{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T10:54:45Z","timestamp":1781866485171,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":35,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T00:00:00Z","timestamp":1782086400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CCF-2324514"],"award-info":[{"award-number":["CCF-2324514"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CNS-2132385"],"award-info":[{"award-number":["CNS-2132385"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,22]]},"DOI":"10.1145\/3797248.3815404","type":"proceedings-article","created":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T10:46:08Z","timestamp":1781865968000},"page":"28-35","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["MARLIN: Multi-Agent Game-Theoretic Reinforcement Learning for Sustainable LLM Inference in Cloud Datacenters"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-7693-703X","authenticated-orcid":false,"given":"Hayden","family":"Moore","sequence":"first","affiliation":[{"name":"Colorado State University, Fort Collins, CO, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5828-4394","authenticated-orcid":false,"given":"Sirui","family":"Qi","sequence":"additional","affiliation":[{"name":"Colorado State University, Fort Collins, CO, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9830-8588","authenticated-orcid":false,"given":"Dejan","family":"Milojicic","sequence":"additional","affiliation":[{"name":"Hewlett Packard Labs, Milpitas, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3177-3041","authenticated-orcid":false,"given":"Cullen","family":"Bash","sequence":"additional","affiliation":[{"name":"Hewlett Packard Labs, Milpitas, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0846-0066","authenticated-orcid":false,"given":"Sudeep","family":"Pasricha","sequence":"additional","affiliation":[{"name":"ECE, Colorado State University, Fort Collins, CO, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,22]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"crossref","unstructured":"Kazi Main\u00a0Uddin Ahmed et\u00a0al. 2021. A Review of Data Centers Energy Consumption and Reliability Modeling. IEEE Access 9 (2021) 152536\u2013152563.","DOI":"10.1109\/ACCESS.2021.3125092"},{"key":"e_1_3_3_1_3_2","series-title":"(UCC \u201925)","volume-title":"Proceedings of the 18th IEEE\/ACM UCC","author":"Alsalem Latifah","year":"2026","unstructured":"Latifah Alsalem and Karim Djemame. 2026. Task Scheduling in Edge Computing Environments: a Hierarchical Cluster-based Federated Deep Reinforcement Learning Approach. In Proceedings of the 18th IEEE\/ACM UCC(UCC \u201925). Association for Computing Machinery, New York, NY, USA, Article 47, 8\u00a0pages."},{"key":"e_1_3_3_1_4_2","volume-title":"Advances in Neural Information Processing Systems","author":"Andrychowicz Marcin","year":"2017","unstructured":"Marcin Andrychowicz et\u00a0al. 2017. Hindsight Experience Replay. In Advances in Neural Information Processing Systems , I.\u00a0Guyon, U.\u00a0Von Luxburg, S.\u00a0Bengio, H.\u00a0Wallach, R.\u00a0Fergus, S.\u00a0Vishwanathan, and R.\u00a0Garnett (Eds.), Vol.\u00a030. Curran Associates, Inc."},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"crossref","unstructured":"B.\u00a0M. Beena et\u00a0al. 2025. A Green Cloud-Based Framework for Energy-Efficient Task Scheduling Using Carbon Intensity Data for Heterogeneous Cloud Servers. IEEE Access 13 (2025) 73916\u201373938.","DOI":"10.1109\/ACCESS.2025.3562882"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"crossref","unstructured":"Rui Chen et\u00a0al. 2023. Power and thermal-aware virtual machine scheduling optimization in cloud data center. Future Generation Computer Systems 145 (2023) 578\u2013589.","DOI":"10.1016\/j.future.2023.03.049"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"crossref","unstructured":"Tracy\u00a0Yingying Cheng and Xiaohua Jia. 2020. Delay-Sensitive Multicast in Inter-Datacenter WAN Using Compressive Latency Monitoring. IEEE Transactions on Cloud Computing 8 1 (2020) 86\u201396.","DOI":"10.1109\/TCC.2017.2769080"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"crossref","unstructured":"K. Deb et\u00a0al. 2002. A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE Transactions on Evolutionary Computation 6 2 (2002) 182\u2013197.","DOI":"10.1109\/4235.996017"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"crossref","unstructured":"Chao Guo et\u00a0al. 2025. Q-Learning-Based Workload Consolidation for Data Centers With Composable Architecture. IEEE Transactions on Industrial Informatics 21 3 (2025) 2324\u20132333.","DOI":"10.1109\/TII.2024.3503776"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"crossref","unstructured":"Chunyang He Zhifeng Liu Jianguo Wu et\u00a0al. 2021. Future global urban water scarcity and potential solutions. Nature communications 12 1 (2021) 4667.","DOI":"10.1038\/s41467-021-25026-3"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"crossref","unstructured":"Taufik Hidayat et\u00a0al. 2025. Reinforcement Learning-Driven Hybrid Precopy\/Postcopy VM Migration for Energy-Efficient Data Centers. IEEE Access 13 (2025) 169521\u2013169533.","DOI":"10.1109\/ACCESS.2025.3613235"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"crossref","unstructured":"Ninad Hogade Sudeep Pasricha and Howard\u00a0Jay Siegel. 2022. Energy and Network Aware Workload Management for Geographically Distributed Data Centers. IEEE Transactions on Sustainable Computing 7 2 (2022) 400\u2013413.","DOI":"10.1109\/TSUSC.2021.3086087"},{"key":"e_1_3_3_1_13_2","unstructured":"Nidhal Jegham et\u00a0al. 2025. How Hungry is AI? Benchmarking Energy Water and Carbon Footprint of LLM Inference. arxiv:https:\/\/arXiv.org\/abs\/2505.09598\u00a0[cs.CY]"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"crossref","unstructured":"Yi Jin et\u00a0al. 2019. Water use of electricity technologies: A global meta-analysis. Renewable and Sustainable Energy Reviews 115 (2019) 109391.","DOI":"10.1016\/j.rser.2019.109391"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/Confluence51648.2021.9377049"},{"key":"e_1_3_3_1_16_2","unstructured":"Rebecca Leppert. 2026. What We Know about Energy Use at U.S. Data Centers Amid the AI Boom. www.pewresearch.org\/?p=277682 Accessed on Mar.31.2026."},{"key":"e_1_3_3_1_17_2","unstructured":"Yuzhuo Li et\u00a0al. 2024. The Unseen AI Disruptions for Power Grids: LLM-Induced Transients. arxiv:https:\/\/arXiv.org\/abs\/2409.11416\u00a0[cs.AR]"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/3669940.3707215"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/3472883.3487014"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/3716368.3735301"},{"key":"e_1_3_3_1_21_2","unstructured":"Ariffud Muhammad. 2026. LLM Statistics 2026: Comprehensive Insights into Market Trends and Integration. www.hostinger.com\/uk\/tutorials\/llm-statistics Accessed on Mar.31.2026."},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00019"},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/IGSC64514.2024.00010"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"crossref","unstructured":"Sirui Qi Hayden Moore Dejan Milojicic Cullen Bash and Sudeep Pasricha. 2026. SHIELD-EB: Sustainable Hybrid Evolutionary-Boosting Framework for Carbon Wastewater and Cost-Aware Datacenter Management. IEEE Access 14 (2026) 40878\u201340898.","DOI":"10.1109\/ACCESS.2026.3674066"},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/CLOUD67622.2025.00036"},{"key":"e_1_3_3_1_27_2","unstructured":"Sebastian Ruder. 2017. An overview of gradient descent optimization algorithms. arxiv:https:\/\/arXiv.org\/abs\/1609.04747\u00a0[cs.LG]"},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"publisher","unstructured":"Md\u00a0Abu\u00a0Bakar Siddik et\u00a0al. 2021. The environmental footprint of data centers in the United States. Environmental Research Letters 16 6 (may 2021) 064017. 10.1088\/1748-9326\/abfba1","DOI":"10.1088\/1748-9326\/abfba1"},{"key":"e_1_3_3_1_29_2","unstructured":"Shubham Singh. 2026. ChatGPT Users Statistics (2026) \u2013 Active Users & Global Growth Data. www.demandsage.com\/chatgpt-statistics Accessed on Mar.31.2026."},{"key":"e_1_3_3_1_30_2","unstructured":"Robert\u00a0F. Sullivan. 2000. Alternating cold and hot aisles provides more reliable cooling for server farms. White Paper Uptime Institute (2000)."},{"key":"e_1_3_3_1_31_2","unstructured":"Hugo Touvron et\u00a0al. 2023. Llama 2: Open Foundation and Fine-Tuned Chat Models. arxiv:https:\/\/arXiv.org\/abs\/2307.09288\u00a0[cs.CL]"},{"key":"e_1_3_3_1_32_2","unstructured":"John Von\u00a0Neumann and Oskar Morgenstern. 1947. Theory of games and economic behavior 2nd rev. (1947)."},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/3711896.3737413"},{"key":"e_1_3_3_1_34_2","unstructured":"Tianqi Xiao et\u00a0al. 2025. Environmental impact and net-zero pathways for sustainable artificial intelligence servers in the USA. Nature Sustainability (2025) 1\u201313."},{"key":"e_1_3_3_1_35_2","unstructured":"Zheming Yang et\u00a0al. 2024. PerLLM: Personalized Inference Scheduling with Edge-Cloud Collaboration for Diverse LLM Services. arxiv:https:\/\/arXiv.org\/abs\/2405.14636\u00a0[cs.DC]"},{"key":"e_1_3_3_1_36_2","doi-asserted-by":"crossref","unstructured":"Qingxia Zhang et\u00a0al. 2021. A survey on data center cooling systems: Technology power consumption modeling and control strategy optimization. Journal of Systems Architecture 119 (2021) 102253.","DOI":"10.1016\/j.sysarc.2021.102253"}],"event":{"name":"IGSC '26: International Green and Sustainable Computing Conference","location":"Canandaigua USA","acronym":"IGSC 2026","sponsor":["SIGDA ACM Special Interest Group on Design Automation"]},"container-title":["Proceedings of the 16th ACM International Green and Sustainable Computing Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/abs\/10.1145\/3797248.3815404","content-type":"text\/html","content-version":"vor","intended-application":"syndication"}],"deposited":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T10:49:36Z","timestamp":1781866176000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3797248.3815404"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,22]]},"references-count":35,"alternative-id":["10.1145\/3797248.3815404","10.1145\/3797248"],"URL":"https:\/\/doi.org\/10.1145\/3797248.3815404","relation":{},"subject":[],"published":{"date-parts":[[2026,6,22]]},"assertion":[{"value":"2026-06-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}