{"id":"https://openalex.org/W4410794689","doi":"https://doi.org/10.1145/3727353.3727398","title":"Scalability Optimization in Cloud-Based AI Inference Services: Strategies for Real-Time Load Balancing and Automated Scaling","display_name":"Scalability Optimization in Cloud-Based AI Inference Services: Strategies for Real-Time Load Balancing and Automated Scaling","publication_year":2025,"publication_date":"2025-01-10","ids":{"openalex":"https://openalex.org/W4410794689","doi":"https://doi.org/10.1145/3727353.3727398"},"language":"en","primary_location":{"id":"doi:10.1145/3727353.3727398","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3727353.3727398","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3727353.3727398","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 2025 4th International Conference on Big Data, Information and Computer Network","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/10.1145/3727353.3727398","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108937456","display_name":"Yihong Jin","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yihong Jin","raw_affiliation_strings":["Electrical and Computer Engineering Department, University of Illinois at Urbana-Champaign, Champaign, USA"],"raw_orcid":"https://orcid.org/0009-0001-7208-232X","affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering Department, University of Illinois at Urbana-Champaign, Champaign, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054537423","display_name":"Ze Yang","orcid":"https://orcid.org/0009-0008-5650-4378"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ze Yang","raw_affiliation_strings":["Electrical and Computer Engineering Department, University of Illinois at Urbana-Champaign, Champaign, USA"],"raw_orcid":"https://orcid.org/0009-0008-5650-4378","affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering Department, University of Illinois at Urbana-Champaign, Champaign, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":17.3214,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.99232809,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"266","last_page":"270"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9984999895095825,"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"}},"topics":[{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9984999895095825,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9983000159263611,"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/T12127","display_name":"Software System Performance and Reliability","score":0.9772999882698059,"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/scalability","display_name":"Scalability","score":0.8557370901107788},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8115869164466858},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.8061659336090088},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7244583368301392},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.5987973213195801},{"id":"https://openalex.org/keywords/load-balancing","display_name":"Load balancing (electrical power)","score":0.527691125869751},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4554978013038635},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.34889423847198486},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.244455486536026},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2242874801158905},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1684080958366394}],"concepts":[{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.8557370901107788},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8115869164466858},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.8061659336090088},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7244583368301392},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.5987973213195801},{"id":"https://openalex.org/C138959212","wikidata":"https://www.wikidata.org/wiki/Q1806783","display_name":"Load balancing (electrical power)","level":3,"score":0.527691125869751},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4554978013038635},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.34889423847198486},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.244455486536026},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2242874801158905},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1684080958366394},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.0},{"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:10.1145/3727353.3727398","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3727353.3727398","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3727353.3727398","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 2025 4th International Conference on Big Data, Information and Computer Network","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3727353.3727398","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3727353.3727398","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3727353.3727398","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 2025 4th International Conference on Big Data, Information and Computer Network","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4410794689.pdf","grobid_xml":"https://content.openalex.org/works/W4410794689.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W3022627217","https://openalex.org/W3168560073","https://openalex.org/W3214130872","https://openalex.org/W3214315505","https://openalex.org/W4200475818","https://openalex.org/W4281697563","https://openalex.org/W4283806601","https://openalex.org/W4321392480","https://openalex.org/W4381194802","https://openalex.org/W4399361416","https://openalex.org/W4401934230","https://openalex.org/W4404486311"],"related_works":["https://openalex.org/W4244478748","https://openalex.org/W3150465815","https://openalex.org/W4223488648","https://openalex.org/W2134969820","https://openalex.org/W2251605416","https://openalex.org/W1997222214","https://openalex.org/W2560439919","https://openalex.org/W4389340727","https://openalex.org/W2802581102","https://openalex.org/W2166734474"],"abstract_inverted_index":{"With":[0],"the":[1,77,87,115,129,154,172,176],"fast":[2],"growth":[3],"of":[4,37,60,62,131],"AI":[5,39],"inference":[6,40],"services":[7],"on":[8,69],"clouds,":[9],"how":[10],"to":[11,65,75,94,117,145,171],"rapidly":[12],"scale":[13,141],"and":[14,48,71,102,162],"ensure":[15],"high":[16],"performance":[17],"under":[18],"dynamic":[19],"workloads":[20],"has":[21],"been":[22],"demanding":[23],"for":[24,34,79,136],"a":[25,31,55,137],"good":[26],"solution.":[27],"This":[28],"study":[29],"presents":[30],"novel":[32],"framework":[33],"scalability":[35],"optimization":[36,177],"cloud":[38],"services,":[41],"which":[42,58,98],"aims":[43],"at":[44],"real-time":[45],"load":[46,68,157],"balancing":[47,158],"autoscaling":[49],"strategies.":[50],"Therefore,":[51],"this":[52,84,110],"model":[53,111,155],"proposes":[54],"hybrid":[56],"system,":[57],"consists":[59],"use":[61,130],"reinforcement":[63],"learning":[64],"adaptively":[66],"distribute":[67],"servers":[70],"deep":[72],"neural":[73],"network":[74],"compute":[76],"demand":[78,148],"each":[80],"user.":[81],"By":[82],"employing":[83],"multi-layered":[85],"method,":[86],"system":[88],"can":[89],"predict":[90],"workload":[91],"variation":[92],"patterns":[93],"preemptively":[95],"allocate":[96],"resources,":[97],"optimises":[99],"resource":[100],"utilisation":[101],"minimises":[103],"latency.":[104],"The":[105],"key":[106],"aspect":[107],"is":[108,179],"that":[109,153,169],"not":[112],"only":[113],"provides":[114],"ability":[116],"recognise":[118],"failure":[119],"more":[120,139],"effectively":[121],"or":[122],"improve":[123],"overall":[124],"fault":[125],"tolerance,":[126],"but":[127],"with":[128,147],"decentralised":[132],"decision":[133],"making":[134],"allows":[135],"faster,":[138],"responsive":[140],"up":[142],"(and":[143],"down)":[144],"assist":[146],"fluctuations.":[149],"Experimental":[150],"results":[151],"show":[152],"improves":[156],"efficiency":[159],"by":[160,166],"35%":[161],"reduces":[163],"response":[164],"delay":[165],"28%,":[167],"so":[168],"compared":[170],"traditional":[173],"scaling":[174],"solution,":[175],"effect":[178],"obviously.":[180]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":5}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}