{"id":"https://openalex.org/W4408697712","doi":"https://doi.org/10.1109/tmc.2025.3553201","title":"ExpertDRL: Request Dispatching and Instance Configuration for Serverless Edge Inference With Foundation Models","display_name":"ExpertDRL: Request Dispatching and Instance Configuration for Serverless Edge Inference With Foundation Models","publication_year":2025,"publication_date":"2025-03-21","ids":{"openalex":"https://openalex.org/W4408697712","doi":"https://doi.org/10.1109/tmc.2025.3553201"},"language":"en","primary_location":{"id":"doi:10.1109/tmc.2025.3553201","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmc.2025.3553201","pdf_url":null,"source":{"id":"https://openalex.org/S69141925","display_name":"IEEE Transactions on Mobile Computing","issn_l":"1536-1233","issn":["1536-1233","1558-0660","2161-9875"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Mobile 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":"https://openalex.org/A5016449315","display_name":"Yue Zeng","orcid":"https://orcid.org/0000-0002-5553-5534"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Zeng","raw_affiliation_strings":["Department of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","Department of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, Jiangsu, China"],"raw_orcid":"https://orcid.org/0000-0002-5553-5534","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102905745","display_name":"Junlong Zhou","orcid":"https://orcid.org/0000-0002-7734-4077"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junlong Zhou","raw_affiliation_strings":["Department of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","Department of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, Jiangsu, China"],"raw_orcid":"https://orcid.org/0000-0002-7734-4077","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087746903","display_name":"Baoliu Ye","orcid":"https://orcid.org/0000-0003-1065-449X"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baoliu Ye","raw_affiliation_strings":["Department of Computer Science and Technology, State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","State Key Laboratory for Novel Software Technology, Department of Computer Science and Technology, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-1065-449X","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Department of Computer Science and Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017137055","display_name":"Zhihao Qu","orcid":"https://orcid.org/0000-0001-7538-1985"},"institutions":[{"id":"https://openalex.org/I163340411","display_name":"Hohai University","ror":"https://ror.org/01wd4xt90","country_code":"CN","type":"education","lineage":["https://openalex.org/I163340411"]},{"id":"https://openalex.org/I4210155611","display_name":"Ministry of Water Resources of the People's Republic of China","ror":"https://ror.org/04e698d63","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210155611"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihao Qu","raw_affiliation_strings":["Key Laboratory of Water Big Data Technology of Ministry of Water Resources, Hohai University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-7538-1985","affiliations":[{"raw_affiliation_string":"Key Laboratory of Water Big Data Technology of Ministry of Water Resources, Hohai University, Nanjing, China","institution_ids":["https://openalex.org/I163340411","https://openalex.org/I4210155611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043464306","display_name":"Song Guo","orcid":"https://orcid.org/0000-0001-9831-2202"},"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":"Song Guo","raw_affiliation_strings":["Hong Kong University of Science and Technology, Clear Water Bay, Hong Kong","Hong Kong University of Science and Technology, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0001-9831-2202","affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Clear Water Bay, Hong Kong","institution_ids":["https://openalex.org/I200769079"]},{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Tianjian Gong","orcid":null},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianjian Gong","raw_affiliation_strings":["Department of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","Department of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, Jiangsu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100455206","display_name":"Pan Li","orcid":"https://orcid.org/0000-0002-9057-5056"},"institutions":[{"id":"https://openalex.org/I142108993","display_name":"Southwest University","ror":"https://ror.org/01kj4z117","country_code":"CN","type":"education","lineage":["https://openalex.org/I142108993"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pan Li","raw_affiliation_strings":["College of Electronic and Information Engineering, Southwest University, Chongqing, China"],"raw_orcid":"https://orcid.org/0000-0002-9057-5056","affiliations":[{"raw_affiliation_string":"College of Electronic and Information Engineering, Southwest University, Chongqing, China","institution_ids":["https://openalex.org/I142108993"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":28.3856,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.99376004,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"24","issue":"9","first_page":"8089","last_page":"8104"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9832000136375427,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9832000136375427,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9828000068664551,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9185000061988831,"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":0.8406271934509277},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.564429759979248},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.5025486946105957},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.49822235107421875},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.4733959436416626},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4135698974132538},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2365524172782898}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8406271934509277},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.564429759979248},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.5025486946105957},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.49822235107421875},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.4733959436416626},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4135698974132538},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2365524172782898},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tmc.2025.3553201","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmc.2025.3553201","pdf_url":null,"source":{"id":"https://openalex.org/S69141925","display_name":"IEEE Transactions on Mobile Computing","issn_l":"1536-1233","issn":["1536-1233","1558-0660","2161-9875"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Mobile Computing","raw_type":"journal-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-168936","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-168936","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":[],"awards":[{"id":"https://openalex.org/G1709435680","display_name":null,"funder_award_id":"62402226","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2474133561","display_name":null,"funder_award_id":"62172224","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3505793782","display_name":null,"funder_award_id":"BK20220138","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"},{"id":"https://openalex.org/G3979638104","display_name":null,"funder_award_id":"BK20241453","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"},{"id":"https://openalex.org/G7557400493","display_name":null,"funder_award_id":"62441225","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W2145339207","https://openalex.org/W2194775991","https://openalex.org/W2776507577","https://openalex.org/W2824027552","https://openalex.org/W2905342581","https://openalex.org/W2962739339","https://openalex.org/W3034429256","https://openalex.org/W3043571714","https://openalex.org/W3130689885","https://openalex.org/W3191167321","https://openalex.org/W4205991051","https://openalex.org/W4211124581","https://openalex.org/W4214690606","https://openalex.org/W4224313989","https://openalex.org/W4285197124","https://openalex.org/W4294904165","https://openalex.org/W4312199008","https://openalex.org/W4318586145","https://openalex.org/W4378804772","https://openalex.org/W4388095409","https://openalex.org/W4388240216","https://openalex.org/W4396757579","https://openalex.org/W6637373629","https://openalex.org/W6684921986","https://openalex.org/W6730956707","https://openalex.org/W6737664043","https://openalex.org/W6759579507","https://openalex.org/W6765484274","https://openalex.org/W6766978945","https://openalex.org/W6784333009","https://openalex.org/W6798686915","https://openalex.org/W6800751262","https://openalex.org/W6839353041","https://openalex.org/W6845997457","https://openalex.org/W6922480057","https://openalex.org/W6989568545"],"related_works":["https://openalex.org/W2381393187","https://openalex.org/W2332779545","https://openalex.org/W2358060160","https://openalex.org/W2035483685","https://openalex.org/W1969764885","https://openalex.org/W596947562","https://openalex.org/W2793937822","https://openalex.org/W2790817834","https://openalex.org/W2777605427","https://openalex.org/W2501983714"],"abstract_inverted_index":{"The":[0],"prevalence":[1],"of":[2,82,126,175],"the":[3,77,83,121,153,162,173,244],"pre-training":[4],"&":[5],"fine-tuning":[6,20],"paradigm":[7],"enables":[8],"machine":[9],"learning":[10,140],"models":[11,23],"to":[12,15,47,75,128,194,231,240,243],"quickly":[13],"adapt":[14],"various":[16,27],"downstream":[17],"tasks":[18],"by":[19,229,238],"pre-trained":[21],"foundation":[22],"(FMs),":[24],"greatly":[25],"facilitating":[26],"IoT":[28],"applications":[29],"that":[30,113,136,224],"rely":[31],"on":[32,212],"model":[33,79,123],"inference":[34,42,49,59,116,177,183],"in":[35,89,100],"dynamic":[36,90],"edge":[37,97],"serverless":[38,58],"environments.":[39],"Efficiently":[40],"dispatching":[41,69,148],"requests":[43,50,117],"and":[44,70,85,92,103,142,149,190,216,218,233],"configuring":[45],"instances":[46],"batch":[48,115],"can":[51,118,226],"significantly":[52],"enhance":[53],"resource":[54],"efficiency.":[55],"However,":[56],"existing":[57],"solutions":[60,158,189,198],"are":[61],"tailored":[62],"for":[63,145,196],"traditional":[64],"models,":[65],"make":[66],"coarse-grained":[67],"request":[68,147,235],"instance":[71,150,192],"configuration":[72],"decisions,":[73],"fail":[74],"exploit":[76,120],"shared":[78,122],"backbone":[80,124],"characteristics":[81],"FM":[84,127],"capture":[86],"delayed":[87],"rewards":[88],"environments,":[91],"ignore":[93],"communication":[94],"latency":[95],"between":[96],"sites,":[98],"resulting":[99],"high":[101],"costs":[102,171,228],"constraint":[104],"violations.":[105],"In":[106],"this":[107],"paper,":[108],"we":[109,208],"leverage":[110],"our":[111,167,210],"insight":[112],"fine-grained":[114,146],"effectively":[119],"feature":[125],"save":[129,227],"monetary":[130,170],"costs.":[131],"We":[132],"propose":[133],"an":[134,213],"algorithm":[135],"incorporates":[137],"deep":[138],"reinforcement":[139],"(DRL)":[141],"expert":[143,163],"intervention":[144,164],"configuration,":[151],"where":[152],"DRL":[154],"component":[155],"outputs":[156],"fractional":[157,188],"as":[159],"guidance,":[160],"while":[161,199],"module":[165,186],"integrates":[166],"insights\u2014batching":[168],"reduces":[169],"at":[172],"expense":[174],"increased":[176],"latency,":[178],"whereas":[179],"higher":[180],"configurations":[181,193],"shorten":[182],"latency.":[184],"This":[185],"rounds":[187],"adjusts":[191],"search":[195],"optimal":[197],"satisfying":[200],"constraints,":[201],"with":[202],"theoretical":[203],"guarantees":[204],"rigorously":[205],"proved.":[206],"Finally,":[207],"conducted":[209],"experiments":[211],"OpenFaas-based":[214],"platform":[215],"simulator,":[217],"extensive":[219],"trace-driven":[220],"evaluation":[221],"results":[222],"show":[223],"ExpertDRL":[225],"up":[230,239],"85.14%":[232],"improve":[234],"acceptance":[236],"ratio":[237],"26.93%,":[241],"compared":[242],"state-of-the-art":[245],"solution.":[246]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":8}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}