{"id":"https://openalex.org/W4405935501","doi":"https://doi.org/10.23919/cnsm62983.2024.10814523","title":"EdgeRL: Reinforcement Learning-driven Deep Learning Model Inference Optimization at Edge","display_name":"EdgeRL: Reinforcement Learning-driven Deep Learning Model Inference Optimization at Edge","publication_year":2024,"publication_date":"2024-10-28","ids":{"openalex":"https://openalex.org/W4405935501","doi":"https://doi.org/10.23919/cnsm62983.2024.10814523"},"language":"en","primary_location":{"id":"doi:10.23919/cnsm62983.2024.10814523","is_oa":false,"landing_page_url":"https://doi.org/10.23919/cnsm62983.2024.10814523","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 20th International Conference on Network and Service Management (CNSM)","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/A5074308655","display_name":"Motahare Mounesan","orcid":null},"institutions":[{"id":"https://openalex.org/I174216632","display_name":"City University of New York","ror":"https://ror.org/00453a208","country_code":"US","type":"education","lineage":["https://openalex.org/I174216632"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Motahare Mounesan","raw_affiliation_strings":["Computer Science, City University of New York,New York,NY,USA"],"affiliations":[{"raw_affiliation_string":"Computer Science, City University of New York,New York,NY,USA","institution_ids":["https://openalex.org/I174216632"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100718556","display_name":"Xiaojie Zhang","orcid":"https://orcid.org/0009-0005-6576-1876"},"institutions":[{"id":"https://openalex.org/I916048824","display_name":"Hunan First Normal University","ror":"https://ror.org/00s9d1a36","country_code":"CN","type":"education","lineage":["https://openalex.org/I916048824"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaojie Zhang","raw_affiliation_strings":["Computer Science, Hunan First Normal University,Changsha,China"],"affiliations":[{"raw_affiliation_string":"Computer Science, Hunan First Normal University,Changsha,China","institution_ids":["https://openalex.org/I916048824"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015917097","display_name":"Saptarshi Debroy","orcid":"https://orcid.org/0000-0002-4783-119X"},"institutions":[{"id":"https://openalex.org/I174216632","display_name":"City University of New York","ror":"https://ror.org/00453a208","country_code":"US","type":"education","lineage":["https://openalex.org/I174216632"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Saptarshi Debroy","raw_affiliation_strings":["Computer Science, City University of New York,New York,NY,USA"],"affiliations":[{"raw_affiliation_string":"Computer Science, City University of New York,New York,NY,USA","institution_ids":["https://openalex.org/I174216632"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5074308655"],"corresponding_institution_ids":["https://openalex.org/I174216632"],"apc_list":null,"apc_paid":null,"fwci":2.1822,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.89860092,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.7329999804496765,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.7329999804496765,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8004887104034424},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7150487303733826},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6407001614570618},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6102119088172913},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.5196329355239868},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4267013669013977},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4190191328525543}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8004887104034424},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7150487303733826},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6407001614570618},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6102119088172913},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.5196329355239868},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4267013669013977},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4190191328525543}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/cnsm62983.2024.10814523","is_oa":false,"landing_page_url":"https://doi.org/10.23919/cnsm62983.2024.10814523","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 20th International Conference on Network and Service Management (CNSM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2800687011","https://openalex.org/W3134255974","https://openalex.org/W3188107178","https://openalex.org/W4224134719","https://openalex.org/W4236099117","https://openalex.org/W4385489040","https://openalex.org/W4400234282","https://openalex.org/W4401386516","https://openalex.org/W4403332296","https://openalex.org/W6683195989","https://openalex.org/W6692846177"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W4380075502"],"abstract_inverted_index":{"Balancing":[0],"mutually":[1],"diverging":[2],"performance":[3,63],"metrics,":[4],"such":[5,40],"as,":[6],"processing":[7],"latency,":[8],"outcome":[9],"accuracy,":[10],"and":[11,60,76,97],"end":[12,90],"device":[13,91],"energy":[14,92],"consumption":[15],"is":[16],"a":[17,77],"challenging":[18],"undertaking":[19],"for":[20],"deep":[21,73],"learning":[22,74],"model":[23,75],"inference":[24,58,94,99],"in":[25,87],"ad-hoc":[26],"edge":[27],"environments.":[28],"In":[29],"this":[30],"paper,":[31],"we":[32,80],"propose":[33],"EdgeRL":[34,85],"framework":[35,86],"that":[36,52],"seeks":[37],"to":[38],"strike":[39],"balance":[41],"by":[42],"using":[43],"an":[44],"Advantage":[45],"Actor-Critic":[46],"(A2C)":[47],"Reinforcement":[48],"Learning":[49],"(RL)":[50],"approach":[51],"can":[53],"choose":[54],"optimal":[55],"run-time":[56],"DNN":[57],"parameters":[59],"aligns":[61],"the":[62,67,82],"metrics":[64],"based":[65],"on":[66],"application":[68],"requirements.":[69],"Using":[70],"real":[71],"world":[72],"hardware":[78],"testbed,":[79],"evaluate":[81],"benefits":[83],"of":[84,89],"terms":[88],"savings,":[93],"accuracy":[95],"improvement,":[96],"end-to-end":[98],"latency":[100],"reduction.":[101]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}