{"id":"https://openalex.org/W3119908787","doi":"https://doi.org/10.1145/3429880.3430093","title":"Implications of Public Cloud Resource Heterogeneity for Inference Serving","display_name":"Implications of Public Cloud Resource Heterogeneity for Inference Serving","publication_year":2020,"publication_date":"2020-12-07","ids":{"openalex":"https://openalex.org/W3119908787","doi":"https://doi.org/10.1145/3429880.3430093","mag":"3119908787"},"language":"en","primary_location":{"id":"doi:10.1145/3429880.3430093","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3429880.3430093","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 Sixth International Workshop on Serverless Computing","raw_type":"proceedings-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/A5104087483","display_name":"Jashwant Raj Gunasekaran","orcid":"https://orcid.org/0000-0001-9607-0131"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jashwant Raj Gunasekaran","raw_affiliation_strings":["The Pennsylvania State University"],"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063891736","display_name":"Cyan Subhra Mishra","orcid":"https://orcid.org/0000-0002-5532-9757"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cyan Subhra Mishra","raw_affiliation_strings":["The Pennsylvania State University"],"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015124590","display_name":"Prashanth Thinakaran","orcid":"https://orcid.org/0000-0003-0861-2055"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Prashanth Thinakaran","raw_affiliation_strings":["The Pennsylvania State University"],"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007116603","display_name":"Mahmut Kandemir","orcid":"https://orcid.org/0000-0002-9940-9951"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mahmut Taylan Kandemir","raw_affiliation_strings":["The Pennsylvania State University"],"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054027488","display_name":"Chita R. Das","orcid":"https://orcid.org/0000-0002-4746-7578"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chita R. Das","raw_affiliation_strings":["The Pennsylvania State University"],"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5104087483"],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":null,"apc_paid":null,"fwci":0.9251,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.77970056,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"7","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9994999766349792,"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":0.9994999766349792,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T12238","display_name":"Green IT and Sustainability","score":0.9894000291824341,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/provisioning","display_name":"Provisioning","score":0.8371028304100037},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.819502055644989},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.808487057685852},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.783515989780426},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.7735217809677124},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.6171841621398926},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5822915434837341},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4406859874725342},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4236093759536743},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36563318967819214},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.13728412985801697},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.09258106350898743},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08051228523254395}],"concepts":[{"id":"https://openalex.org/C172191483","wikidata":"https://www.wikidata.org/wiki/Q1071806","display_name":"Provisioning","level":2,"score":0.8371028304100037},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.819502055644989},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.808487057685852},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.783515989780426},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.7735217809677124},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.6171841621398926},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5822915434837341},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4406859874725342},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4236093759536743},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36563318967819214},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.13728412985801697},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.09258106350898743},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08051228523254395},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3429880.3430093","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3429880.3430093","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 Sixth International Workshop on Serverless Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2886050937","https://openalex.org/W2887862501","https://openalex.org/W2892876587","https://openalex.org/W2944614352","https://openalex.org/W2953038929","https://openalex.org/W2956461999","https://openalex.org/W2970239788","https://openalex.org/W3010457348","https://openalex.org/W3039010666"],"related_works":["https://openalex.org/W96612179","https://openalex.org/W2770234245","https://openalex.org/W2941957272","https://openalex.org/W2785227142","https://openalex.org/W572531444","https://openalex.org/W2945962340","https://openalex.org/W3008625068","https://openalex.org/W3128807919","https://openalex.org/W3176411177","https://openalex.org/W3035501883"],"abstract_inverted_index":{"We":[0],"are":[1,71],"witnessing":[2],"an":[3,86],"increasing":[4],"trend":[5],"towards":[6,170],"using":[7],"Machine":[8],"Learning":[9],"(ML)":[10],"based":[11,194],"prediction":[12,57],"systems,":[13,22],"spanning":[14],"across":[15],"different":[16,125],"application":[17,173,192],"domains,":[18],"including":[19],"product":[20],"recommendation":[21],"personal":[23],"assistant":[24],"devices,":[25],"facial":[26],"recognition,":[27],"etc.":[28],"These":[29],"applications":[30],"typically":[31],"have":[32],"diverse":[33],"requirements":[34,193],"in":[35,73],"terms":[36,74],"of":[37,49,56,64,75,96,120,144,182],"accuracy":[38,116],"and":[39,78,99,105,117,146,167],"response":[40],"latency,":[41],"that":[42,161],"can":[43,189],"be":[44],"satisfied":[45],"by":[46,69],"a":[47,183],"myriad":[48],"ML":[50,122],"models.":[51],"However,":[52],"the":[53,62,114,139,159,179],"deployment":[54],"cost":[55],"serving":[58,88,186],"primarily":[59],"depends":[60],"on":[61,124,195],"type":[63],"resources":[65],"being":[66],"procured,":[67],"which":[68,188],"themselves":[70],"heterogeneous":[72],"provisioning":[76],"latencies":[77],"billing":[79],"complexity.":[80],"Thus,":[81],"it":[82],"is":[83],"strenuous":[84],"for":[85,172,191],"inference":[87,185],"system":[89],"to":[90,102,150,157],"choose":[91],"from":[92,141,163],"this":[93,109,153],"confounding":[94],"array":[95],"resource":[97,128,147,168,198],"types":[98,101],"model":[100,145,166],"provide":[103],"low-latency":[104],"cost-effective":[106],"inferences.":[107],"In":[108],"work":[110,135],"we":[111,155,177],"quantitatively":[112],"characterize":[113],"cost,":[115],"latency":[118],"implications":[119,181],"hosting":[121],"inferences":[123],"public":[126,196],"cloud":[127,197],"offerings.":[129],"Our":[130],"evaluation":[131],"shows":[132],"that,":[133],"prior":[134],"does":[136],"not":[137],"solve":[138,158],"problem":[140],"both":[142,165],"dimensions":[143],"heterogeneity.":[148],"Hence,":[149],"holistically":[151],"address":[152],"problem,":[154],"need":[156],"issues":[160],"arise":[162],"combining":[164],"heterogeneity":[169],"optimizing":[171],"constraints.":[174],"Towards":[175],"this,":[176],"discuss":[178],"design":[180],"self-managed":[184],"system,":[187],"optimize":[190],"characteristics.":[199]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
