{"id":"https://openalex.org/W4285279870","doi":"https://doi.org/10.1109/tgcn.2022.3171680","title":"Energy-Efficient Online Scheduling of Transformer Inference Services on GPU Servers","display_name":"Energy-Efficient Online Scheduling of Transformer Inference Services on GPU Servers","publication_year":2022,"publication_date":"2022-05-05","ids":{"openalex":"https://openalex.org/W4285279870","doi":"https://doi.org/10.1109/tgcn.2022.3171680"},"language":"en","primary_location":{"id":"doi:10.1109/tgcn.2022.3171680","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tgcn.2022.3171680","pdf_url":null,"source":{"id":"https://openalex.org/S4210192662","display_name":"IEEE Transactions on Green Communications and Networking","issn_l":"2473-2400","issn":["2473-2400"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Green Communications and Networking","raw_type":"journal-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/A5005934380","display_name":"Yuxin Wang","orcid":"https://orcid.org/0000-0001-7680-1419"},"institutions":[{"id":"https://openalex.org/I141568987","display_name":"Hong Kong Baptist University","ror":"https://ror.org/0145fw131","country_code":"HK","type":"education","lineage":["https://openalex.org/I141568987"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yuxin Wang","raw_affiliation_strings":["Department of Computer Science, Hong Kong Baptist University, Hong Kong, SAR, China"],"raw_orcid":"https://orcid.org/0000-0001-7680-1419","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Hong Kong Baptist University, Hong Kong, SAR, China","institution_ids":["https://openalex.org/I141568987"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018867983","display_name":"Qiang Wang","orcid":"https://orcid.org/0000-0002-2986-967X"},"institutions":[{"id":"https://openalex.org/I141568987","display_name":"Hong Kong Baptist University","ror":"https://ror.org/0145fw131","country_code":"HK","type":"education","lineage":["https://openalex.org/I141568987"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Qiang Wang","raw_affiliation_strings":["Department of Computer Science, Hong Kong Baptist University, Hong Kong, SAR, China"],"raw_orcid":"https://orcid.org/0000-0002-2986-967X","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Hong Kong Baptist University, Hong Kong, SAR, China","institution_ids":["https://openalex.org/I141568987"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100730785","display_name":"Xiaowen Chu","orcid":"https://orcid.org/0000-0001-9745-4372"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xiaowen Chu","raw_affiliation_strings":["Data Science and Analytics Thrust, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China","Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0001-9745-4372","affiliations":[{"raw_affiliation_string":"Data Science and Analytics Thrust, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China","institution_ids":[]},{"raw_affiliation_string":"Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.668,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.6961368,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"6","issue":"3","first_page":"1649","last_page":"1659"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9987999796867371,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9987999796867371,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9944999814033508,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8183609843254089},{"id":"https://openalex.org/keywords/server","display_name":"Server","score":0.691108226776123},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.6163149476051331},{"id":"https://openalex.org/keywords/energy-consumption","display_name":"Energy consumption","score":0.5397049188613892},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.537746012210846},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5286857485771179},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4830927848815918},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.3261580467224121},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.26112791895866394},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1893928050994873},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.07939419150352478}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8183609843254089},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.691108226776123},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.6163149476051331},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.5397049188613892},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.537746012210846},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5286857485771179},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4830927848815918},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3261580467224121},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.26112791895866394},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1893928050994873},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.07939419150352478},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tgcn.2022.3171680","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tgcn.2022.3171680","pdf_url":null,"source":{"id":"https://openalex.org/S4210192662","display_name":"IEEE Transactions on Green Communications and Networking","issn_l":"2473-2400","issn":["2473-2400"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Green Communications and Networking","raw_type":"journal-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-118320","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-118320","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.8999999761581421}],"awards":[{"id":"https://openalex.org/G2966285179","display_name":null,"funder_award_id":"HKBU 12200418","funder_id":"https://openalex.org/F4320321592","funder_display_name":"Research Grants Council, University Grants Committee"}],"funders":[{"id":"https://openalex.org/F4320320955","display_name":"Hong Kong Baptist University","ror":"https://ror.org/0145fw131"},{"id":"https://openalex.org/F4320321592","display_name":"Research Grants Council, University Grants Committee","ror":"https://ror.org/00djwmt25"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2139774022","https://openalex.org/W2529165666","https://openalex.org/W2614112306","https://openalex.org/W2614226686","https://openalex.org/W2760837370","https://openalex.org/W2798291715","https://openalex.org/W2896457183","https://openalex.org/W2903810591","https://openalex.org/W2905270607","https://openalex.org/W2945148926","https://openalex.org/W2948947170","https://openalex.org/W2962824709","https://openalex.org/W3034655362","https://openalex.org/W3037110041","https://openalex.org/W3043273434","https://openalex.org/W3117477522","https://openalex.org/W3130716829","https://openalex.org/W3157546558","https://openalex.org/W3172509117","https://openalex.org/W3204998121","https://openalex.org/W4206706211","https://openalex.org/W4288337707","https://openalex.org/W6638523607","https://openalex.org/W6739901393","https://openalex.org/W6769454693"],"related_works":["https://openalex.org/W2092530219","https://openalex.org/W2388464034","https://openalex.org/W2533125852","https://openalex.org/W2140460949","https://openalex.org/W2105580438","https://openalex.org/W2057435755","https://openalex.org/W2018782216","https://openalex.org/W4214747436","https://openalex.org/W2953002963","https://openalex.org/W179829755"],"abstract_inverted_index":{"Cloud":[0],"service":[1,73],"providers":[2],"are":[3],"deploying":[4],"Transformer-based":[5],"deep":[6],"learning":[7],"models":[8],"on":[9,81,104,138,172,189],"GPU":[10,51,139,175,190],"servers":[11,191],"to":[12,42,144,168],"support":[13],"many":[14],"online":[15,131,205],"inference-as-a-service":[16],"(IAAS)":[17],"applications,":[18],"given":[19],"the":[20,49,54,64,82,146,154,158,161,173,184,204,214,218],"predominant":[21],"performance":[22,84,96,115,221],"of":[23,44,46,60,88,183,186],"Transformers":[24],"in":[25],"natural":[26],"language":[27],"processing":[28],"(NLP)":[29],"tasks.":[30],"However,":[31],"Transformers\u2019":[32],"inherent":[33],"high":[34],"complexity":[35],"and":[36,57,85,101,116,163,170,196,217],"large":[37],"model":[38,119],"size":[39],"(e.g.,":[40],"billions":[41,45],"hundreds":[43],"parameters)":[47],"tax":[48],"resource-constrained":[50],"servers.":[52,176],"Improving":[53],"energy":[55,86,102,117,164,215],"efficiency":[56,87,165,216],"payload":[58],"capability":[59],"IAAS":[61],"without":[62],"violating":[63],"service-level":[65],"agreement":[66],"(SLA)":[67],"becomes":[68],"a":[69,78,114,180],"practical":[70],"challenge":[71],"for":[72,120,136],"providers.":[74],"This":[75],"work":[76],"conducts":[77],"comprehensive":[79],"study":[80],"inference":[83,133,188,207,220],"Transformer":[89,121,137,187],"models.":[90],"First,":[91],"we":[92,112,128,142],"empirically":[93],"characterize":[94],"essential":[95],"metrics,":[97],"including":[98],"latency,":[99],"throughput,":[100],"consumption":[103,118],"NVIDIA":[105],"GPUs":[106],"under":[107,222],"various":[108,193],"workload":[109,197],"configurations.":[110],"Second,":[111],"establish":[113],"that":[122,202],"facilitates":[123],"energy-efficient":[124],"scheduling":[125,134,156,210],"policies.":[126],"Finally,":[127],"propose":[129],"an":[130],"batch":[132,206],"scheme":[135],"servers,":[140],"which":[141],"refer":[143],"as":[145],"Mixed":[147],"Aligned":[148],"Scheduling":[149],"(MAS)":[150],"scheme.":[151],"Compared":[152],"with":[153,192,208],"existing":[155],"schemes,":[157],"MAS":[159],"improves":[160],"throughput":[162],"by":[166],"up":[167],"61.56%":[169],"69.79%":[171],"V100":[174],"Our":[177],"findings":[178],"expose":[179],"full":[181],"scope":[182],"characteristics":[185],"input":[194],"shapes":[195],"balancing":[198],"degrees.":[199],"We":[200],"show":[201],"merging":[203],"robust":[209],"schemes":[211],"can":[212],"improve":[213],"overall":[219],"latency":[223],"constraints.":[224]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}