{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T16:48:59Z","timestamp":1781282939552,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":14,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,1,10]],"date-time":"2025-01-10T00:00:00Z","timestamp":1736467200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,1,10]]},"DOI":"10.1145\/3727353.3727398","type":"proceedings-article","created":{"date-parts":[[2025,5,27]],"date-time":"2025-05-27T16:31:13Z","timestamp":1748363473000},"page":"266-270","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["Scalability Optimization in Cloud-Based AI Inference Services: Strategies for Real-Time Load Balancing and Automated Scaling"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-7208-232X","authenticated-orcid":false,"given":"Yihong","family":"Jin","sequence":"first","affiliation":[{"name":"Electrical and Computer Engineering Department, University of Illinois at Urbana-Champaign, Champaign, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5650-4378","authenticated-orcid":false,"given":"Ze","family":"Yang","sequence":"additional","affiliation":[{"name":"Electrical and Computer Engineering Department, University of Illinois at Urbana-Champaign, Champaign, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,5,27]]},"reference":[{"key":"e_1_3_3_1_1_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3074962"},{"key":"e_1_3_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2024.110526"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-020-2939-3"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.53430\/ijsru.2024.8.2.0064"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.6440"},{"key":"e_1_3_3_1_6_2","volume-title":"IEEE","author":"Tong Jingwan","year":"2021","unstructured":"Tong, Jingwan, et al. \"A holistic auto-scaling algorithm for multi-service applications based on balanced queuing network.\" 2021 IEEE International Conference on Web Services (ICWS). IEEE, 2021."},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/3626788"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3126048"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.3390\/s24175551"},{"issue":"1","key":"e_1_3_3_1_10_2","first-page":"23","article-title":"Automated Scaling and Load Balancing in Kubernetes for High-Volume Data Processing","volume":"2","author":"Mustyala Anirudh","year":"2023","unstructured":"Mustyala, Anirudh, and Karthik Allam. \"Automated Scaling and Load Balancing in Kubernetes for High-Volume Data Processing.\" ESP Journal of Engineering and Technology Advancements 2.1 (2023): 23-38.","journal-title":"ESP Journal of Engineering and Technology Advancements"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10776-022-00568-5"},{"issue":"06","key":"e_1_3_3_1_12_2","first-page":"1366","article-title":"Server less Architecture: Optimizing Application Scalability and Cost Efficiency in Cloud Computing","volume":"1","author":"Ahmed Nisher","year":"2021","unstructured":"Ahmed, Nisher, et al. \"Server less Architecture: Optimizing Application Scalability and Cost Efficiency in Cloud Computing.\" BULLET: Jurnal Multidisiplin Ilmu 1.06 (2021): 1366-1380.","journal-title":"BULLET: Jurnal Multidisiplin Ilmu"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.comcom.2023.06.010"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1080\/07421222.2022.2063551"}],"event":{"name":"BDICN 2025: 2025 4th International Conference on Big Data, Information and Computer Network","location":"Guangzhou China","acronym":"BDICN 2025"},"container-title":["Proceedings of the 2025 4th International Conference on Big Data, Information and Computer Network"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3727353.3727398","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3727353.3727398","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:56:56Z","timestamp":1750298216000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3727353.3727398"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,10]]},"references-count":14,"alternative-id":["10.1145\/3727353.3727398","10.1145\/3727353"],"URL":"https:\/\/doi.org\/10.1145\/3727353.3727398","relation":{},"subject":[],"published":{"date-parts":[[2025,1,10]]},"assertion":[{"value":"2025-05-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}