{"id":"https://openalex.org/W4416956281","doi":"https://doi.org/10.1145/3769102.3774241","title":"How Heavy is the Edge? Resource Utilization of Edge Generative AI on Distributed AI Infrastructure","display_name":"How Heavy is the Edge? Resource Utilization of Edge Generative AI on Distributed AI Infrastructure","publication_year":2025,"publication_date":"2025-12-03","ids":{"openalex":"https://openalex.org/W4416956281","doi":"https://doi.org/10.1145/3769102.3774241"},"language":null,"primary_location":{"id":"doi:10.1145/3769102.3774241","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3769102.3774241","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3769102.3774241","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Tenth ACM/IEEE Symposium on Edge Computing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3769102.3774241","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108954018","display_name":"Liang Wu","orcid":"https://orcid.org/0009-0009-1546-8144"},"institutions":[{"id":"https://openalex.org/I43579087","display_name":"University of Wisconsin\u2013Milwaukee","ror":"https://ror.org/031q21x57","country_code":"US","type":"education","lineage":["https://openalex.org/I43579087"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liang Wu","raw_affiliation_strings":["University of Wisconsin-Milwaukee, Milwaukee, WI, USA"],"raw_orcid":"https://orcid.org/0009-0009-1546-8144","affiliations":[{"raw_affiliation_string":"University of Wisconsin-Milwaukee, Milwaukee, WI, USA","institution_ids":["https://openalex.org/I43579087"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100360185","display_name":"Zhen Zeng","orcid":"https://orcid.org/0000-0002-7877-292X"},"institutions":[{"id":"https://openalex.org/I43579087","display_name":"University of Wisconsin\u2013Milwaukee","ror":"https://ror.org/031q21x57","country_code":"US","type":"education","lineage":["https://openalex.org/I43579087"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhen Zeng","raw_affiliation_strings":["University of Wisconsin-Milwaukee, Milwaukee, WI, USA"],"raw_orcid":"https://orcid.org/0000-0002-7877-292X","affiliations":[{"raw_affiliation_string":"University of Wisconsin-Milwaukee, Milwaukee, WI, USA","institution_ids":["https://openalex.org/I43579087"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057478629","display_name":"Zhongshu Gu","orcid":"https://orcid.org/0000-0001-9624-2669"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhongshu Gu","raw_affiliation_strings":["IBM Research, Yorktown Heights, NY, USA"],"raw_orcid":"https://orcid.org/0000-0001-9624-2669","affiliations":[{"raw_affiliation_string":"IBM Research, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056965264","display_name":"Pengxia Wu","orcid":"https://orcid.org/0000-0002-0826-1614"},"institutions":[{"id":"https://openalex.org/I57053284","display_name":"Rockwell Automation (United States)","ror":"https://ror.org/01sx1pm50","country_code":"US","type":"company","lineage":["https://openalex.org/I57053284"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pengxia Wu","raw_affiliation_strings":["Rockwell Automation, Milwaukee, WI, USA"],"raw_orcid":"https://orcid.org/0000-0002-0826-1614","affiliations":[{"raw_affiliation_string":"Rockwell Automation, Milwaukee, WI, USA","institution_ids":["https://openalex.org/I57053284"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.8903999924659729,"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":0.8903999924659729,"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.024299999698996544,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.011800000444054604,"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/cloud-computing","display_name":"Cloud computing","score":0.7005000114440918},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.6735000014305115},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.6635000109672546},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.49790000915527344},{"id":"https://openalex.org/keywords/edge-computing","display_name":"Edge computing","score":0.482699990272522},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4449999928474426},{"id":"https://openalex.org/keywords/edge-device","display_name":"Edge device","score":0.4259999990463257}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7087000012397766},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.7005000114440918},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.6735000014305115},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.6635000109672546},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.49790000915527344},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.482699990272522},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4449999928474426},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4438000023365021},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.4259999990463257},{"id":"https://openalex.org/C157170001","wikidata":"https://www.wikidata.org/wiki/Q4781507","display_name":"Applications of artificial intelligence","level":2,"score":0.385699987411499},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38109999895095825},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.32409998774528503},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.322299987077713},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3188000023365021},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3172000050544739},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.31279999017715454},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.3018999993801117},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.257999986410141}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3769102.3774241","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3769102.3774241","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3769102.3774241","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Tenth ACM/IEEE Symposium on Edge Computing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3769102.3774241","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3769102.3774241","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3769102.3774241","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Tenth ACM/IEEE Symposium on Edge Computing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416956281.pdf"},"referenced_works_count":2,"referenced_works":["https://openalex.org/W4322761281","https://openalex.org/W4410453764"],"related_works":[],"abstract_inverted_index":{"Distributed":[0],"AI":[1,16,36,44,101],"infrastructures":[2,21],"are":[3],"extensively":[4],"employed":[5],"in":[6],"cloud":[7],"industry":[8],"settings":[9],"to":[10,22,103],"accommodate":[11],"the":[12,23,49,99],"growing":[13],"demands":[14],"of":[15,53,66],"services.":[17],"However,":[18],"extending":[19],"such":[20],"edge":[24,35,54,71,106],"remains":[25],"under":[26],"exploration.":[27],"This":[28,46],"study":[29],"addresses":[30],"this":[31],"challenge":[32],"by":[33],"enabling":[34],"with":[37,92],"Ray,":[38,93],"a":[39,62,87],"widely":[40],"adopted":[41],"open-source":[42],"distributed":[43,100],"infrastructure.":[45],"work":[47],"uncovers":[48],"resource":[50],"utilization":[51],"patterns":[52],"GenAI":[55,68,80],"across":[56],"deployment":[57],"and":[58,78,84],"inference":[59],"stages,":[60],"providing":[61],"more":[63],"comprehensive":[64],"view":[65],"how":[67],"workloads":[69],"affect":[70],"resources.":[72],"Our":[73],"findings,":[74],"based":[75],"on":[76,86,97],"deploying":[77],"running":[79],"models":[81],"(GPT-2,":[82],"TinyLlama,":[83],"Llama-1B)":[85],"three-Raspberry":[88],"Pi":[89],"5":[90],"cluster":[91],"reveal":[94],"valuable":[95],"insights":[96],"leveraging":[98],"infrastructure":[102],"support":[104],"resource-intensive":[105],"intelligence.":[107]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-12-03T00:00:00"}