{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T02:12:41Z","timestamp":1791166361653,"version":"4.1.0"},"reference-count":54,"publisher":"Elsevier BV","issue":"2","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2025,11,30]],"date-time":"2025-11-30T00:00:00Z","timestamp":1764460800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/100010097","name":"China Association for Science and Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100010097","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008868","name":"Jiangsu Province Department of Science and Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100008868","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Digital Communications and Networks"],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1016\/j.dcan.2025.11.006","type":"journal-article","created":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T08:25:58Z","timestamp":1764750358000},"page":"236-251","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":2,"title":["Green scheduling for LLM workloads with model and data reuse across geo-distributed data centers"],"prefix":"10.1016","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-1005-0996","authenticated-orcid":false,"given":"Hao","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-6183-9856","authenticated-orcid":false,"given":"Xiaonyu","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5601-0513","authenticated-orcid":false,"given":"Ran","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1269-2097","authenticated-orcid":false,"given":"Jie","family":"Hao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9467-1491","authenticated-orcid":false,"given":"Qiang","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8906-813X","authenticated-orcid":false,"given":"Hongke","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"3","key":"10.1016\/j.dcan.2025.11.006_bib0001","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3641289","article-title":"A survey on evaluation of large language models","volume":"15","author":"Chang","year":"2024","journal-title":"ACM Trans. Intell. Syst. Technol."},{"key":"10.1016\/j.dcan.2025.11.006_bib0002","unstructured":"N. Maslej, L. Fattorini, E. Brynjolfsson, J. Etchemendy, K. Ligett, T. Lyons, J. Manyika, H. Ngo, J. C. Niebles, V. Parli, et al., Artificial intelligence index report 2023, arXiv: 2310.03715, (2023)."},{"key":"10.1016\/j.dcan.2025.11.006_bib0003","series-title":"GLOBECOM 2023-2023 IEEE Global Communications Conference","first-page":"3500","article-title":"Sustainable aigc workload scheduling of geo-distributed data centers: a multi-agent reinforcement learning approach","author":"Zhang","year":"2023"},{"issue":"4","key":"10.1016\/j.dcan.2025.11.006_bib0004","doi-asserted-by":"crossref","first-page":"628","DOI":"10.1109\/TSUSC.2024.3520969","article-title":"Game-theoretic deep reinforcement learning to minimize carbon emissions and energy costs for AI inference workloads in geo-distributed data centers","volume":"10","author":"Hogade","year":"2025","journal-title":"IEEE Trans. Sustain. Comput."},{"issue":"1","key":"10.1016\/j.dcan.2025.11.006_bib0005","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TPDS.2018.2882174","article-title":"A truthful and efficient incentive mechanism for demand response in green datacenters","volume":"31","author":"Zhou","year":"2018","journal-title":"IEEE Trans. Parall. Distrib. Syst."},{"key":"10.1016\/j.dcan.2025.11.006_bib0006","unstructured":"Electricitymaps, Electricitymaps: get carbon electricity data for your research project. https:\/\/www.electricitymaps.com\/research2025. (accessed 20\u202fMarch 2025)."},{"key":"10.1016\/j.dcan.2025.11.006_bib0007","series-title":"Proceedings of the 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24)","first-page":"709","article-title":"Characterization of large language model development in the datacenter","author":"Hu","year":"2024"},{"issue":"12","key":"10.1016\/j.dcan.2025.11.006_bib0008","doi-asserted-by":"crossref","first-page":"2331","DOI":"10.1109\/TPDS.2024.3467212","article-title":"Two-timescale joint optimization of task scheduling and resource scaling in multi-data center system based on multi-agent deep reinforcement learning","volume":"35","author":"Chen","year":"2024","journal-title":"IEEE Trans. Parall. Distrib. Syst."},{"key":"10.1016\/j.dcan.2025.11.006_bib0009","series-title":"Proceedings of the 2024 IEEE\/IAS Industrial and Commercial Power System Asia","first-page":"748","article-title":"Online job scheduling for energy cost optimization in geo-distributed data centers considering data locality: a multi-agent reinforcement learning approach","author":"Lang","year":"2024"},{"issue":"8","key":"10.1016\/j.dcan.2025.11.006_bib0010","doi-asserted-by":"crossref","DOI":"10.1016\/j.jksuci.2024.102170","article-title":"An electricity price and energy-efficient workflow scheduling in geographically distributed cloud data centers","volume":"36","author":"Hussain","year":"2024","journal-title":"J. King Saud Univ.-Comput. Inf. Sci."},{"key":"10.1016\/j.dcan.2025.11.006_bib0011","series-title":"Proceedings of the 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems","first-page":"118","article-title":"Carbon explorer: a holistic framework for designing carbon aware datacenters","author":"Acun","year":"2023"},{"key":"10.1016\/j.dcan.2025.11.006_bib0012","series-title":"Proceedings of the 30th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming","first-page":"297","article-title":"WaterWise: co-optimizing carbon-and water-footprint toward environmentally sustainable cloud computing","author":"Jiang","year":"2025"},{"issue":"2","key":"10.1016\/j.dcan.2025.11.006_bib0013","doi-asserted-by":"crossref","first-page":"1270","DOI":"10.1109\/TPWRS.2022.3173250","article-title":"Carbon-aware computing for datacenters","volume":"38","author":"Radovanovi\u0107","year":"2022","journal-title":"IEEE Trans. Power Syst."},{"key":"10.1016\/j.dcan.2025.11.006_bib0014","series-title":"Proceedings of the 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24)","first-page":"563","article-title":"MAST: Global scheduling of ML training across geo-distributed datacenters at hyperscale","author":"Choudhury","year":"2024"},{"issue":"2","key":"10.1016\/j.dcan.2025.11.006_bib0015","doi-asserted-by":"crossref","first-page":"1133","DOI":"10.1109\/TCC.2022.3162556","article-title":"Transactive operational framework for internet data centers in geo-distributed local energy markets","volume":"11","author":"Guo","year":"2022","journal-title":"IEEE Trans. Cloud Comput."},{"key":"10.1016\/j.dcan.2025.11.006_bib0016","series-title":"Proceedings of the 8th ACM European Conference on Computer Systems","first-page":"351","article-title":"Omega: flexible, scalable schedulers for large compute clusters","author":"Schwarzkopf","year":"2013"},{"key":"10.1016\/j.dcan.2025.11.006_bib0017","series-title":"Proceedings of the Tenth European Conference on Computer Systems","first-page":"1","article-title":"Large-scale cluster management at google with borg","author":"Verma","year":"2015"},{"issue":"1","key":"10.1016\/j.dcan.2025.11.006_bib0018","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1145\/2898442.2898444","article-title":"Borg, omega, and kubernetes: lessons learned from three container-management systems over a decade","volume":"14","author":"Burns","year":"2016","journal-title":"Queue"},{"key":"10.1016\/j.dcan.2025.11.006_bib0019","series-title":"12th USENIX Workshop on Hot Topics in Cloud Computing (HotCloud 20)","first-page":"1","article-title":"Towards GPU utilization prediction for cloud deep learning","author":"Yeung","year":"2020"},{"key":"10.1016\/j.dcan.2025.11.006_bib0020","series-title":"2022 IEEE 40th International Conference on Computer Design (ICCD)","first-page":"672","article-title":"Tear up the bubble boom: lessons learned from a deep learning research and development cluster","author":"Yang","year":"2022"},{"key":"10.1016\/j.dcan.2025.11.006_bib0021","series-title":"17th USENIX Symposium on Networked Systems Design and Implementation (NSDI 20)","first-page":"289","article-title":"Themis: fair and efficient GPU cluster scheduling","author":"Mahajan","year":"2020"},{"issue":"11","key":"10.1016\/j.dcan.2025.11.006_bib0022","doi-asserted-by":"crossref","first-page":"2781","DOI":"10.1109\/TPDS.2021.3136245","article-title":"Astraea: a fair deep learning scheduler for multi-tenant gpu clusters","volume":"33","author":"Ye","year":"2021","journal-title":"IEEE Trans. Parall. Distrib. Syst."},{"key":"10.1016\/j.dcan.2025.11.006_bib0023","series-title":"Proceedings of the 2nd ACM International Workshop on Distributed Machine Learning","first-page":"15","article-title":"Doing more by doing less: how structured partial backpropagation improves deep learning clusters","author":"Kumar","year":"2021"},{"key":"10.1016\/j.dcan.2025.11.006_bib0024","series-title":"21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24)","first-page":"1403","article-title":"CASSINI: network-aware job scheduling in machine learning clusters","author":"Rajasekaran","year":"2024"},{"key":"10.1016\/j.dcan.2025.11.006_bib0025","series-title":"Proceedings of the 29th Symposium on Operating Systems Principles","first-page":"642","article-title":"Sia: heterogeneity-aware, goodput-optimized ML-cluster scheduling","author":"Jayaram Subramanya","year":"2023"},{"key":"10.1016\/j.dcan.2025.11.006_bib0026","series-title":"Proceedings of the 22nd International Middleware Conference","first-page":"260","article-title":"Let\u2019s wait awhile: how temporal workload shifting can reduce carbon emissions in the cloud","author":"Wiesner","year":"2021"},{"key":"10.1016\/j.dcan.2025.11.006_bib0027","series-title":"Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems","first-page":"479","article-title":"Going green for less green: optimizing the cost of reducing cloud carbon emissions","author":"Hanafy","year":"2024"},{"key":"10.1016\/j.dcan.2025.11.006_bib0028","series-title":"Proceedings of the ACM on Measurement and Analysis of Computing Systems","first-page":"1","article-title":"Carbonscaler: leveraging cloud workload elasticity for optimizing carbon-efficiency","author":"Hanafy","year":"2023"},{"key":"10.1016\/j.dcan.2025.11.006_bib0029","series-title":"22nd USENIX Symposium on Networked Systems Design and Implementation (NSDI 25)","first-page":"999","article-title":"GREEN: carbon-efficient resource scheduling for machine learning clusters","author":"Xu","year":"2025"},{"key":"10.1016\/j.dcan.2025.11.006_bib0030","series-title":"2023 USENIX Annual Technical Conference (USENIX ATC 23)","first-page":"851","article-title":"EnvPipe: performance-preserving DNN training framework for saving energy","author":"Choi","year":"2023"},{"key":"10.1016\/j.dcan.2025.11.006_bib0031","series-title":"20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23)","first-page":"119","article-title":"Zeus: understanding and optimizing GPU energy consumption of DNN training","author":"You","year":"2023"},{"key":"10.1016\/j.dcan.2025.11.006_bib0032","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1016\/j.future.2022.02.018","article-title":"Deadline-constrained energy-aware workflow scheduling in geographically distributed cloud data centers","volume":"132","author":"Hussain","year":"2022","journal-title":"Future Gen. Comput. Syst."},{"issue":"5","key":"10.1016\/j.dcan.2025.11.006_bib0033","doi-asserted-by":"crossref","first-page":"2766","DOI":"10.1109\/TSC.2021.3054754","article-title":"Energy-minimized scheduling of real-time parallel workflows on heterogeneous distributed computing systems","volume":"15","author":"Hu","year":"2021","journal-title":"IEEE Trans. Serv. Comput."},{"key":"10.1016\/j.dcan.2025.11.006_bib0034","series-title":"Proceedings of the 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems","first-page":"252","article-title":"Ecovisor: a virtual energy system for carbon-efficient applications","author":"Souza","year":"2023"},{"key":"10.1016\/j.dcan.2025.11.006_bib0035","series-title":"Proceedings of the 2021 IEEE 23rd Int Conf on High Performance Computing & Communications","first-page":"2410","article-title":"Joint energy and computation workload management for geo-distributed data centers in smart grid","author":"Li","year":"2021"},{"issue":"10","key":"10.1016\/j.dcan.2025.11.006_bib0036","doi-asserted-by":"crossref","first-page":"2208","DOI":"10.1016\/j.joule.2020.08.001","article-title":"Mitigating curtailment and carbon emissions through load migration between data centers","volume":"4","author":"Zheng","year":"2020","journal-title":"Joule"},{"issue":"3","key":"10.1016\/j.dcan.2025.11.006_bib0037","doi-asserted-by":"crossref","first-page":"705","DOI":"10.1109\/TPDS.2017.2773504","article-title":"Time-and cost-efficient task scheduling across geo-distributed data centers","volume":"29","author":"Hu","year":"2017","journal-title":"IEEE Trans. Parall. Distrib. Syst."},{"issue":"4","key":"10.1016\/j.dcan.2025.11.006_bib0038","doi-asserted-by":"crossref","first-page":"604","DOI":"10.1109\/TPDS.2024.3360448","article-title":"Multi-agent deep reinforcement learning framework for renewable energy-aware workflow scheduling on distributed cloud data centers","volume":"35","author":"Jayanetti","year":"2024","journal-title":"IEEE Trans. Parall. Distrib. Syst."},{"key":"10.1016\/j.dcan.2025.11.006_bib0039","series-title":"Proceedings of the Second International Conference on Knowledge Discovery and Data Mining","first-page":"226","article-title":"A density-based algorithm for discovering clusters in large spatial databases with noise","author":"Ester","year":"1996"},{"key":"10.1016\/j.dcan.2025.11.006_bib0040","series-title":"Proceedings of the 36th Conference on Neural Information Processing Systems","first-page":"24611","article-title":"The surprising effectiveness of ppo in cooperative multi-agent games","author":"Yu","year":"2022"},{"key":"10.1016\/j.dcan.2025.11.006_bib0041","series-title":"Proceedings of the 31st Conference on Neural Information Processing Systems","first-page":"1","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"Lowe","year":"2017"},{"key":"10.1016\/j.dcan.2025.11.006_bib0042","series-title":"Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence","first-page":"1","article-title":"Counterfactual multi-agent policy gradients","author":"Foerster","year":"2018"},{"issue":"1","key":"10.1016\/j.dcan.2025.11.006_bib0043","doi-asserted-by":"crossref","first-page":"265","DOI":"10.1007\/BF01588971","article-title":"An analysis of approximations for maximizing submodular set functions\u2014I","volume":"14","author":"Nemhauser","year":"1978","journal-title":"Math. Programm."},{"key":"10.1016\/j.dcan.2025.11.006_bib0044","series-title":"Handbook of Combinatorial Optimization","author":"Pisinger","year":"1998"},{"key":"10.1016\/j.dcan.2025.11.006_bib0045","unstructured":"W. Liu, W. Cai, K. Jiang, G. Cheng, Y. Wang, J. Wang, J. Cao, L. Xu, C. Mu, C. Sun, XuanCe: a comprehensive and unified deep reinforcement learning library, arXiv: 2312.16248, (2023)."},{"key":"10.1016\/j.dcan.2025.11.006_bib0046","unstructured":"Y. Wang, Y. Chen, Z. Li, X. Kang, Z. Tang, X. He, R. Guo, X. Wang, Q. Wang, A.C. Zhou, et al., BurstGPT: a real-world workload dataset to optimize LLM serving systems, arXiv: 2401.17644. (2024)."},{"key":"10.1016\/j.dcan.2025.11.006_bib0047","series-title":"Proceedings of the 2023 USENIX Annual Technical Conference (USENIX ATC 23)","first-page":"995","article-title":"Beware of fragmentation: scheduling GPU-Sharing workloads with fragmentation gradient descent","author":"Weng","year":"2023"},{"key":"10.1016\/j.dcan.2025.11.006_bib0048","series-title":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","first-page":"1","article-title":"Characterization and prediction of deep learning workloads in large-scale gpu datacenters","author":"Hu","year":"2021"},{"key":"10.1016\/j.dcan.2025.11.006_bib0049","series-title":"Proceedings of the 2019 USENIX Annual Technical Conference (USENIX ATC 19)","first-page":"947","article-title":"Analysis of large-scale multi-tenant GPU clusters for DNN training workloads","author":"Jeon","year":"2019"},{"key":"10.1016\/j.dcan.2025.11.006_bib0050","unstructured":"Ollama, Ollama: GitHub Repository. 2025. (accessed: 05 February 2025). https:\/\/github.com\/ollama\/ollama\/blob\/main\/README.md."},{"key":"10.1016\/j.dcan.2025.11.006_bib0051","unstructured":"Zjh-819, LLMDataHub: Awesome Datasets for LLM Training. 2023. (accessed: 15 July 2025). https:\/\/github.com\/Zjh-819\/LLMDataHub."},{"key":"10.1016\/j.dcan.2025.11.006_bib0052","series-title":"Proceedings of the 2013 IEEE International Conference on Communications (ICC)","first-page":"2578","article-title":"Virtual machines migration in a cloud data center scenario: an experimental analysis","author":"Adami","year":"2013"},{"key":"10.1016\/j.dcan.2025.11.006_bib0053","doi-asserted-by":"crossref","first-page":"142","DOI":"10.1016\/j.future.2021.08.014","article-title":"Optimal data placement strategy considering capacity limitation and load balancing in geographically distributed cloud","volume":"127","author":"Li","year":"2022","journal-title":"Future Gen. Comput. Syst."},{"issue":"4","key":"10.1016\/j.dcan.2025.11.006_bib0054","doi-asserted-by":"crossref","first-page":"785","DOI":"10.1111\/jiec.12630","article-title":"Electricity intensity of internet data transmission: untangling the estimates","volume":"22","author":"Aslan","year":"2018","journal-title":"J. Industr. Ecol."}],"container-title":["Digital Communications and Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2352864825001828?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2352864825001828?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T20:54:04Z","timestamp":1775681644000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S2352864825001828"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":54,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,2]]}},"alternative-id":["S2352864825001828"],"URL":"https:\/\/doi.org\/10.1016\/j.dcan.2025.11.006","relation":{},"ISSN":["2352-8648"],"issn-type":[{"value":"2352-8648","type":"print"}],"subject":[],"published":{"date-parts":[[2026,2]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Green scheduling for LLM workloads with model and data reuse across geo-distributed data centers","name":"articletitle","label":"Article Title"},{"value":"Digital Communications and Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.dcan.2025.11.006","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 Chongqing University of Posts and Telecommunications. Publishing services by Elsevier B.V. on behalf of KeAi Communications Co. Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}]}}