{"id":"https://openalex.org/W4391559146","doi":"https://doi.org/10.1007/s11241-024-09418-4","title":"Inference serving with end-to-end latency SLOs over dynamic edge networks","display_name":"Inference serving with end-to-end latency SLOs over dynamic edge networks","publication_year":2024,"publication_date":"2024-02-06","ids":{"openalex":"https://openalex.org/W4391559146","doi":"https://doi.org/10.1007/s11241-024-09418-4"},"language":"en","primary_location":{"id":"doi:10.1007/s11241-024-09418-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11241-024-09418-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11241-024-09418-4.pdf","source":{"id":"https://openalex.org/S183885566","display_name":"Real-Time Systems","issn_l":"0922-6443","issn":["0922-6443","1573-1383"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Real-Time Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s11241-024-09418-4.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005067086","display_name":"Vinod Nigade","orcid":"https://orcid.org/0000-0001-9020-555X"},"institutions":[{"id":"https://openalex.org/I865915315","display_name":"Vrije Universiteit Amsterdam","ror":"https://ror.org/008xxew50","country_code":"NL","type":"education","lineage":["https://openalex.org/I865915315"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Vinod Nigade","raw_affiliation_strings":["Vrije Universiteit Amsterdam, Amsterdam, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Vrije Universiteit Amsterdam, Amsterdam, The Netherlands","institution_ids":["https://openalex.org/I865915315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091147312","display_name":"Pablo Bauszat","orcid":"https://orcid.org/0009-0005-8512-3089"},"institutions":[{"id":"https://openalex.org/I865915315","display_name":"Vrije Universiteit Amsterdam","ror":"https://ror.org/008xxew50","country_code":"NL","type":"education","lineage":["https://openalex.org/I865915315"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Pablo Bauszat","raw_affiliation_strings":["Vrije Universiteit Amsterdam, Amsterdam, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Vrije Universiteit Amsterdam, Amsterdam, The Netherlands","institution_ids":["https://openalex.org/I865915315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055231636","display_name":"Henri E. Bal","orcid":"https://orcid.org/0000-0001-9827-4461"},"institutions":[{"id":"https://openalex.org/I865915315","display_name":"Vrije Universiteit Amsterdam","ror":"https://ror.org/008xxew50","country_code":"NL","type":"education","lineage":["https://openalex.org/I865915315"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Henri Bal","raw_affiliation_strings":["Vrije Universiteit Amsterdam, Amsterdam, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Vrije Universiteit Amsterdam, Amsterdam, The Netherlands","institution_ids":["https://openalex.org/I865915315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100403185","display_name":"Lin Wang","orcid":"https://orcid.org/0009-0002-9835-2719"},"institutions":[{"id":"https://openalex.org/I865915315","display_name":"Vrije Universiteit Amsterdam","ror":"https://ror.org/008xxew50","country_code":"NL","type":"education","lineage":["https://openalex.org/I865915315"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Lin Wang","raw_affiliation_strings":["Vrije Universiteit Amsterdam, Amsterdam, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Vrije Universiteit Amsterdam, Amsterdam, The Netherlands","institution_ids":["https://openalex.org/I865915315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5005067086"],"corresponding_institution_ids":["https://openalex.org/I865915315"],"apc_list":{"value":2190,"currency":"EUR","value_usd":2790},"apc_paid":{"value":2190,"currency":"EUR","value_usd":2790},"fwci":1.3901,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.82771651,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"60","issue":"2","first_page":"239","last_page":"290"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9972000122070312,"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"}},"topics":[{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9972000122070312,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9919000267982483,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9850000143051147,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.8289231061935425},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6036402583122253},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5530399680137634},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.48359793424606323},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.47546476125717163},{"id":"https://openalex.org/keywords/dead-end","display_name":"Dead end","score":0.4193054139614105},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.3810369372367859},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.25455981492996216},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1865144670009613},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.11191737651824951},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.0572625994682312}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.8289231061935425},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6036402583122253},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5530399680137634},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.48359793424606323},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.47546476125717163},{"id":"https://openalex.org/C2986709869","wikidata":"https://www.wikidata.org/wiki/Q398589","display_name":"Dead end","level":3,"score":0.4193054139614105},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.3810369372367859},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.25455981492996216},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1865144670009613},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.11191737651824951},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0572625994682312},{"id":"https://openalex.org/C2780023022","wikidata":"https://www.wikidata.org/wiki/Q1338171","display_name":"Compensation (psychology)","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1007/s11241-024-09418-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11241-024-09418-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11241-024-09418-4.pdf","source":{"id":"https://openalex.org/S183885566","display_name":"Real-Time Systems","issn_l":"0922-6443","issn":["0922-6443","1573-1383"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Real-Time Systems","raw_type":"journal-article"},{"id":"pmh:oai:research.vu.nl:publications/80db3863-9129-453f-aa1d-f2e85a22f9f3","is_oa":true,"landing_page_url":"https://research.vu.nl/en/publications/80db3863-9129-453f-aa1d-f2e85a22f9f3","pdf_url":null,"source":{"id":"https://openalex.org/S4306401107","display_name":"VU Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I865915315","host_organization_name":"Vrije Universiteit Amsterdam","host_organization_lineage":["https://openalex.org/I865915315"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nigade, V, Bauszat, P, Bal, H & Wang, L 2024, 'Inference serving with end-to-end latency SLOs over dynamic edge networks', Real-time Systems, vol. 60, no. 2, pp. 239-290. https://doi.org/10.1007/s11241-024-09418-4","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:research.vu.nl:openaire/80db3863-9129-453f-aa1d-f2e85a22f9f3","is_oa":true,"landing_page_url":"https://hdl.handle.net/1871.1/80db3863-9129-453f-aa1d-f2e85a22f9f3","pdf_url":null,"source":{"id":"https://openalex.org/S4306401107","display_name":"VU Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I865915315","host_organization_name":"Vrije Universiteit Amsterdam","host_organization_lineage":["https://openalex.org/I865915315"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Nigade, V, Bauszat, P, Bal, H & Wang, L 2024, 'Inference serving with end-to-end latency SLOs over dynamic edge networks', Real-time Systems, vol. 60, no. 2, pp. 239-290. https://doi.org/10.1007/s11241-024-09418-4","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.1007/s11241-024-09418-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11241-024-09418-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11241-024-09418-4.pdf","source":{"id":"https://openalex.org/S183885566","display_name":"Real-Time Systems","issn_l":"0922-6443","issn":["0922-6443","1573-1383"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Real-Time Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1250097850","display_name":null,"funder_award_id":"P16-25","funder_id":"https://openalex.org/F4320321800","funder_display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek"},{"id":"https://openalex.org/G2737184226","display_name":null,"funder_award_id":"P16-25","funder_id":"https://openalex.org/F4320334893","funder_display_name":"Stichting voor de Technische Wetenschappen"},{"id":"https://openalex.org/G6009445997","display_name":null,"funder_award_id":"unknown","funder_id":"https://openalex.org/F4320321800","funder_display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek"},{"id":"https://openalex.org/G629491556","display_name":null,"funder_award_id":"(NWO)","funder_id":"https://openalex.org/F4320321800","funder_display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek"}],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320321800","display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","ror":"https://ror.org/04jsz6e67"},{"id":"https://openalex.org/F4320323384","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24"},{"id":"https://openalex.org/F4320334893","display_name":"Stichting voor de Technische Wetenschappen","ror":"https://ror.org/057tq3593"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4391559146.pdf"},"referenced_works_count":52,"referenced_works":["https://openalex.org/W1676314349","https://openalex.org/W1861492603","https://openalex.org/W1982647060","https://openalex.org/W2129636357","https://openalex.org/W2194775991","https://openalex.org/W2507174453","https://openalex.org/W2599379624","https://openalex.org/W2606492274","https://openalex.org/W2678047256","https://openalex.org/W2766304518","https://openalex.org/W2783538964","https://openalex.org/W2792220137","https://openalex.org/W2798170643","https://openalex.org/W2962677625","https://openalex.org/W2963273111","https://openalex.org/W2963918968","https://openalex.org/W2964108773","https://openalex.org/W2964259004","https://openalex.org/W2964325192","https://openalex.org/W2964350391","https://openalex.org/W2965289829","https://openalex.org/W2974412363","https://openalex.org/W2994749257","https://openalex.org/W2997214666","https://openalex.org/W3009922718","https://openalex.org/W3030408490","https://openalex.org/W3034292689","https://openalex.org/W3034544214","https://openalex.org/W3035192036","https://openalex.org/W3045045900","https://openalex.org/W3046754651","https://openalex.org/W3047392327","https://openalex.org/W3047681172","https://openalex.org/W3092462694","https://openalex.org/W3096609285","https://openalex.org/W3097904259","https://openalex.org/W3102767875","https://openalex.org/W3134255974","https://openalex.org/W3176780274","https://openalex.org/W3179122174","https://openalex.org/W3181120673","https://openalex.org/W3203990902","https://openalex.org/W3204647170","https://openalex.org/W3210617645","https://openalex.org/W4200337351","https://openalex.org/W4206375371","https://openalex.org/W4283727273","https://openalex.org/W4288346093","https://openalex.org/W4295886237","https://openalex.org/W4297792979","https://openalex.org/W4312199008","https://openalex.org/W6602254124"],"related_works":["https://openalex.org/W3008625068","https://openalex.org/W3128807919","https://openalex.org/W3176411177","https://openalex.org/W3179968364","https://openalex.org/W3016188207","https://openalex.org/W4293268064","https://openalex.org/W3035501883","https://openalex.org/W2151749779","https://openalex.org/W2218833963","https://openalex.org/W2964709658"],"abstract_inverted_index":{"Abstract":[0],"While":[1],"high":[2,190],"accuracy":[3,85],"is":[4,18],"of":[5],"paramount":[6],"importance":[7],"for":[8,59,101],"deep":[9,76],"learning":[10],"(DL)":[11],"inference,":[12],"serving":[13,53],"inference":[14,52,61,140],"requests":[15],"on":[16,165],"time":[17],"equally":[19],"critical":[20],"but":[21],"has":[22,31],"not":[23],"been":[24],"carefully":[25],"studied":[26],"especially":[27],"when":[28],"the":[29,41,68,99,138,185],"request":[30],"to":[32,81,121],"be":[33],"served":[34],"over":[35],"a":[36,90,166],"dynamic":[37,145],"wireless":[38],"network":[39,69,78,115,174],"at":[40,128,183],"edge.":[42],"In":[43],"this":[44],"paper,":[45],"we":[46,132],"propose":[47,118],"Jellyfish\u2014a":[48],"novel":[49],"edge":[50],"DL":[51],"system":[54],"that":[55,93,131,149,177],"achieves":[56],"soft":[57],"guarantees":[58],"end-to-end":[60],"latency":[62,134,181],"service-level":[63],"objectives":[64],"(SLO).":[65],"Jellyfish":[66,88,178],"handles":[67],"variability":[70],"by":[71],"utilizing":[72],"both":[73],"data":[74,102],"and":[75,86,103,108,125,154,169,172],"neural":[77],"(DNN)":[79],"adaptation":[80,96],"conduct":[82],"tradeoffs":[83],"between":[84],"latency.":[87],"features":[89],"new":[91],"design":[92],"enables":[94],"collective":[95],"policies":[97],"where":[98],"decisions":[100],"DNN":[104],"adaptations":[105],"are":[106],"aligned":[107],"coordinated":[109],"among":[110],"multiple":[111,151],"users":[112,124],"with":[113],"varying":[114],"conditions.":[116],"We":[117,142],"efficient":[119],"algorithms":[120],"continuously":[122],"map":[123],"adapt":[126],"DNNs":[127,148],"runtime,":[129],"so":[130],"fulfill":[133],"SLOs":[135,182],"while":[136,188],"maximizing":[137],"overall":[139],"accuracy.":[141,191],"further":[143],"investigate":[144],"DNNs,":[146],"i.e.,":[147],"encompass":[150],"architecture":[152],"variants,":[153],"demonstrate":[155],"their":[156],"potential":[157],"benefit":[158],"through":[159],"preliminary":[160],"experiments.":[161],"Our":[162],"experiments":[163],"based":[164],"prototype":[167],"implementation":[168],"real-world":[170],"WiFi":[171],"LTE":[173],"traces":[175],"show":[176],"can":[179],"meet":[180],"around":[184],"99th":[186],"percentile":[187],"maintaining":[189]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-29T08:15:47.926485","created_date":"2025-10-10T00:00:00"}