{"id":"https://openalex.org/W4410987935","doi":"https://doi.org/10.1109/percom64205.2025.00032","title":"OctopInf: Workload-Aware Inference Serving for Edge Video Analytics","display_name":"OctopInf: Workload-Aware Inference Serving for Edge Video Analytics","publication_year":2025,"publication_date":"2025-03-17","ids":{"openalex":"https://openalex.org/W4410987935","doi":"https://doi.org/10.1109/percom64205.2025.00032"},"language":"en","primary_location":{"id":"doi:10.1109/percom64205.2025.00032","is_oa":false,"landing_page_url":"https://doi.org/10.1109/percom64205.2025.00032","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Pervasive Computing and Communications (PerCom)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101924638","display_name":"Thanh-Tung Nguyen","orcid":"https://orcid.org/0000-0002-8186-2600"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Thanh-Tung Nguyen","raw_affiliation_strings":["KAIST,School of Computing,Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST,School of Computing,Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011894742","display_name":"Lucas Liebe","orcid":"https://orcid.org/0009-0004-9252-4764"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Lucas Liebe","raw_affiliation_strings":["KAIST,School of Computing,Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST,School of Computing,Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104189427","display_name":"Nhat-Quang Tau","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Nhat-Quang Tau","raw_affiliation_strings":["KAIST,School of Computing,Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST,School of Computing,Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100625838","display_name":"Yuheng Wu","orcid":"https://orcid.org/0000-0001-8473-0999"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yuheng Wu","raw_affiliation_strings":["KAIST,School of Computing,Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST,School of Computing,Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jinghan Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jinghan Cheng","raw_affiliation_strings":["KAIST,School of Computing,Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST,School of Computing,Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046640082","display_name":"Dongman Lee","orcid":"https://orcid.org/0000-0001-5923-6227"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Dongman Lee","raw_affiliation_strings":["KAIST,School of Computing,Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST,School of Computing,Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":5.9441,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.96162989,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"128","last_page":"137"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9671000242233276,"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":0.9671000242233276,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9628999829292297,"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/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9605000019073486,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8091466426849365},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.7829796075820923},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.7560927867889404},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6122188568115234},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.5579283237457275},{"id":"https://openalex.org/keywords/visual-analytics","display_name":"Visual analytics","score":0.4785221815109253},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.33259594440460205},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2483862042427063},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.17519041895866394},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.08079922199249268}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8091466426849365},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.7829796075820923},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.7560927867889404},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6122188568115234},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.5579283237457275},{"id":"https://openalex.org/C59732488","wikidata":"https://www.wikidata.org/wiki/Q2528440","display_name":"Visual analytics","level":3,"score":0.4785221815109253},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.33259594440460205},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2483862042427063},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.17519041895866394},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.08079922199249268}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/percom64205.2025.00032","is_oa":false,"landing_page_url":"https://doi.org/10.1109/percom64205.2025.00032","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Pervasive Computing and Communications (PerCom)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W2086402015","https://openalex.org/W2098926188","https://openalex.org/W2752236330","https://openalex.org/W2872933037","https://openalex.org/W2887117815","https://openalex.org/W2896225285","https://openalex.org/W2908372320","https://openalex.org/W2982157693","https://openalex.org/W3017194848","https://openalex.org/W3039856203","https://openalex.org/W3046256272","https://openalex.org/W3047364469","https://openalex.org/W3047589404","https://openalex.org/W3095488153","https://openalex.org/W3106564420","https://openalex.org/W3109296687","https://openalex.org/W3113927661","https://openalex.org/W3162157550","https://openalex.org/W3169749941","https://openalex.org/W3217119770","https://openalex.org/W4207032740","https://openalex.org/W4281608480","https://openalex.org/W4289821779","https://openalex.org/W4312199008","https://openalex.org/W4361732920","https://openalex.org/W4366250533","https://openalex.org/W4381746742","https://openalex.org/W4386707601","https://openalex.org/W4392968216","https://openalex.org/W4394711787","https://openalex.org/W4394711815","https://openalex.org/W4397026267","https://openalex.org/W6735636592","https://openalex.org/W6779103662","https://openalex.org/W6802095294"],"related_works":["https://openalex.org/W2000785801","https://openalex.org/W986318368","https://openalex.org/W2384410913","https://openalex.org/W2352878646","https://openalex.org/W2004734601","https://openalex.org/W2287264064","https://openalex.org/W2130149817","https://openalex.org/W2990194547","https://openalex.org/W1480123525","https://openalex.org/W2186032312"],"abstract_inverted_index":{"Edge":[0,40],"Video":[1],"Analytics":[2],"(EVA)":[3],"has":[4],"become":[5],"a":[6,70,108,132],"major":[7],"application":[8],"of":[9,19,87,116,138,147],"pervasive":[10],"computing,":[11],"enabling":[12],"real-time":[13,80],"visual":[14],"processing.":[15],"EVA":[16,49,169],"pipelines,":[17],"composed":[18],"deep":[20],"neural":[21],"networks":[22],"(DNNs),":[23],"typically":[24],"demand":[25],"efficient":[26],"inference":[27,75,117,170],"serving":[28,76],"under":[29],"stringent":[30],"latency":[31],"requirements,":[32],"which":[33],"is":[34,176],"challenging":[35,160],"due":[36,55],"to":[37,56,149,152],"the":[38,62,84,114,136,153],"dynamic":[39,88],"environments":[41,90],"(e.g.,":[42,58],"workload":[43,98],"variability":[44],"and":[45,73,97,103,123,155,175],"network":[46],"instability).":[47],"Moreover,":[48],"pipelines":[50],"face":[51],"significant":[52],"resource":[53,57,93],"contention":[54],"GPU)":[59],"constraints":[60],"at":[61,178],"Edge.":[63],"In":[64],"this":[65],"paper,":[66],"we":[67,106],"introduce":[68],"OctopInf,":[69],"novel":[71],"resource-efficient":[72],"workload-aware":[74],"system":[77],"designed":[78],"for":[79,166],"EVA.":[81],"OctopInf":[82,162],"tackles":[83],"unique":[85],"challenges":[86],"edge":[89,101],"through":[91],"fine-grained":[92],"allocation,":[94],"adaptive":[95],"batching,":[96],"balancing":[99],"between":[100],"devices":[102],"servers.":[104],"Furthermore,":[105],"propose":[107],"spatiotemporal":[109],"scheduling":[110],"algorithm":[111],"that":[112],"optimizes":[113],"co-location":[115],"tasks":[118],"on":[119,131],"GPUs,":[120],"improving":[121],"performance":[122],"ensuring":[124],"service-level":[125],"objectives":[126],"(SLOs)":[127],"compliance.":[128],"Extensive":[129],"evaluations":[130],"real-world":[133],"testbed":[134],"demonstrate":[135],"effectiveness":[137],"our":[139],"approach.":[140],"It":[141],"achieves":[142],"an":[143],"effective":[144],"throughput":[145],"increase":[146],"up":[148],"10\u00d7":[150],"compared":[151],"baselines":[154],"shows":[156],"better":[157],"robustness":[158],"in":[159],"scenarios.":[161],"can":[163],"be":[164],"used":[165],"any":[167],"DNN-based":[168],"task":[171],"with":[172],"minimal":[173],"adaptation":[174],"available":[177],"https://github.com/tungngreen/PipelineScheduler.":[179]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}