{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,12]],"date-time":"2026-10-12T23:22:25Z","timestamp":1791847345189,"version":"4.3.4"},"reference-count":61,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3734498","type":"journal-article","created":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T14:27:04Z","timestamp":1790260024000},"page":"146019-146040","source":"Crossref","is-referenced-by-count":1,"title":["PRESAGE: Uncertainty-Aware Predictive Elastic Scheduling for Cloud Analytics and GenAI Inference"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-3927-0742","authenticated-orcid":false,"given":"Yinuo","family":"Wang","sequence":"first","affiliation":[{"name":"The University of Chicago","place":["Chicago, IL, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4134-0639","authenticated-orcid":false,"given":"Xuanping","family":"Zou","sequence":"additional","affiliation":[{"name":"Zoom Communications Inc.","place":["San Jose, CA, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-4002-2980","authenticated-orcid":false,"given":"Zhou","family":"Lu","sequence":"additional","affiliation":[{"name":"Northeastern University","place":["Boston, MA, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kailang","family":"Wei","sequence":"additional","affiliation":[{"name":"Emory University","place":["Atlanta, GA, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-7583-7819","authenticated-orcid":false,"given":"Minjae","family":"Rhee","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana\u2013Champaign","place":["Champaign, IL, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3342195.3387517"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/2741948.2741964"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3132747.3132772"},{"key":"ref4","first-page":"205","article-title":"Serverless in the wild: Characterizing and optimizing the serverless workload at a large cloud provider","volume-title":"Proc. USENIX Annu. Tech. Conf. (ATC)","author":"Shahrad"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3326285.3329074"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00019"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3342195.3387524"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijforecast.2019.07.001"},{"key":"ref11","first-page":"10148","article-title":"A decoder-only foundation model for time-series forecasting","volume-title":"Proc. 41st Int. Conf. Mach. Learn. (ICML)","author":"Das"},{"key":"ref12","article-title":"Chronos: Learning the language of time series","author":"Ansari","year":"2024","journal-title":"arXiv:2403.07815"},{"key":"ref13","first-page":"53140","article-title":"Unified training of universal time series forecasting transformers","volume-title":"Proc. 41st Int. Conf. Mach. Learn. (ICML)","author":"Woo"},{"key":"ref14","first-page":"16115","article-title":"MOMENT: A family of open time-series foundation models","volume-title":"Proc. 41st Int. Conf. Mach. Learn. (ICML)","author":"Goswami"},{"key":"ref15","article-title":"Lag-llama: Towards foundation models for probabilistic time series forecasting","author":"Rasul","year":"2023","journal-title":"arXiv:2310.08278"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3005745.3005750"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3341302.3342080"},{"key":"ref18","first-page":"805","article-title":"FIRM: An intelligent fine-grained resource management framework for SLO-oriented microservices","volume-title":"Proc. 14th USENIX Symp. Operating Syst. Design Implement. (OSDI)","author":"Qiu"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3445814.3446693"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/OJCS.2026.3667549"},{"key":"ref21","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Hu"},{"key":"ref22","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proc. 36th Int. Conf. Mach. Learn. (ICML)","author":"Houlsby"},{"key":"ref23","volume-title":"TimesFM: A Decoder-Only Foundation Model for Time-Series Forecasting\u2014Google\/Timesfm-1.0-200m Checkpoint","year":"2024"},{"key":"ref24","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive NLP tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Lewis"},{"key":"ref25","first-page":"2206","article-title":"Improving language models by retrieving from trillions of tokens","volume-title":"Proc. 39th Int. Conf. Mach. Learn. (ICML)","author":"Borgeaud"},{"key":"ref26","article-title":"TimeRAG: BOOSTING LLM time series forecasting via retrieval-augmented generation","author":"Yang","year":"2024","journal-title":"arXiv:2412.16643"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0091"},{"key":"ref28","first-page":"3543","article-title":"Conformalized quantile regression","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Romano"},{"key":"ref29","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref30","first-page":"193","article-title":"DistServe: Disaggregating prefill and decoding for goodput-optimized large language model serving","volume-title":"Proc. 18th USENIX Symp. Operating Syst. Design Implement. (OSDI)","author":"Zhong"},{"key":"ref31","first-page":"1660","article-title":"Adaptive conformal inference under distribution shift","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"34","author":"Gibbs"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1000"},{"key":"ref33","article-title":"Anomaly transformer: Time series anomaly detection with association discrepancy","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Xu"},{"key":"ref34","volume-title":"Alibaba Cluster Trace Program","year":"2026"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3772052.3772206"},{"key":"ref36","volume-title":"Azure Public Dataset","year":"2024"},{"key":"ref37","volume-title":"Google Cluster-Usage Traces (ClusterData2019)","year":"2019"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17325"},{"key":"ref39","first-page":"22419","article-title":"Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Wu"},{"key":"ref40","article-title":"A time series is worth 64 words: Long-term forecasting with transformers","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Nie"},{"key":"ref41","article-title":"ITransformer: Inverted transformers are effective for time series forecasting","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Liu"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i9.26317"},{"key":"ref43","article-title":"Search-R2: Enhancing search-integrated reasoning via actor-refiner collaboration","author":"He","year":"2026","journal-title":"arXiv:2602.03647"},{"key":"ref44","first-page":"521","article-title":"Orca: A distributed serving system for transformer-based generative models","volume-title":"Proc. 16th USENIX Symp. Operating Syst. Design Implement. (OSDI)","author":"Yu"},{"key":"ref45","article-title":"SARATHI: Efficient LLM inference by piggybacking decodes with chunked prefills","author":"Agrawal","year":"2023","journal-title":"arXiv:2308.16369"},{"key":"ref46","first-page":"6402","article-title":"Simple and scalable predictive uncertainty estimation using deep ensembles","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Lakshminarayanan"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.5555\/3045390.3045502"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.21236\/ADA459827"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2025.3633290"},{"issue":"162","key":"ref50","first-page":"1","article-title":"Conformal inference for online prediction with arbitrary distribution shifts","volume":"25","author":"Gibbs","year":"2024","journal-title":"J. Mach. Learn. Res."},{"key":"ref51","first-page":"25834","article-title":"Adaptive conformal predictions for time series","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Zaffran"},{"key":"ref52","first-page":"11559","article-title":"Conformal prediction interval for dynamic time-series","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Xu"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1214\/23-AOS2276"},{"key":"ref54","article-title":"Copula conformal prediction for multi-step time series forecasting","author":"Sun","year":"2022","journal-title":"arXiv:2212.03281"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA61900.2025.00102"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1877"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4899-4541-9"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.2307\/4615733"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1037\/0033-2909.114.3.494"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1137\/070710111"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1111\/j.1937-5956.1993.tb00094.x"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11694384.pdf?arnumber=11694384","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T19:08:54Z","timestamp":1790622534000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11694384\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":61,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3734498","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}