":"https://openalex.org/W4416004364","doi":"https://doi.org/10.1145/3731599.3767471"},"language":null,"primary_location":{"id":"doi:10.1145/3731599.3767471","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3731599.3767471","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SC '25 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis","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/A5081141790","display_name":"Pavana Prakash","orcid":"https://orcid.org/0000-0002-5752-5778"},"institutions":[{"id":"https://openalex.org/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pavana Prakash","raw_affiliation_strings":["Hewlett Packard Labs, Milpitas, USA"],"raw_orcid":"https://orcid.org/0000-0002-5752-5778","affiliations":[{"raw_affiliation_string":"Hewlett Packard Labs, Milpitas, USA","institution_ids":["https://openalex.org/I1324840837"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056770660","display_name":"Rolando P. Hong Enriquez","orcid":"https://orcid.org/0009-0008-5652-4408"},"institutions":[{"id":"https://openalex.org/I4210156325","display_name":"Hewlett-Packard (United Kingdom)","ror":"https://ror.org/05g4mtv59","country_code":"GB","type":"company","lineage":["https://openalex.org/I1324840837","https://openalex.org/I4210156325"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Rolando P. Hong Enriquez","raw_affiliation_strings":["Hewlett Packard Labs, Oxford, United Kingdom"],"raw_orcid":"https://orcid.org/0009-0008-5652-4408","affiliations":[{"raw_affiliation_string":"Hewlett Packard Labs, Oxford, United Kingdom","institution_ids":["https://openalex.org/I4210156325"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029590134","display_name":"Sergey Serebryakov","orcid":"https://orcid.org/0000-0001-6963-9337"},"institutions":[{"id":"https://openalex.org/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sergey Serebryakov","raw_affiliation_strings":["Hewlett Packard Labs, Milpitas, USA"],"raw_orcid":"https://orcid.org/0000-0001-6963-9337","affiliations":[{"raw_affiliation_string":"Hewlett Packard Labs, Milpitas, USA","institution_ids":["https://openalex.org/I1324840837"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003789391","display_name":"David Grant","orcid":"https://orcid.org/0009-0005-8435-6446"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Grant","raw_affiliation_strings":["Oak Ridge National Laboratory (ORNL), Oak Ridge, USA"],"raw_orcid":"https://orcid.org/0009-0005-8435-6446","affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory (ORNL), Oak Ridge, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018102608","display_name":"Wesley Brewer","orcid":"https://orcid.org/0000-0002-3639-3956"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wesley Brewer","raw_affiliation_strings":["Oak Ridge National Laboratory (ORNL), Oak Ridge, USA"],"raw_orcid":"https://orcid.org/0000-0002-3639-3956","affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory (ORNL), Oak Ridge, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027761275","display_name":"Dejan Miloji\u010di\u0107","orcid":"https://orcid.org/0000-0001-9830-8588"},"institutions":[{"id":"https://openalex.org/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dejan Milojicic","raw_affiliation_strings":["Hewlett Packard Labs, Milpitas, USA"],"raw_orcid":"https://orcid.org/0000-0001-9830-8588","affiliations":[{"raw_affiliation_string":"Hewlett Packard Labs, Milpitas, USA","institution_ids":["https://openalex.org/I1324840837"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.34145373,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"997","last_page":"1002"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.6191999912261963,"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":0.6191999912261963,"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":0.2092999964952469,"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/T10714","display_name":"Software-Defined Networks and 5G","score":0.014299999922513962,"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/reliability","display_name":"Reliability (semiconductor)","score":0.7152000069618225},{"id":"https://openalex.org/keywords/pace","display_name":"Pace","score":0.6962000131607056},{"id":"https://openalex.org/keywords/downtime","display_name":"Downtime","score":0.5670999884605408},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5228999853134155},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5156000256538391},{"id":"https://openalex.org/keywords/interdependence","display_name":"Interdependence","score":0.41429999470710754},{"id":"https://openalex.org/keywords/causality","display_name":"Causality (physics)","score":0.4000000059604645},{"id":"https://openalex.org/keywords/granger-causality","display_name":"Granger causality","score":0.39640000462532043}],"concepts":[{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.7152000069618225},{"id":"https://openalex.org/C2777526511","wikidata":"https://www.wikidata.org/wiki/Q691543","display_name":"Pace","level":2,"score":0.6962000131607056},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6689000129699707},{"id":"https://openalex.org/C180591934","wikidata":"https://www.wikidata.org/wiki/Q1253369","display_name":"Downtime","level":2,"score":0.5670999884605408},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5228999853134155},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5156000256538391},{"id":"https://openalex.org/C185874996","wikidata":"https://www.wikidata.org/wiki/Q269699","display_name":"Interdependence","level":2,"score":0.41429999470710754},{"id":"https://openalex.org/C64357122","wikidata":"https://www.wikidata.org/wiki/Q1149766","display_name":"Causality (physics)","level":2,"score":0.4000000059604645},{"id":"https://openalex.org/C129824826","wikidata":"https://www.wikidata.org/wiki/Q2630107","display_name":"Granger causality","level":2,"score":0.39640000462532043},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39399999380111694},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39329999685287476},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.36899998784065247},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.36809998750686646},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3677000105381012},{"id":"https://openalex.org/C84945661","wikidata":"https://www.wikidata.org/wiki/Q7366567","display_name":"Root cause","level":2,"score":0.3659999966621399},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.34700000286102295},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.3122999966144562},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.30379998683929443},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.2818000018596649},{"id":"https://openalex.org/C2776145597","wikidata":"https://www.wikidata.org/wiki/Q25339462","display_name":"Dropout (neural networks)","level":2,"score":0.26589998602867126},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.26019999384880066},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.25690001249313354}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3731599.3767471","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3731599.3767471","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SC '25 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W2178225550","https://openalex.org/W2593118993","https://openalex.org/W3115176797","https://openalex.org/W3209605437","https://openalex.org/W4312204532","https://openalex.org/W4403964558","https://openalex.org/W4406172366","https://openalex.org/W4406265500"],"related_works":[],"abstract_inverted_index":{"Modern":[0],"datacenters":[1],"operate":[2],"at":[3],"unprecedented":[4],"scale,":[5],"supporting":[6],"HPC":[7],"and":[8,28,37,61,81,100,125],"AI":[9],"workloads":[10],"while":[11],"consuming":[12],"hundreds":[13],"of":[14,16],"megawatts":[15],"power.":[17],"Their":[18],"reliability":[19,124],"is":[20],"challenged":[21],"by":[22],"complex":[23],"interdependencies":[24],"across":[25],"cooling,":[26],"power,":[27],"network":[29],"subsystems,":[30],"where":[31],"failures":[32],"can":[33],"cascade":[34],"into":[35,114],"downtime":[36],"degraded":[38],"performance.":[39],"Existing":[40],"monitoring":[41],"approaches,":[42],"largely":[43],"threshold":[44],"or":[45],"only":[46],"correlation-based,":[47],"struggle":[48],"to":[49,77],"isolate":[50],"root":[51],"causes":[52],"within":[53],"high-dimensional,":[54],"evolving":[55],"telemetry.":[56,87],"We":[57],"present":[58],"PACE":[59,88,113],"(Pattern":[60],"Causal":[62],"Exploration),":[63],"an":[64],"ML-based":[65],"framework":[66],"that":[67,95],"combines":[68],"unsupervised":[69],"correlation":[70],"clustering":[71],"with":[72,97],"supervised,":[73],"lag-aware":[74],"Granger":[75],"causality":[76],"uncover":[78],"subsystem":[79,93],"structure":[80],"directed":[82],"causal":[83,91],"pathways":[84],"from":[85],"multivariate":[86],"yields":[89],"interpretable":[90],"graphs,":[92],"heatmaps,":[94],"align":[96],"physical":[98],"processes":[99],"control":[101],"logic,":[102],"providing":[103],"actionable":[104],"insights":[105],"for":[106],"operations.":[107],"Finally,":[108],"we":[109],"discuss":[110],"how":[111],"embedding":[112],"digital":[115],"twin":[116],"architectures":[117],"enables":[118],"causal-informed":[119],"what-if":[120],"reasoning,":[121],"advancing":[122],"the":[123],"efficiency":[126],"in":[127],"datacenters.":[128]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-07T00:00:00"}