{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T14:56:05Z","timestamp":1784645765259,"version":"3.55.0"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CCF-1302693"],"award-info":[{"award-number":["CCF-1302693"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Sustain. Comput."],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1109\/tsusc.2024.3520969","type":"journal-article","created":{"date-parts":[[2024,12,24]],"date-time":"2024-12-24T14:30:13Z","timestamp":1735050613000},"page":"628-641","source":"Crossref","is-referenced-by-count":17,"title":["Game-Theoretic Deep Reinforcement Learning to Minimize Carbon Emissions and Energy Costs for AI Inference Workloads in Geo-Distributed Data Centers"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8560-2497","authenticated-orcid":false,"given":"Ninad","family":"Hogade","sequence":"first","affiliation":[{"name":"Hewlett Packard Labs, Fort Collins, CO, 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":"Department of Electrical and Computer Engineering, Colorado State University, Fort Collins, CO, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Key internet statistics in 2023 (including mobile)","year":"2023"},{"key":"ref2","article-title":"AI and the data center: Challenges and investment strategies","year":"2023"},{"key":"ref3","volume-title":"Cisco Global Cloud Index: Forecast and Methodology, 2016\u20132021","year":"2018"},{"key":"ref4","article-title":"Data center locations","year":"2023"},{"key":"ref5","article-title":"Global infrastructure","year":"2023"},{"key":"ref6","article-title":"The value of geographically diverse data centers","year":"2023"},{"key":"ref7","article-title":"What is time-of-use pricing and why is it important?","year":"2016"},{"key":"ref8","article-title":"Dynamic pricing","year":"2016"},{"key":"ref9","article-title":"Demand charges","year":"2017"},{"key":"ref10","article-title":"Carbon emissions of data usage increasing, but what is yours?","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TSUSC.2018.2822674"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TSUSC.2021.3086087"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CLOUD.2013.77"},{"key":"ref14","article-title":"Why AI inference will remain largely on the CPU","year":"2023"},{"key":"ref15","article-title":"AI stocks: Why the \u2018inferencing\u2019 market will be bigger than training models","year":"2023"},{"key":"ref16","article-title":"Infrastructure requirements for AI inference vs. training","year":"2022"},{"key":"ref17","article-title":"Unlock the power of poweredge servers for AI workloads: Experience up to 177% performance boost!","year":"2023"},{"key":"ref18","article-title":"CPU vs GPU: How to narrow the deep learning performance gap?","year":"2023"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TSUSC.2022.3208781"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.comcom.2020.04.061"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IWQoS.2017.7969161"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/MCC.2018.1081060"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CCIOT48581.2019.8980333"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2018.2865927"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TSUSC.2019.2910533"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2020.06.038"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2018.2813333"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-020-03523-4"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS51616.2021.00023"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/SMC53654.2022.9945426"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3024135"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CLOUD53861.2021.00037"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3472456.3473514"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s10696-021-09408-9"},{"key":"ref36","article-title":"A stochastic reliability model of a server under a random workload","author":"Traylor","year":"2015"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-016-1783-y"},{"key":"ref38","article-title":"DC AIBench: Datacenter AI benchmarks","year":"2023"},{"key":"ref39","article-title":"U.S. electric power industry estimated emissions by state","year":"2023"},{"key":"ref40","author":"Brockman","year":"2016","journal-title":"ArXiv:1606.01540"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-57077-4_10"},{"issue":"1","key":"ref42","first-page":"1","article-title":"Stable-baselines3: Reliable reinforcement learning implementations","volume":"22","author":"Raffin","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00035"},{"key":"ref44","first-page":"116","article-title":"The GENITOR algorithm and selective pressure: Why rank-based allocation of reproductive trials is best","volume-title":"Proc. 3rd lnternational Conf. Genet. Algorithms","author":"Whitley"},{"key":"ref45","article-title":"Amazon CloudFront pricing","year":"2023"},{"key":"ref46","article-title":"National solar radiation database","year":"2023"},{"key":"ref47","article-title":"Net metering","year":"2023"}],"container-title":["IEEE Transactions on Sustainable Computing"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/7274860\/11121336\/10811780-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7274860\/11121336\/10811780.pdf?arnumber=10811780","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,9]],"date-time":"2025-08-09T04:44:13Z","timestamp":1754714653000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10811780\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":47,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tsusc.2024.3520969","relation":{},"ISSN":["2377-3782","2377-3790"],"issn-type":[{"value":"2377-3782","type":"electronic"},{"value":"2377-3790","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7]]}}}