{"id":"https://openalex.org/W4396707569","doi":"https://doi.org/10.1145/3661825","title":"OptimML: Joint Control of Inference Latency and Server Power Consumption for ML Performance Optimization","display_name":"OptimML: Joint Control of Inference Latency and Server Power Consumption for ML Performance Optimization","publication_year":2024,"publication_date":"2024-05-07","ids":{"openalex":"https://openalex.org/W4396707569","doi":"https://doi.org/10.1145/3661825"},"language":"en","primary_location":{"id":"doi:10.1145/3661825","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3661825","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3661825","source":{"id":"https://openalex.org/S16632050","display_name":"ACM Transactions on Autonomous and Adaptive Systems","issn_l":"1556-4665","issn":["1556-4665","1556-4703"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Autonomous and Adaptive Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3661825","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060052943","display_name":"G. X. Chen","orcid":"https://orcid.org/0009-0003-0995-3721"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guoyu Chen","raw_affiliation_strings":["The Ohio State University, Columbus, OH, USA","The Ohio State University, USA"],"raw_orcid":"https://orcid.org/0009-0003-0995-3721","affiliations":[{"raw_affiliation_string":"The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"The Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100658019","display_name":"Xiaorui Wang","orcid":"https://orcid.org/0000-0001-9633-1418"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaorui Wang","raw_affiliation_strings":["The Ohio State University, Columbus, OH, USA","The Ohio State University, USA"],"raw_orcid":"https://orcid.org/0000-0001-9633-1418","affiliations":[{"raw_affiliation_string":"The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"The Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04654916,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"21","issue":"2","first_page":"1","last_page":"27"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9993000030517578,"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":0.9993000030517578,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9975000023841858,"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":0.8863750696182251},{"id":"https://openalex.org/keywords/server","display_name":"Server","score":0.7729024887084961},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.7030057907104492},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5662567615509033},{"id":"https://openalex.org/keywords/testbed","display_name":"Testbed","score":0.5333654284477234},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.5083989500999451},{"id":"https://openalex.org/keywords/power-control","display_name":"Power control","score":0.44230759143829346},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.4142093360424042},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.3002246022224426},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.2734961211681366},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.26419222354888916},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.21477213501930237}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8863750696182251},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.7729024887084961},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.7030057907104492},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5662567615509033},{"id":"https://openalex.org/C31395832","wikidata":"https://www.wikidata.org/wiki/Q1318674","display_name":"Testbed","level":2,"score":0.5333654284477234},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.5083989500999451},{"id":"https://openalex.org/C56685638","wikidata":"https://www.wikidata.org/wiki/Q2300474","display_name":"Power control","level":3,"score":0.44230759143829346},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.4142093360424042},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.3002246022224426},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.2734961211681366},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26419222354888916},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.21477213501930237},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3661825","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3661825","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3661825","source":{"id":"https://openalex.org/S16632050","display_name":"ACM Transactions on Autonomous and Adaptive Systems","issn_l":"1556-4665","issn":["1556-4665","1556-4703"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Autonomous and Adaptive Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3661825","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3661825","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3661825","source":{"id":"https://openalex.org/S16632050","display_name":"ACM Transactions on Autonomous and Adaptive Systems","issn_l":"1556-4665","issn":["1556-4665","1556-4703"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Autonomous and Adaptive Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5699999928474426,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[{"id":"https://openalex.org/G7075333376","display_name":null,"funder_award_id":"CNS-2336886","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4396707569.pdf"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W1536680647","https://openalex.org/W1919191429","https://openalex.org/W1964622779","https://openalex.org/W1969742965","https://openalex.org/W1987912519","https://openalex.org/W1993508117","https://openalex.org/W2006312753","https://openalex.org/W2015673634","https://openalex.org/W2033597569","https://openalex.org/W2038337218","https://openalex.org/W2099786809","https://openalex.org/W2112806194","https://openalex.org/W2162847528","https://openalex.org/W2167215970","https://openalex.org/W2172654076","https://openalex.org/W2194775991","https://openalex.org/W2524428287","https://openalex.org/W2531894595","https://openalex.org/W2543907405","https://openalex.org/W2554302513","https://openalex.org/W2747329762","https://openalex.org/W2809251854","https://openalex.org/W2884675507","https://openalex.org/W2897303255","https://openalex.org/W2904454889","https://openalex.org/W2911595481","https://openalex.org/W2928790192","https://openalex.org/W2950248853","https://openalex.org/W2951001719","https://openalex.org/W2966297916","https://openalex.org/W3105579047","https://openalex.org/W3128172237","https://openalex.org/W3215698464","https://openalex.org/W4230147572","https://openalex.org/W4253267708","https://openalex.org/W4310895557","https://openalex.org/W4367046811"],"related_works":["https://openalex.org/W2883256816","https://openalex.org/W2171408034","https://openalex.org/W3003320923","https://openalex.org/W2106140982","https://openalex.org/W2152313554","https://openalex.org/W2064303750","https://openalex.org/W1509300825","https://openalex.org/W3092582874","https://openalex.org/W2054620577","https://openalex.org/W3048672182"],"abstract_inverted_index":{"Power":[0],"capping":[1,21],"is":[2,22,175],"an":[3,165],"important":[4,44],"technique":[5],"for":[6,126],"high-density":[7],"servers":[8,41],"to":[9,123,177],"safely":[10],"oversubscribe":[11],"the":[12,28,75,80,109,189],"power":[13,20,85,104,127,162],"infrastructure":[14],"in":[15,36,188],"a":[16,64,91,132],"data":[17],"center.":[18],"However,":[19],"commonly":[23],"accomplished":[24],"by":[25,106],"dynamically":[26],"lowering":[27],"server":[29,71,84,103,120],"processors\u2019":[30],"frequency":[31,121],"levels,":[32],"which":[33,68],"can":[34],"result":[35],"degraded":[37],"application":[38],"performance.":[39,72],"For":[40],"that":[42,96,146],"run":[43],"machine":[45],"learning":[46],"(ML)":[47],"applications":[48],"with":[49,135,153,169],"Service-Level":[50],"Objective":[51],"(SLO)":[52],"requirements,":[53],"inference":[54,77,100,150],"performance":[55],"such":[56],"as":[57],"recognition":[58],"accuracy":[59,78,151,183],"must":[60],"be":[61,124],"optimized":[62],"within":[63],"certain":[65],"latency":[66,82,101,160],"constraint,":[67],"demands":[69],"high":[70],"To":[73],"achieve":[74,178],"best":[76],"under":[79],"desired":[81],"and":[83,102,143,161,173,184],"constraints,":[86],"this":[87],"article":[88],"proposes":[89],"OptimML,":[90],"multi-input-multi-output":[92],"(MIMO)":[93],"control":[94,167,182],"framework":[95,139],"jointly":[97],"controls":[98],"both":[99,159],"consumption,":[105],"flexibly":[107],"adjusting":[108],"ML":[110,138],"model":[111,171],"size":[112],"(and":[113],"so":[114],"its":[115],"required":[116],"computing":[117],"resources)":[118],"when":[119],"needs":[122],"lowered":[125],"capping.":[128],"Our":[129],"results":[130],"on":[131],"hardware":[133,195],"testbed":[134],"widely":[136],"adopted":[137],"(including":[140],"PyTorch,":[141],"TensorFlow,":[142],"MXNet)":[144],"show":[145],"OptimML":[147],"achieves":[148],"higher":[149],"compared":[152],"several":[154],"well-designed":[155],"baselines,":[156],"while":[157],"respecting":[158],"constraints.":[163],"Furthermore,":[164],"adaptive":[166],"scheme":[168],"online":[170],"switching":[172],"estimation":[174],"designed":[176],"analytic":[179],"assurance":[180],"of":[181,191],"system":[185],"stability,":[186],"even":[187],"face":[190],"significant":[192],"workload":[193],"or":[194],"variations.":[196]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}