{"id":"https://openalex.org/W4404386288","doi":"https://doi.org/10.1145/3698038.3698556","title":"InferCool: Enhancing AI Inference Cooling through Transparent, Non-Intrusive Task Reassignment","display_name":"InferCool: Enhancing AI Inference Cooling through Transparent, Non-Intrusive Task Reassignment","publication_year":2024,"publication_date":"2024-11-14","ids":{"openalex":"https://openalex.org/W4404386288","doi":"https://doi.org/10.1145/3698038.3698556"},"language":"en","primary_location":{"id":"doi:10.1145/3698038.3698556","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3698038.3698556","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/A5006710277","display_name":"Qiangyu Pei","orcid":"https://orcid.org/0000-0001-8870-4309"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qiangyu Pei","raw_affiliation_strings":["Huazhong University of Science and Technology, Wuhan, China and National Engineering Research Center for Big Data Technology and System, Services Computing Technology and System Lab, Cluster and Grid Computing Lab, Huazhong University of Science and Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology, Wuhan, China and National Engineering Research Center for Big Data Technology and System, Services Computing Technology and System Lab, Cluster and Grid Computing Lab, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100403099","display_name":"Lin Wang","orcid":"https://orcid.org/0000-0001-7181-6128"},"institutions":[{"id":"https://openalex.org/I206945453","display_name":"Paderborn University","ror":"https://ror.org/058kzsd48","country_code":"DE","type":"education","lineage":["https://openalex.org/I206945453"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Lin Wang","raw_affiliation_strings":["Paderborn University, Paderborn, Germany"],"affiliations":[{"raw_affiliation_string":"Paderborn University, Paderborn, Germany","institution_ids":["https://openalex.org/I206945453"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110011266","display_name":"Dong Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210144143","display_name":"Inspur (China)","ror":"https://ror.org/0474p4r72","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210144143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Zhang","raw_affiliation_strings":["Inspur Data Co., Ltd., Jinan, China"],"affiliations":[{"raw_affiliation_string":"Inspur Data Co., Ltd., Jinan, China","institution_ids":["https://openalex.org/I4210144143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110892639","display_name":"Bingheng Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210144143","display_name":"Inspur (China)","ror":"https://ror.org/0474p4r72","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210144143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bingheng Yan","raw_affiliation_strings":["Inspur Data Co., Ltd., Jinan, China"],"affiliations":[{"raw_affiliation_string":"Inspur Data Co., Ltd., Jinan, China","institution_ids":["https://openalex.org/I4210144143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027592563","display_name":"Yu Chen","orcid":"https://orcid.org/0000-0003-0782-0450"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Yu","raw_affiliation_strings":["Huazhong University of Science and Technology, Wuhan, China and National Engineering Research Center for Big Data Technology and System, Services Computing Technology and System Lab, Cluster and Grid Computing Lab, Huazhong University of Science and Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology, Wuhan, China and National Engineering Research Center for Big Data Technology and System, Services Computing Technology and System Lab, Cluster and Grid Computing Lab, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048398271","display_name":"Fangming Liu","orcid":"https://orcid.org/0000-0002-8570-1345"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]},{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fangming Liu","raw_affiliation_strings":["Huazhong University of Science and Technology, Peng Cheng Laboratory, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology, Peng Cheng Laboratory, Wuhan, China","institution_ids":["https://openalex.org/I47720641","https://openalex.org/I4210136793"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5006710277"],"corresponding_institution_ids":["https://openalex.org/I47720641"],"apc_list":null,"apc_paid":null,"fwci":2.8958,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.92601818,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"487","last_page":"504"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9889000058174133,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9889000058174133,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9767000079154968,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9760000109672546,"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/inference","display_name":"Inference","score":0.7920361757278442},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6966891288757324},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6759037375450134},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46723228693008423},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3371981978416443},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12820693850517273},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.1202346682548523}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7920361757278442},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6966891288757324},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6759037375450134},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46723228693008423},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3371981978416443},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12820693850517273},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.1202346682548523}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3698038.3698556","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3698038.3698556","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2024446827","https://openalex.org/W2040309615","https://openalex.org/W2044657099","https://openalex.org/W2111165502","https://openalex.org/W2170532136","https://openalex.org/W2883521700","https://openalex.org/W2902633182","https://openalex.org/W2946069812","https://openalex.org/W2950144996","https://openalex.org/W2982157693","https://openalex.org/W2982619481","https://openalex.org/W2988410283","https://openalex.org/W3035915309","https://openalex.org/W3097411828","https://openalex.org/W3130689885","https://openalex.org/W3157133500","https://openalex.org/W3208777667","https://openalex.org/W4214540558","https://openalex.org/W4214669552","https://openalex.org/W4304192541","https://openalex.org/W4308427193","https://openalex.org/W4366564134","https://openalex.org/W4388041447"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W3196817267","https://openalex.org/W1976600725"],"abstract_inverted_index":{"The":[0],"increasing":[1],"power":[2,133],"consumption":[3],"of":[4,18,53,80,178],"AI":[5,29,54],"inference":[6,30,55,93,122],"in":[7,38],"modern":[8,90],"datacenters":[9],"has":[10,31],"escalated":[11],"cooling":[12,20,41,56,81,104,114,119,175,188],"demands":[13],"significantly,":[14],"necessitating":[15],"the":[16,48,73,77,96,103,163],"adoption":[17],"potent":[19],"approaches":[21],"like":[22],"water":[23],"cooling.":[24],"Unlike":[25],"traditional":[26],"cloud":[27],"workloads,":[28],"unique":[32],"characteristics":[33],"that":[34,159],"create":[35],"substantial":[36],"gaps":[37],"achieving":[39],"optimal":[40],"efficiency.":[42],"In":[43],"this":[44,108],"work,":[45],"we":[46,83,110],"present":[47],"first":[49],"comprehensive":[50],"measurement":[51],"study":[52],"across":[57,169],"various":[58],"models":[59],"within":[60],"an":[61],"industrial-ready":[62],"scheduling":[63,97,146,195],"framework,":[64],"highlighting":[65],"significant":[66],"inefficiencies":[67],"and":[68,134,138,144,154,190],"their":[69],"causes.":[70],"To":[71],"fill":[72],"gap":[74],"while":[75],"following":[76],"fundamental":[78],"requirements":[79],"systems,":[82],"explore":[84],"a":[85,113,131,139,151,155],"new":[86],"opportunity":[87],"presented":[88],"by":[89,167],"Multi-Instance":[91],"GPU-enabled":[92],"serving,":[94],"where":[95],"dimension":[98],"is":[99,191],"naturally":[100],"orthogonal":[101],"to":[102,117,174,186],"dimension.":[105],"Building":[106],"on":[107,150],"insight,":[109],"develop":[111],"InferCool,":[112],"middleware":[115],"designed":[116],"enhance":[118],"efficiency":[120],"for":[121],"serving":[123],"through":[124],"transparent,":[125],"non-intrusive":[126],"task":[127],"reassignment.":[128],"It":[129],"includes":[130],"streamlined":[132],"temperature":[135,166],"prediction":[136],"approach":[137],"thermal-aware,":[140],"adaptive":[141],"application":[142],"deployment":[143],"request":[145],"mechanism.":[147],"Real-world":[148],"experiments":[149],"water-cooled":[152],"testbed":[153],"three-node":[156],"cluster":[157],"demonstrate":[158],"InferCool":[160,182],"can":[161],"reduce":[162],"maximum":[164],"GPU":[165],"5\u00b0C":[168],"eight":[170],"A100":[171],"GPUs,":[172],"equivalent":[173],"energy":[176],"savings":[177],"about":[179],"20%.":[180],"Importantly,":[181],"requires":[183],"no":[184],"modifications":[185],"existing":[187,194],"infrastructures":[189],"compatible":[192],"with":[193],"systems.":[196]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}
