{"id":"https://openalex.org/W4399168608","doi":"https://doi.org/10.1109/tetc.2024.3403874","title":"Online Resource Provisioning and Batch Scheduling for AIoT Inference Serving in an XPU Edge Cloud","display_name":"Online Resource Provisioning and Batch Scheduling for AIoT Inference Serving in an XPU Edge Cloud","publication_year":2024,"publication_date":"2024-05-30","ids":{"openalex":"https://openalex.org/W4399168608","doi":"https://doi.org/10.1109/tetc.2024.3403874"},"language":"en","primary_location":{"id":"doi:10.1109/tetc.2024.3403874","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tetc.2024.3403874","pdf_url":null,"source":{"id":"https://openalex.org/S2496326734","display_name":"IEEE Transactions on Emerging Topics in Computing","issn_l":"2168-6750","issn":["2168-6750","2376-4562"],"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 Emerging Topics in Computing","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":null,"display_name":"Rongkai Liu","orcid":"https://orcid.org/0009-0001-9977-2742"},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":null,"type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rongkai Liu","raw_affiliation_strings":["China Telecom Research Institute, Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0001-9977-2742","affiliations":[{"raw_affiliation_string":"China Telecom Research Institute, Guangzhou, China","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yuting Wu","orcid":"https://orcid.org/0009-0001-4452-3837"},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":null,"type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuting Wu","raw_affiliation_strings":["China Telecom Research Institute, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-4452-3837","affiliations":[{"raw_affiliation_string":"China Telecom Research Institute, Beijing, China","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100675366","display_name":"Kongyange Zhao","orcid":"https://orcid.org/0000-0003-1927-782X"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kongyange Zhao","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-1927-782X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100760218","display_name":"Zhi Zhou","orcid":"https://orcid.org/0000-0002-0987-9344"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhi Zhou","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-0987-9344","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiang Gao","orcid":"https://orcid.org/0009-0009-5639-8066"},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":null,"type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Gao","raw_affiliation_strings":["China Telecom Research Institute, Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0009-5639-8066","affiliations":[{"raw_affiliation_string":"China Telecom Research Institute, Guangzhou, China","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100594625","display_name":"Xianchen Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":null,"type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianchen Lin","raw_affiliation_strings":["China Telecom Research Institute, Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0008-6304-9684","affiliations":[{"raw_affiliation_string":"China Telecom Research Institute, Guangzhou, China","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100763625","display_name":"Xiaoxi Zhang","orcid":"https://orcid.org/0000-0003-0751-2773"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoxi Zhang","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-0751-2773","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100385692","display_name":"Xu Chen","orcid":"https://orcid.org/0000-0001-9943-6020"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Chen","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-9943-6020","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":null,"display_name":"Gang Lu","orcid":"https://orcid.org/0009-0009-8572-9987"},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":null,"type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gang Lu","raw_affiliation_strings":["China Telecom Research Institute, Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0009-8572-9987","affiliations":[{"raw_affiliation_string":"China Telecom Research Institute, Guangzhou, China","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1363,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.78191532,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"13","issue":"1","first_page":"234","last_page":"249"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9666000008583069,"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":0.9666000008583069,"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":0.8537083864212036},{"id":"https://openalex.org/keywords/provisioning","display_name":"Provisioning","score":0.8321593999862671},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.8014781475067139},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5818538069725037},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5502750873565674},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.47655537724494934},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.463705837726593},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.43979740142822266},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4288621246814728},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.13774552941322327},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.13747137784957886},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1338571012020111},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.07987934350967407}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8537083864212036},{"id":"https://openalex.org/C172191483","wikidata":"https://www.wikidata.org/wiki/Q1071806","display_name":"Provisioning","level":2,"score":0.8321593999862671},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.8014781475067139},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5818538069725037},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5502750873565674},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.47655537724494934},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.463705837726593},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.43979740142822266},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4288621246814728},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.13774552941322327},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.13747137784957886},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1338571012020111},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.07987934350967407},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tetc.2024.3403874","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tetc.2024.3403874","pdf_url":null,"source":{"id":"https://openalex.org/S2496326734","display_name":"IEEE Transactions on Emerging Topics in Computing","issn_l":"2168-6750","issn":["2168-6750","2376-4562"],"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 Emerging Topics in Computing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1511558225","https://openalex.org/W1989702938","https://openalex.org/W2012423440","https://openalex.org/W2022958320","https://openalex.org/W2089990924","https://openalex.org/W2094108467","https://openalex.org/W2095320658","https://openalex.org/W2098909968","https://openalex.org/W2114153586","https://openalex.org/W2169466806","https://openalex.org/W2753317989","https://openalex.org/W2904351595","https://openalex.org/W2908372320","https://openalex.org/W2919017393","https://openalex.org/W2939220765","https://openalex.org/W2981207549","https://openalex.org/W2996600026","https://openalex.org/W3004127905","https://openalex.org/W3016842236","https://openalex.org/W3017135926","https://openalex.org/W3029542841","https://openalex.org/W3093818819","https://openalex.org/W3116103263","https://openalex.org/W3130689885","https://openalex.org/W3158444059","https://openalex.org/W3162157550","https://openalex.org/W3191664269","https://openalex.org/W4214921909","https://openalex.org/W4246998394","https://openalex.org/W4282934545","https://openalex.org/W4294904165","https://openalex.org/W4309639696","https://openalex.org/W4378906223","https://openalex.org/W4387870549","https://openalex.org/W6661137625","https://openalex.org/W6720433847","https://openalex.org/W6775603788","https://openalex.org/W6796196852","https://openalex.org/W6843363710","https://openalex.org/W6849527209","https://openalex.org/W6850465662"],"related_works":["https://openalex.org/W2017432143","https://openalex.org/W1973694374","https://openalex.org/W4244478748","https://openalex.org/W2983574358","https://openalex.org/W2370475531","https://openalex.org/W4385924768","https://openalex.org/W4256551238","https://openalex.org/W2785227142","https://openalex.org/W572531444","https://openalex.org/W2945962340"],"abstract_inverted_index":{"Driven":[0],"by":[1],"the":[2,10,15,20,36,50,128,140,145,157,160,177,180],"accelerated":[3],"convergence":[4],"of":[5,12,22,25,168,179],"artificial":[6],"intelligence":[7],"(AI)":[8],"and":[9,32,71,109],"Internet":[11],"Things":[13,26],"(IoT),":[14],"recent":[16],"years":[17],"have":[18,73],"witnessed":[19],"booming":[21],"Artificial":[23],"Intelligence":[24],"(AIoT).":[27],"Edge":[28],"clouds":[29],"place":[30],"computing":[31],"service":[33,146],"capabilities":[34],"at":[35],"network":[37,41],"edges":[38],"to":[39,57,132,138,165],"reduce":[40],"transmission":[42],"overhead,":[43],"which":[44],"has":[45,91],"been":[46,74],"widely":[47],"recognized":[48],"as":[49,68],"critical":[51],"infrastructure":[52],"for":[53,105,112,127,156],"AIoT":[54,115],"applications.":[55],"Meanwhile,":[56],"accelerate":[58],"computationintensive":[59],"edge":[60,78,84,121],"cloud":[61],"AI":[62,65],"operations,":[63],"specialized":[64],"accelerators":[66],"such":[67,81],"GPU,":[69],"NPU,":[70],"TPU":[72],"increasingly":[75],"integrated":[76],"into":[77],"clouds.":[79],"For":[80],"emerging":[82],"XPU":[83,120,152],"clouds,":[85],"utilizing":[86],"costly":[87],"XPUs":[88],"more":[89,113],"efficiently":[90],"become":[92],"a":[93,166],"significant":[94],"challenge.":[95],"In":[96],"this":[97],"paper,":[98],"we":[99,175],"present":[100],"an":[101,119],"online":[102,129,182],"optimization":[103,125,183],"framework":[104,130],"joint":[106],"resource":[107,161],"provisioning":[108],"batch":[110,135],"scheduling":[111],"costefficient":[114],"inference":[116,136],"serving":[117],"in":[118],"cloud.":[122],"The":[123],"essential":[124],"process":[126],"is":[131,163],"first":[133],"adaptively":[134],"tasks":[137],"increase":[139],"system":[141],"throughput":[142],"without":[143],"compromising":[144],"level":[147],"agreement":[148],"(SLA).":[149],"Next,":[150],"heterogeneous":[151],"resources":[153],"are":[154],"provisioned":[155],"batches.":[158],"Finally,":[159],"instance":[162],"consolidated":[164],"minimum":[167],"physical":[169],"servers.":[170],"Via":[171],"extensive":[172],"trace-driven":[173],"simulations,":[174],"verify":[176],"performance":[178],"presented":[181],"framework.":[184]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
