{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T11:45:38Z","timestamp":1767181538541,"version":"3.48.0"},"publisher-location":"New York, NY, USA","reference-count":37,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1145\/3773274.3774258","type":"proceedings-article","created":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T11:40:28Z","timestamp":1767181228000},"page":"1-9","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["A Hybrid Forecasting and Reinforcement Learning Approach for Latency-Constrained Scaling of Generative AI Systems"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-1439-5693","authenticated-orcid":false,"given":"Yue","family":"Peng","sequence":"first","affiliation":[{"name":"Faculty of Engineering and Information Technology, The University of Melbourne, Melbourne, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5998-222X","authenticated-orcid":false,"given":"Richard","family":"Sinnott","sequence":"additional","affiliation":[{"name":"Faculty of Engineering and Information Technology, The University of Melbourne, Melbourne, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,12,31]]},"reference":[{"key":"e_1_3_3_2_2_2","doi-asserted-by":"publisher","unstructured":"Siddharth Agarwal Maria\u00a0A. Rodriguez and Rajkumar Buyya. 2024. A Deep Recurrent-Reinforcement Learning Method for Intelligent AutoScaling of Serverless Functions. IEEE Transactions on Services Computing 17 5 (Sept. 2024) 1899\u20131910. 10.1109\/tsc.2024.3387661","DOI":"10.1109\/tsc.2024.3387661"},{"key":"e_1_3_3_2_3_2","unstructured":"Alibaba Group. 2024. Alibaba Cluster Data. https:\/\/github.com\/alibaba\/clusterdata Accessed: 2025-07-13."},{"key":"e_1_3_3_2_4_2","unstructured":"Aliyun Container Service. 2024. gpushare-scheduler-extender. https:\/\/github.com\/AliyunContainerService\/gpushare-scheduler-extender Accessed: 2025-07-13."},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"publisher","unstructured":"Haoyu Bai Minxian Xu Kejiang Ye Rajkumar Buyya and Chengzhong Xu. 2024. DRPC: Distributed Reinforcement Learning Approach for Scalable Resource Provisioning in Container-Based Clusters. IEEE Transactions on Services Computing 17 6 (2024) 3473\u20133484. 10.1109\/TSC.2024.3433388","DOI":"10.1109\/TSC.2024.3433388"},{"key":"e_1_3_3_2_6_2","unstructured":"Google Cloud. [n. d.]. Best practices for autoscaling large language model (LLM) inference workloads with GPUs on Google Kubernetes Engine (GKE). https:\/\/cloud.google.com\/kubernetes-engine\/docs\/best-practices\/machine-learning\/inference\/autoscaling#queue-size"},{"key":"e_1_3_3_2_7_2","first-page":"67","volume-title":"ICAS 2011, The Seventh International Conference on Autonomic and Autonomous Systems","author":"Dutreilh Xavier","year":"2011","unstructured":"Xavier Dutreilh, Sergey Kirgizov, Olga Melekhova, Jacques Malenfant, Nicolas Rivierre, and Isis Truck. 2011. Using reinforcement learning for autonomic resource allocation in clouds: towards a fully automated workflow. In ICAS 2011, The Seventh International Conference on Autonomic and Autonomous Systems. 67\u201374."},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"crossref","unstructured":"Jerome\u00a0H Friedman. 2001. Greedy function approximation: a gradient boosting machine. Annals of statistics (2001) 1189\u20131232.","DOI":"10.1214\/aos\/1013203451"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/BDCloud.2018.00077"},{"key":"e_1_3_3_2_10_2","unstructured":"Matthew Hausknecht and Peter Stone. 2017. Deep Recurrent Q-Learning for Partially Observable MDPs. arxiv:https:\/\/arXiv.org\/abs\/1507.06527\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/1507.06527"},{"key":"e_1_3_3_2_11_2","unstructured":"Peter Henderson Riashat Islam Philip Bachman Joelle Pineau Doina Precup and David Meger. 2017. Deep Reinforcement Learning that Matters. CoRR abs\/1709.06560 (2017). arXiv:https:\/\/arXiv.org\/abs\/1709.06560http:\/\/arxiv.org\/abs\/1709.06560"},{"key":"e_1_3_3_2_12_2","unstructured":"Julien Herzen Francesco L\u00c3\u00a4ssig Samuele\u00a0Giuliano Piazzetta Thomas Neuer L\u00c3\u00a9o Tafti Guillaume Raille Tomas\u00a0Van Pottelbergh Marek Pasieka Andrzej Skrodzki Nicolas Huguenin Maxime Dumonal Jan Ko\u00c5\u203acisz Dennis Bader Fr\u00c3\u00a9d\u00c3\u00a9rick Gusset Mounir Benheddi Camila Williamson Michal Kosinski Matej Petrik and Ga\u00c3\u00abl Grosch. 2022. Darts: User-Friendly Modern Machine Learning for Time Series. Journal of Machine Learning Research 23 124 (2022) 1\u20136. http:\/\/jmlr.org\/papers\/v23\/21-1177.html"},{"key":"e_1_3_3_2_13_2","unstructured":"Benjamin Lefaudeux Francisco Massa Diana Liskovich Wenhan Xiong Vittorio Caggiano Sean Naren Min Xu Jieru Hu Marta Tintore Susan Zhang Patrick Labatut Daniel Haziza Luca Wehrstedt Jeremy Reizenstein and Grigory Sizov. 2022. xFormers: A modular and hackable Transformer modelling library. https:\/\/github.com\/facebookresearch\/xformers."},{"key":"e_1_3_3_2_14_2","unstructured":"Zichang Liu Aditya Desai Fangshuo Liao Weitao Wang Victor Xie Zhaozhuo Xu Anastasios Kyrillidis and Anshumali Shrivastava. 2023. Scissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Time. arxiv:https:\/\/arXiv.org\/abs\/2305.17118\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2305.17118"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"crossref","unstructured":"Tania Lorido-Botran Jose Miguel-Alonso and Jose\u00a0A Lozano. 2014. A review of auto-scaling techniques for elastic applications in cloud environments. Journal of grid computing 12 (2014) 559\u2013592.","DOI":"10.1007\/s10723-014-9314-7"},{"key":"e_1_3_3_2_16_2","first-page":"561","volume-title":"13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18)","author":"Moritz Philipp","year":"2018","unstructured":"Philipp Moritz, Robert Nishihara, Stephanie Wang, Alexey Tumanov, Richard Liaw, Eric Liang, Melih Elibol, Zongheng Yang, William Paul, Michael\u00a0I. Jordan, and Ion Stoica. 2018. Ray: A Distributed Framework for Emerging AI Applications. In 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18). USENIX Association, Carlsbad, CA, 561\u2013577. https:\/\/www.usenix.org\/conference\/osdi18\/presentation\/moritz"},{"key":"e_1_3_3_2_17_2","volume-title":"International Conference on Learning Representations","author":"Nie Yuqi","year":"2023","unstructured":"Yuqi Nie, Nam H.\u00a0Nguyen, Phanwadee Sinthong, and Jayant Kalagnanam. 2023. A Time Series is Worth 64 Words: Long-term Forecasting with Transformers. In International Conference on Learning Representations."},{"key":"e_1_3_3_2_18_2","volume-title":"k8s-device-plugin","year":"2024","unstructured":"NVIDIA. 2024. k8s-device-plugin. https:\/\/github.com\/NVIDIA\/k8s-device-plugin Accessed: 2025-07-13."},{"key":"e_1_3_3_2_19_2","unstructured":"NVIDIA. 2024. Multi-Process Service (MPS) Documentation. https:\/\/docs.nvidia.com\/deploy\/mps\/index.html Accessed: 2025-07-13."},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"publisher","unstructured":"Zhicheng Pan Yihang Wang Yingying Zhang Sean\u00a0Bin Yang Yunyao Cheng Peng Chen Chenjuan Guo Qingsong Wen Xiduo Tian Yunliang Dou Zhiqiang Zhou Chengcheng Yang Aoying Zhou and Bin Yang. 2023. MagicScaler: Uncertainty-Aware Predictive Autoscaling. Proc. VLDB Endow. 16 12 (Aug. 2023) 3808\u20133821. 10.14778\/3611540.3611566","DOI":"10.14778\/3611540.3611566"},{"key":"e_1_3_3_2_21_2","unstructured":"Reiner Pope Sholto Douglas Aakanksha Chowdhery Jacob Devlin James Bradbury Anselm Levskaya Jonathan Heek Kefan Xiao Shivani Agrawal and Jeff Dean. 2022. Efficiently Scaling Transformer Inference. arxiv:https:\/\/arXiv.org\/abs\/2211.05102\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2211.05102"},{"key":"e_1_3_3_2_22_2","first-page":"805","volume-title":"14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20)","author":"Qiu Haoran","year":"2020","unstructured":"Haoran Qiu, Subho\u00a0S. Banerjee, Saurabh Jha, Zbigniew\u00a0T. Kalbarczyk, and Ravishankar\u00a0K. Iyer. 2020. FIRM: An Intelligent Fine-grained Resource Management Framework for SLO-Oriented Microservices. In 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20). USENIX Association, 805\u2013825. https:\/\/www.usenix.org\/conference\/osdi20\/presentation\/qiu"},{"key":"e_1_3_3_2_23_2","unstructured":"Robin Rombach Andreas Blattmann Dominik Lorenz Patrick Esser and Bj\u00f6rn Ommer. 2022. High-Resolution Image Synthesis with Latent Diffusion Models. arxiv:https:\/\/arXiv.org\/abs\/2112.10752\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2112.10752"},{"key":"e_1_3_3_2_24_2","unstructured":"Lucia Schuler Somaya Jamil and Niklas K\u00fchl. 2020. AI-based Resource Allocation: Reinforcement Learning for Adaptive Auto-scaling in Serverless Environments. arxiv:https:\/\/arXiv.org\/abs\/2005.14410\u00a0[cs.DC] https:\/\/arxiv.org\/abs\/2005.14410"},{"key":"e_1_3_3_2_25_2","unstructured":"John Schulman Philipp Moritz Sergey Levine Michael Jordan and Pieter Abbeel. 2018. High-Dimensional Continuous Control Using Generalized Advantage Estimation. arxiv:https:\/\/arXiv.org\/abs\/1506.02438\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/1506.02438"},{"key":"e_1_3_3_2_26_2","unstructured":"John Schulman Filip Wolski Prafulla Dhariwal Alec Radford and Oleg Klimov. 2017. Proximal Policy Optimization Algorithms. CoRR abs\/1707.06347 (2017). arXiv:https:\/\/arXiv.org\/abs\/1707.06347http:\/\/arxiv.org\/abs\/1707.06347"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICAC.2006.1662383"},{"key":"e_1_3_3_2_28_2","unstructured":"Mark Towers Ariel Kwiatkowski Jordan Terry John\u00a0U. Balis Gianluca\u00a0De Cola Tristan Deleu Manuel Goul\u00e3o Andreas Kallinteris Markus Krimmel Arjun KG Rodrigo Perez-Vicente Andrea Pierr\u00e9 Sander Schulhoff Jun\u00a0Jet Tai Hannah Tan and Omar\u00a0G. Younis. 2024. Gymnasium: A Standard Interface for Reinforcement Learning Environments. arxiv:https:\/\/arXiv.org\/abs\/2407.17032\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2407.17032"},{"key":"e_1_3_3_2_29_2","unstructured":"Patrick von Platen Suraj Patil Anton Lozhkov Pedro Cuenca Nathan Lambert Kashif Rasul Mishig Davaadorj Dhruv Nair Sayak Paul William Berman Yiyi Xu Steven Liu and Thomas Wolf. 2022. Diffusers: State-of-the-art diffusion models. https:\/\/github.com\/huggingface\/diffusers."},{"key":"e_1_3_3_2_30_2","unstructured":"Yuxuan Wang Haixu Wu Jiaxiang Dong Yong Liu Mingsheng Long and Jianmin Wang. 2024. Deep Time Series Models: A Comprehensive Survey and Benchmark. (2024)."},{"key":"e_1_3_3_2_31_2","unstructured":"Zijie\u00a0J. Wang Evan Montoya David Munechika Haoyang Yang Benjamin Hoover and Duen\u00a0Horng Chau. 2022. DiffusionDB: A Large-Scale Prompt Gallery Dataset for Text-to-Image Generative Models. arXiv:https:\/\/arXiv.org\/abs\/2210.14896 [cs] (2022). https:\/\/arxiv.org\/abs\/2210.14896"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"publisher","unstructured":"Minxian Xu Chenghao Song Shashikant Ilager Sukhpal\u00a0Singh Gill Juanjuan Zhao Kejiang Ye and Chengzhong Xu. 2022. CoScal: Multifaceted Scaling of Microservices With Reinforcement Learning. IEEE Transactions on Network and Service Management 19 4 (2022) 3995\u20134009. 10.1109\/TNSM.2022.3210211","DOI":"10.1109\/TNSM.2022.3210211"},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539063"},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"publisher","unstructured":"Anastasios Zafeiropoulos Eleni Fotopoulou Nikos Filinis and Symeon Papavassiliou. 2022. Reinforcement learning-assisted autoscaling mechanisms for serverless computing platforms. Simulation Modelling Practice and Theory 116 (2022) 102461. 10.1016\/j.simpat.2021.102461","DOI":"10.1016\/j.simpat.2021.102461"},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICWS49710.2020.00072"},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/COMPSAC54236.2022.00137"},{"key":"e_1_3_3_2_37_2","unstructured":"Haoyi Zhou Shanghang Zhang Jieqi Peng Shuai Zhang Jianxin Li Hui Xiong and Wancai Zhang. 2021. Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting. arxiv:https:\/\/arXiv.org\/abs\/2012.07436\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2012.07436"},{"key":"e_1_3_3_2_38_2","volume-title":"Proc. 39th International Conference on Machine Learning (ICML 2022)","author":"Zhou Tian","year":"2022","unstructured":"Tian Zhou, Ziqing Ma, Qingsong Wen, Xue Wang, Liang Sun, and Rong Jin. 2022. FEDformer: Frequency enhanced decomposed transformer for long-term series forecasting. In Proc. 39th International Conference on Machine Learning (ICML 2022) (Baltimore, Maryland)."}],"event":{"name":"UCC '25: 2025 IEEE\/ACM 18th International Conference on Utility and Cloud Computing","location":"France France","acronym":"UCC '25","sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture"]},"container-title":["Proceedings of the 18th IEEE\/ACM International Conference on Utility and Cloud Computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3773274.3774258","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T11:40:42Z","timestamp":1767181242000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3773274.3774258"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12]]},"references-count":37,"alternative-id":["10.1145\/3773274.3774258","10.1145\/3773274"],"URL":"https:\/\/doi.org\/10.1145\/3773274.3774258","relation":{},"subject":[],"published":{"date-parts":[[2025,12]]},"assertion":[{"value":"2025-12-31","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}