{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T23:15:21Z","timestamp":1781910921927,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":33,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,6,16]],"date-time":"2023-06-16T00:00:00Z","timestamp":1686873600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Natural Science Foundation, China","award":["No. 62262026, No. GJJ211111"],"award-info":[{"award-number":["No. 62262026, No. GJJ211111"]}]},{"name":"Ministry of Education, Singapore","award":["Tier 1 of RT14\/22 and RG96\/20"],"award-info":[{"award-number":["Tier 1 of RT14\/22 and RG96\/20"]}]},{"name":"Nanyang Technological University, Singapore","award":["No. NTU?ACE2020-01"],"award-info":[{"award-number":["No. NTU?ACE2020-01"]}]},{"name":"National Research Foundation, Singapore","award":["NRF2020NRF-CG001-027"],"award-info":[{"award-number":["NRF2020NRF-CG001-027"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,6,20]]},"DOI":"10.1145\/3575813.3597343","type":"proceedings-article","created":{"date-parts":[[2023,6,16]],"date-time":"2023-06-16T16:18:31Z","timestamp":1686932311000},"page":"333-346","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":12,"title":["Toward Model-Assisted Safe Reinforcement Learning for Data Center Cooling Control: A Lyapunov-based Approach"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0341-8213","authenticated-orcid":false,"given":"Zhiwei","family":"Cao","sequence":"first","affiliation":[{"name":"Nanyang Technological University, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8827-9373","authenticated-orcid":false,"given":"Ruihang","family":"Wang","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5405-9890","authenticated-orcid":false,"given":"Xin","family":"Zhou","sequence":"additional","affiliation":[{"name":"Jiangxi Science and Technology Normal University, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2751-5114","authenticated-orcid":false,"given":"Yonggang","family":"Wen","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,6,16]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"International conference on machine learning. PMLR, 22\u201331","author":"Achiam Joshua","year":"2017","unstructured":"Joshua Achiam, David Held, Aviv Tamar, and Pieter Abbeel. 2017. Constrained policy optimization. In International conference on machine learning. PMLR, 22\u201331."},{"key":"e_1_3_2_1_2_1","volume-title":"Differentiable convex optimization layers. Advances in neural information processing systems 32","author":"Agrawal Akshay","year":"2019","unstructured":"Akshay Agrawal, Brandon Amos, Shane Barratt, Stephen Boyd, Steven Diamond, and J\u00a0Zico Kolter. 2019. Differentiable convex optimization layers. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_3_2_1_3_1","volume-title":"https:\/\/www.ashrae.org\/file%20library\/technical%20resources\/bookstore\/supplemental%20files\/referencecard_2021thermalguidelines.pdf","author":"Reference Card ASHRAE.","year":"2021","unstructured":"ASHRAE. 2021. ASHRAE TC 9.9 Reference Card (2021). https:\/\/www.ashrae.org\/file%20library\/technical%20resources\/bookstore\/supplemental%20files\/referencecard_2021thermalguidelines.pdf."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3563357.3564050"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2022.3161275"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447555.3464874"},{"key":"e_1_3_2_1_7_1","volume-title":"Lyapunov-based safe policy optimization for continuous control. arXiv preprint arXiv:1901.10031","author":"Chow Yinlam","year":"2019","unstructured":"Yinlam Chow, Ofir Nachum, Aleksandra Faust, Edgar Duenez-Guzman, and Mohammad Ghavamzadeh. 2019. Lyapunov-based safe policy optimization for continuous control. arXiv preprint arXiv:1901.10031 (2019)."},{"key":"e_1_3_2_1_8_1","volume-title":"EnergyPlus: creating a new-generation building energy simulation program. Energy and buildings 33, 4","author":"Crawley B","year":"2001","unstructured":"Drury\u00a0B Crawley, Linda\u00a0K Lawrie, Frederick\u00a0C Winkelmann, Walter\u00a0F Buhl, Y\u00a0Joe Huang, Curtis\u00a0O Pedersen, Richard\u00a0K Strand, Richard\u00a0J Liesen, Daniel\u00a0E Fisher, Michael\u00a0J Witte, 2001. EnergyPlus: creating a new-generation building energy simulation program. Energy and buildings 33, 4 (2001), 319\u2013331."},{"key":"e_1_3_2_1_9_1","volume-title":"Safe exploration in continuous action spaces. arXiv preprint arXiv:1801.08757","author":"Dalal Gal","year":"2018","unstructured":"Gal Dalal, Krishnamurthy Dvijotham, Matej Vecerik, Todd Hester, Cosmin Paduraru, and Yuval Tassa. 2018. Safe exploration in continuous action spaces. arXiv preprint arXiv:1801.08757 (2018)."},{"key":"e_1_3_2_1_10_1","unstructured":"Moss David and Jr John H.\u00a0Bean. 2012. Energy Impact of Increased Server Inlet Temperature. https:\/\/www.se.com\/us\/en\/download\/document\/SPD_JBEN-7KTR88_EN\/."},{"key":"e_1_3_2_1_11_1","unstructured":"Jacqueline Davis Daniel Bizo Andy Lawrence Owen Rogers and Max Smolaks. 2022. Uptime Institute Global Data Center Survey 2022: Resiliency remains critical in a volatile world. https:\/\/uptimeinstitute.com\/resources\/research-and-reports\/uptime-institute-global-data-center-survey-results-2022."},{"key":"e_1_3_2_1_12_1","unstructured":"EMA.2022. Energy Transformation (Chapter 2). https:\/\/www.ema.gov.sg\/singapore-energy-statistics\/Ch02\/index2."},{"key":"e_1_3_2_1_13_1","volume-title":"International conference on machine learning. PMLR, 1587\u20131596","author":"Fujimoto Scott","year":"2018","unstructured":"Scott Fujimoto, Herke Hoof, and David Meger. 2018. Addressing function approximation error in actor-critic methods. In International conference on machine learning. PMLR, 1587\u20131596."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3326285.3329074"},{"key":"e_1_3_2_1_15_1","volume-title":"International conference on machine learning. PMLR","author":"Haarnoja Tuomas","year":"2018","unstructured":"Tuomas Haarnoja, Aurick Zhou, Pieter Abbeel, and Sergey Levine. 2018. Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor. In International conference on machine learning. PMLR, 1861\u20131870."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.enbuild.2020.110599"},{"key":"e_1_3_2_1_17_1","volume-title":"Airflow and cooling performance of data centers: Two performance metrics. ASHRAE transactions 114, 2","author":"K Herrlin","year":"2008","unstructured":"Magunus\u00a0K Herrlin 2008. Airflow and cooling performance of data centers: Two performance metrics. ASHRAE transactions 114, 2 (2008), 182\u2013187."},{"key":"e_1_3_2_1_18_1","volume-title":"Data center cooling using model-predictive control. Advances in Neural Information Processing Systems 31","author":"Lazic Nevena","year":"2018","unstructured":"Nevena Lazic, Craig Boutilier, Tyler Lu, Eehern Wong, Binz Roy, MK Ryu, and Greg Imwalle. 2018. Data center cooling using model-predictive control. Advances in Neural Information Processing Systems 31 (2018)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2927410"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.5555\/1941130"},{"key":"e_1_3_2_1_21_1","unstructured":"Adam Paszke Sam Gross Soumith Chintala Gregory Chanan Edward Yang Zachary DeVito Zeming Lin Alban Desmaison Luca Antiga and Adam Lerer. 2017. Automatic differentiation in pytorch. (2017)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2019.00070"},{"key":"e_1_3_2_1_23_1","volume-title":"Benchmarking safe exploration in deep reinforcement learning. arXiv preprint arXiv:1910.01708 7","author":"Ray Alex","year":"2019","unstructured":"Alex Ray, Joshua Achiam, and Dario Amodei. 2019. Benchmarking safe exploration in deep reinforcement learning. arXiv preprint arXiv:1910.01708 7 (2019), 1."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"crossref","unstructured":"Arman Shehabi Sarah Smith Dale Sartor Richard Brown Magnus Herrlin Jonathan Koomey Eric Masanet Nathaniel Horner In\u00eas Azevedo and William Lintner. 2016. United states data center energy usage report. (2016).","DOI":"10.2172\/1372902"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.enbuild.2018.01.046"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3360322.3360845"},{"key":"e_1_3_2_1_27_1","volume-title":"Toward Physics-Guided Safe Deep Reinforcement Learning for Green Data Center Cooling Control. In 2022 ACM\/IEEE 13th International Conference on Cyber-Physical Systems (ICCPS). IEEE, 159\u2013169","author":"Wang Ruihang","year":"2022","unstructured":"Ruihang Wang, Xinyi Zhang, Xin Zhou, Yonggang Wen, and Rui Tan. 2022. Toward Physics-Guided Safe Deep Reinforcement Learning for Green Data Center Cooling Control. In 2022 ACM\/IEEE 13th International Conference on Cyber-Physical Systems (ICCPS). IEEE, 159\u2013169."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1080\/10789669.2008.10390991"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2001.946075"},{"key":"e_1_3_2_1_30_1","volume-title":"Projection-based constrained policy optimization. arXiv preprint arXiv:2010.03152","author":"Yang Tsung-Yen","year":"2020","unstructured":"Tsung-Yen Yang, Justinian Rosca, Karthik Narasimhan, and Peter\u00a0J Ramadge. 2020. Projection-based constrained policy optimization. arXiv preprint arXiv:2010.03152 (2020)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3360322.3360861"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1115\/IMECE2011-62506"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/STHERM.2012.6188832"}],"event":{"name":"e-Energy '23: The 14th ACM International Conference on Future Energy Systems","location":"Orlando FL USA","acronym":"e-Energy '23","sponsor":["SIGEnergy ACM Special Interest Group on Energy Systems and Informatics"]},"container-title":["Proceedings of the 14th ACM International Conference on Future Energy Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3575813.3597343","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3575813.3597343","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:46:11Z","timestamp":1750178771000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3575813.3597343"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,16]]},"references-count":33,"alternative-id":["10.1145\/3575813.3597343","10.1145\/3575813"],"URL":"https:\/\/doi.org\/10.1145\/3575813.3597343","relation":{},"subject":[],"published":{"date-parts":[[2023,6,16]]},"assertion":[{"value":"2023-06-16","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}