{"id":"https://openalex.org/W4372271902","doi":"https://doi.org/10.1145/3583120.3586953","title":"POS: An Operator Scheduling Framework for Multi-model Inference on Edge Intelligent Computing","display_name":"POS: An Operator Scheduling Framework for Multi-model Inference on Edge Intelligent Computing","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372271902","doi":"https://doi.org/10.1145/3583120.3586953"},"language":"en","primary_location":{"id":"doi:10.1145/3583120.3586953","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3583120.3586953","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 22nd International Conference on Information Processing in Sensor Networks","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/A5014588008","display_name":"Ziyang Zhang","orcid":"https://orcid.org/0000-0003-2539-8257"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyang Zhang","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, China, China"],"raw_orcid":"https://orcid.org/0000-0003-2539-8257","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Huan Li","orcid":"https://orcid.org/0009-0009-7350-5361"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huan Li","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen, China, China"],"raw_orcid":"https://orcid.org/0009-0009-7350-5361","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen, China, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007442135","display_name":"Yang Zhao","orcid":"https://orcid.org/0000-0003-2080-1270"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Zhao","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen, China, China"],"raw_orcid":"https://orcid.org/0000-0003-2080-1270","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen, China, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065564945","display_name":"Changyao Lin","orcid":"https://orcid.org/0000-0001-6805-2649"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changyao Lin","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, China, China"],"raw_orcid":"https://orcid.org/0000-0001-6805-2649","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100454005","display_name":"Jie Liu","orcid":"https://orcid.org/0000-0001-6209-6886"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Liu","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen, China, China"],"raw_orcid":"https://orcid.org/0000-0001-6209-6886","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen, China, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"1"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"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/T13553","display_name":"Age of Information Optimization","score":0.9986000061035156,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9922000169754028,"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":0.819801926612854},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.66623854637146},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5848321318626404},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5622814297676086},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43518081307411194},{"id":"https://openalex.org/keywords/inference-engine","display_name":"Inference engine","score":0.42907002568244934},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.423332542181015},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3559300899505615},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.20354142785072327},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.17200782895088196}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.819801926612854},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.66623854637146},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5848321318626404},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5622814297676086},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43518081307411194},{"id":"https://openalex.org/C46743427","wikidata":"https://www.wikidata.org/wiki/Q1341685","display_name":"Inference engine","level":3,"score":0.42907002568244934},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.423332542181015},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3559300899505615},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.20354142785072327},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.17200782895088196},{"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:10.1145/3583120.3586953","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3583120.3586953","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 22nd International Conference on Information Processing in Sensor Networks","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":28,"referenced_works":["https://openalex.org/W2150066425","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2309415944","https://openalex.org/W2416799949","https://openalex.org/W2804032941","https://openalex.org/W2960833983","https://openalex.org/W2982083293","https://openalex.org/W3034107927","https://openalex.org/W3035582633","https://openalex.org/W3046914828","https://openalex.org/W3049640275","https://openalex.org/W3087982600","https://openalex.org/W3098625345","https://openalex.org/W3102767875","https://openalex.org/W3112101075","https://openalex.org/W3128271665","https://openalex.org/W3130676345","https://openalex.org/W3136585513","https://openalex.org/W3137350414","https://openalex.org/W3144271226","https://openalex.org/W3167214600","https://openalex.org/W3168146412","https://openalex.org/W3173721678","https://openalex.org/W3174529902","https://openalex.org/W3189931457","https://openalex.org/W6785429063","https://openalex.org/W6893864439"],"related_works":["https://openalex.org/W2097707447","https://openalex.org/W2057057690","https://openalex.org/W2368184788","https://openalex.org/W2358964818","https://openalex.org/W2359535128","https://openalex.org/W2381332051","https://openalex.org/W2149404148","https://openalex.org/W2321443665","https://openalex.org/W2375699995","https://openalex.org/W2043719711"],"abstract_inverted_index":{"Edge":[0],"intelligent":[1],"applications,":[2],"such":[3],"as":[4],"autonomous":[5],"driving":[6],"usually":[7],"deploy":[8],"multiple":[9],"inference":[10,40,70,79,130,146],"models":[11],"on":[12,66,72,80,152,163],"resource-constrained":[13,82],"edge":[14,74,83],"devices":[15],"to":[16,37,46,104,140,166],"execute":[17],"a":[18,68,81,91,107],"diverse":[19],"range":[20],"of":[21,27,53,58],"concurrent":[22],"tasks,":[23],"given":[24],"large":[25],"amounts":[26],"input":[28],"data.":[29],"One":[30],"challenge":[31],"is":[32,106],"that":[33,96,125],"these":[34],"tasks":[35],"need":[36],"produce":[38],"reliable":[39],"results":[41],"simultaneously":[42],"with":[43,149],"millisecond-level":[44],"latency":[45],"achieve":[47],"real-time":[48],"performance":[49],"and":[50,136,178],"high":[51],"quality":[52],"service":[54],"(QoS).":[55],"However,":[56],"most":[57],"the":[59,158],"existing":[60],"deep":[61],"learning":[62],"frameworks":[63],"only":[64],"focus":[65],"optimizing":[67],"single":[69],"model":[71],"an":[73,118],"device.":[75],"To":[76],"accelerate":[77],"multi-model":[78],"device,":[84],"in":[85],"this":[86],"paper":[87],"we":[88],"propose":[89],"POS,":[90],"novel":[92],"operator-level":[93],"scheduling":[94,100,113,159],"framework":[95],"combines":[97],"four":[98],"operator":[99,112],"strategies.":[101],"The":[102],"key":[103],"POS":[105,126],"maximum":[108],"entropy":[109],"reinforcement":[110],"learning-based":[111],"algorithm":[114],"MEOS,":[115],"which":[116],"generates":[117],"optimal":[119],"schedule":[120],"automatically.":[121],"Extensive":[122],"experiments":[123],"show":[124],"outperforms":[127],"five":[128,167],"state-of-the-art":[129],"frameworks:":[131],"TensorFlow,":[132],"PyTorch,":[133],"TensorRT,":[134],"TVM,":[135],"IOS,":[137],"by":[138,161],"up":[139],"1.2":[141],"\u00d7":[142,145],"\u223c":[143],"3.9":[144],"speedup":[147],"consistently,":[148],"40%":[150],"improvement":[151],"GPU":[153],"utilization.":[154],"Meanwhile,":[155],"MEOS":[156],"reduces":[157],"overhead":[160],"37%":[162],"average,":[164],"compared":[165],"baseline":[168],"methods":[169],"including":[170],"sequential":[171],"execution,":[172],"dynamic":[173],"programming,":[174],"greedy":[175],"scheduling,":[176],"actor-critic,":[177],"coordinate":[179],"descent":[180],"search":[181],"algorithms.":[182]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}