{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,23]],"date-time":"2025-12-23T16:33:40Z","timestamp":1766507620813,"version":"3.48.0"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,12,23]],"date-time":"2025-12-23T00:00:00Z","timestamp":1766448000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,12,23]],"date-time":"2025-12-23T00:00:00Z","timestamp":1766448000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"name":"CAS Youth Interdisciplinary Team","award":["JCTD-2022-07"],"award-info":[{"award-number":["JCTD-2022-07"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Big Data"],"DOI":"10.1186\/s40537-025-01325-0","type":"journal-article","created":{"date-parts":[[2025,12,23]],"date-time":"2025-12-23T14:30:45Z","timestamp":1766500245000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Deep reinforcement learning for job scheduling on load-aware heterogeneous cluster"],"prefix":"10.1186","volume":"12","author":[{"given":"Zhenjie","family":"Yao","sequence":"first","affiliation":[]},{"given":"Li","family":"Ding","sequence":"additional","affiliation":[]},{"given":"He","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Huiqiang","family":"Li","sequence":"additional","affiliation":[]},{"given":"Lan","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Zhiqiang","family":"Li","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,12,23]]},"reference":[{"key":"1325_CR1","doi-asserted-by":"publisher","unstructured":"Barroso LA, Hlzle U, Ranganathan P. The datacenter as a computer: An introduction to the design of warehouse-scale machines. Synth Lect Comput Archit. Springer Cham. 2009;8(3) https:\/\/doi.org\/10.1007\/978-3-031-01761-2","DOI":"10.1007\/978-3-031-01761-2"},{"key":"1325_CR2","unstructured":"Hadoop A. Hadoop Fair Scheduler. 2014. Available: https:\/\/hadoop.apache.org\/docs\/current\/hadoop-yarn\/hadoop-yarn-site\/FairScheduler.html"},{"key":"1325_CR3","unstructured":"Ghodsi A, Zaharia M, Hindman B, Konwinski A, Shenker S, Stoica I. Dominant resource fairness: Fair allocation of multiple resource types. In: Proceedings of the 8 Th USENIX Symposium on Networked Systems Design and Implementation (NSDI). 2011; 11:323\u2013336"},{"issue":"4","key":"1325_CR4","doi-asserted-by":"publisher","first-page":"455","DOI":"10.1145\/2740070.2626334","volume":"44","author":"R Grandl","year":"2014","unstructured":"Grandl R, Ananthanarayanan G, Kandula S, Rao S, Akella A. Multi-resource packing for cluster schedulers. ACM SIGCOMM Comput Commun Rev. 2014;44(4):455\u201366.","journal-title":"ACM SIGCOMM Comput Commun Rev"},{"key":"1325_CR5","doi-asserted-by":"crossref","unstructured":"Park JW, Tumanov A, Jiang A, Kozuch MA, Ganger GR. 3sigma: distribution-based cluster scheduling for runtime uncertainty. In: Proceedings of the Thirteenth EuroSys Conference, Porto,Portugal. 2018; 1\u201317. ACM","DOI":"10.1145\/3190508.3190515"},{"issue":"10","key":"1325_CR6","doi-asserted-by":"publisher","first-page":"3202","DOI":"10.1016\/j.cor.2007.02.014","volume":"35","author":"F Pezzella","year":"2008","unstructured":"Pezzella F, Morganti G, Ciaschetti G. A genetic algorithm for the flexible job-shop scheduling problem. Comput Oper Res. 2008;35(10):3202\u201312.","journal-title":"Comput Oper Res"},{"issue":"4","key":"1325_CR7","doi-asserted-by":"publisher","first-page":"333","DOI":"10.1109\/TEVC.2002.802450","volume":"6","author":"D Merkle","year":"2002","unstructured":"Merkle D, Middendorf M, Schmeck H. Ant colony optimization for resource-constrained project scheduling. IEEE Trans Evol Comput. 2002;6(4):333\u201346.","journal-title":"IEEE Trans Evol Comput"},{"key":"1325_CR8","doi-asserted-by":"crossref","unstructured":"Pandey S, Wu L, Guru SM, Buyya R. A particle swarm optimization-based heuristic for scheduling workflow applications in cloud computing environments. In: 2010 24th IEEE International Conference on Advanced Information Networking and Applications. 2010;400\u2013407. IEEE","DOI":"10.1109\/AINA.2010.31"},{"issue":"1","key":"1325_CR9","doi-asserted-by":"publisher","first-page":"1087","DOI":"10.1007\/s10586-017-1055-5","volume":"22","author":"K Sreenu","year":"2019","unstructured":"Sreenu K, Sreelatha M. W-scheduler: whale optimization for task scheduling in cloud computing. Cluster Comput. 2019;22(1):1087\u201398.","journal-title":"Cluster Comput"},{"key":"1325_CR10","doi-asserted-by":"publisher","first-page":"301","DOI":"10.1007\/s10586-018-2856-x","volume":"22","author":"SHH Madni","year":"2019","unstructured":"Madni SHH, Abd Latiff MS, Abdulhamid SM, Ali J. Hybrid gradient descent cuckoo search (hgdcs) algorithm for resource scheduling in iaas cloud computing environment. Cluster Comput. 2019;22:301\u201334.","journal-title":"Cluster Comput"},{"key":"1325_CR11","volume-title":"Reinforcement learning: an introduction","author":"RS Sutton","year":"2018","unstructured":"Sutton RS, Barto AG. Reinforcement learning: an introduction. Cambridge: MIT press; 2018."},{"issue":"6","key":"1325_CR12","doi-asserted-by":"publisher","first-page":"3103","DOI":"10.1109\/TCYB.2020.2977661","volume":"51","author":"K Li","year":"2020","unstructured":"Li K, Zhang T, Wang R. Deep reinforcement learning for multiobjective optimization. IEEE Trans Cybern. 2020;51(6):3103\u201314.","journal-title":"IEEE Trans Cybern"},{"key":"1325_CR13","unstructured":"Zhang W, Dietterich TG. A reinforcement learning approach to job-shop scheduling. In: IJCAI. 1995;95:1114\u20131120."},{"key":"1325_CR14","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.121756","volume":"238","author":"J-P Huang","year":"2024","unstructured":"Huang J-P, Gao L, Li X-Y. An end-to-end deep reinforcement learning method based on graph neural network for distributed job-shop scheduling problem. Expert Syst Appl. 2024;238:121756.","journal-title":"Expert Syst Appl"},{"key":"1325_CR15","doi-asserted-by":"publisher","first-page":"292","DOI":"10.1016\/j.jpdc.2017.05.001","volume":"117","author":"AI Orhean","year":"2018","unstructured":"Orhean AI, Pop F, Raicu I. New scheduling approach using reinforcement learning for heterogeneous distributed systems. J Parallel Distrib Comput. 2018;117:292\u2013302.","journal-title":"J Parallel Distrib Comput"},{"issue":"6","key":"1325_CR16","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1109\/MSP.2012.2205597","volume":"29","author":"G Hinton","year":"2012","unstructured":"Hinton G, Deng L, Yu D, Dahl GE, Mohamed A-R, Jaitly N, et al. Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups. IEEE Signal Process Mag. 2012;29(6):82\u201397.","journal-title":"IEEE Signal Process Mag"},{"issue":"6","key":"1325_CR17","doi-asserted-by":"publisher","first-page":"643","DOI":"10.1007\/s11633-018-1136-9","volume":"15","author":"Z-J Yao","year":"2018","unstructured":"Yao Z-J, Bi J, Chen Y-X. Applying deep learning to individual and community health monitoring data: a survey. Int J Autom Comput. 2018;15(6):643\u201355.","journal-title":"Int J Autom Comput"},{"issue":"7587","key":"1325_CR18","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1038\/nature16961","volume":"529","author":"D Silver","year":"2016","unstructured":"Silver D, Huang A, Maddison CJ, Guez A, Sifre L, Driessche GVD, et al. Mastering the game of go with deep neural networks and tree search. Nature. 2016;529(7587):484\u20139.","journal-title":"Nature"},{"issue":"7540","key":"1325_CR19","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"M Volodymyr","year":"2015","unstructured":"Volodymyr M, Kavukcuoglu K, Silver D, Rusu AA, Veness J, Bellemare MG, et al. Human-level control through deep reinforcement learning. Nature. 2015;518(7540):529\u201333.","journal-title":"Nature"},{"key":"1325_CR20","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2024.109784","volume":"120","author":"Z Jiang","year":"2024","unstructured":"Jiang Z, Li Z, Yao Z. Multi-objective optimization in fixed-outline floorplanning with reinforcement learning. Comput Electr Eng. 2024;120:109784.","journal-title":"Comput Electr Eng"},{"key":"1325_CR21","doi-asserted-by":"crossref","unstructured":"Mao H, Alizadeh M, Menache I, Kandula S. Resource management with deep reinforcement learning. In: Proceedings of the 15th ACM Workshop on Hot Topics in Networks. 2016; 50\u201356.","DOI":"10.1145\/3005745.3005750"},{"key":"1325_CR22","doi-asserted-by":"crossref","unstructured":"Mao H, Schwarzkopf M, Venkatakrishnan SB, Meng Z, Alizadeh M. Learning scheduling algorithms for data processing clusters. In: Proceedings of the ACM Special Interest Group on Data Communication. 2019; 270\u2013288.","DOI":"10.1145\/3341302.3342080"},{"key":"1325_CR23","unstructured":"Chen W, Xu Y, Wu X. Deep reinforcement learning for multi-resource multi-machine job scheduling. 2017. arXiv preprint arXiv:1711.07440."},{"key":"1325_CR24","doi-asserted-by":"publisher","first-page":"613","DOI":"10.1007\/978-3-030-86380-7_50","volume-title":"Artificial neural networks and machine learning - ICANN 2021","author":"Z Yao","year":"2021","unstructured":"Yao Z, Chen L, Zhang H. Deep reinforcement learning for job scheduling on cluster. In: Farka\u0161 I, Masulli P, Otte S, Wermter S, editors. Artificial neural networks and machine learning - ICANN 2021. Cham: Springer; 2021. p. 613\u201324."},{"key":"1325_CR25","doi-asserted-by":"publisher","first-page":"153432","DOI":"10.1109\/ACCESS.2019.2948150","volume":"7","author":"M Cheong","year":"2019","unstructured":"Cheong M, Lee H, Yeom I, Woo H. Scarl: attentive reinforcement learning-based scheduling in a multi-resource heterogeneous cluster. IEEE Access. 2019;7:153432\u201344. https:\/\/doi.org\/10.1109\/ACCESS.2019.2948150.","journal-title":"IEEE Access"},{"key":"1325_CR26","doi-asserted-by":"publisher","first-page":"906","DOI":"10.1007\/978-3-030-47436-2_68","volume-title":"Pacific-Asia conference on knowledge discovery and data mining","author":"S Liang","year":"2020","unstructured":"Liang S, Yang Z, Jin F, Chen Y. Data centers job scheduling with deep reinforcement learning. In: Lauw H, Wong RW, Ntoulas A, Lim EP, Ng SK, Pan S, editors. Pacific-Asia conference on knowledge discovery and data mining. Cham: Springer; 2020. p. 906\u201317."},{"key":"1325_CR27","doi-asserted-by":"crossref","unstructured":"Grinsztajn N, Beaumont O, Jeannot E, Preux P. Readys: a reinforcement learning based strategy for heterogeneous dynamic scheduling. In: 2021 IEEE International Conference on Cluster Computing (CLUSTER). 2021; 70\u201381. IEEE.","DOI":"10.1109\/Cluster48925.2021.00031"},{"key":"1325_CR28","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2022.3213575","author":"W Wei","year":"2022","unstructured":"Wei W, Gu H, Wang K, Li J, Zhang X, Wang N. Multi-dimensional resource allocation in distributed data centers using deep reinforcement learning. IEEE Trans Netw Serv Manag. 2022. https:\/\/doi.org\/10.1109\/TNSM.2022.3213575.","journal-title":"IEEE Trans Netw Serv Manag"},{"issue":"8","key":"1325_CR29","doi-asserted-by":"publisher","first-page":"1911","DOI":"10.1109\/TPDS.2021.3132422","volume":"33","author":"Z Chen","year":"2022","unstructured":"Chen Z, Hu J, Min G, Luo C, El-Ghazawi T. Adaptive and efficient resource allocation in cloud datacenters using actor-critic deep reinforcement learning. IEEE Trans Parallel Distrib Syst. 2022;33(8):1911\u201323.","journal-title":"IEEE Trans Parallel Distrib Syst"},{"key":"1325_CR30","doi-asserted-by":"crossref","unstructured":"Qiu H, Mao W, Patke A, Wang C, Franke H, Kalbarczyk ZT, Ba\u015far T, Iyer RK. Simppo: a scalable and incremental online learning framework for serverless resource management. In: Proceedings of the 13th Symposium on Cloud Computing. 2022; 306\u2013322.","DOI":"10.1145\/3542929.3563475"},{"key":"1325_CR31","doi-asserted-by":"crossref","unstructured":"Yanghua P, Yixin B, Yangrui C, Chuan W, Chuanxiong G. Optimus: an efficient dynamic resource scheduler for deep learning clusters. In: Proceedings of the Thirteenth EuroSys Conference. 2018; 1\u201314.","DOI":"10.1145\/3190508.3190517"},{"key":"1325_CR32","unstructured":"Yanghua P, Bao Y, Chen Y, Wu C, Meng C, Lin W. Dl2: a deep learning-driven scheduler for deep learning clusters. In: arXiv Preprint. 2019. Available: https:\/\/arxiv.org\/abs\/1909.06040"},{"key":"1325_CR33","doi-asserted-by":"crossref","unstructured":"Bao Y, Peng Y, Wu C. Deep learning-based job placement in distributed machine learning clusters. In: IEEE INFOCOM 2019-IEEE Conference on Computer Communications. 2019; 505\u2013513. IEEE.","DOI":"10.1109\/INFOCOM.2019.8737460"},{"key":"1325_CR34","doi-asserted-by":"publisher","first-page":"39974","DOI":"10.1109\/ACCESS.2019.2902846","volume":"7","author":"Y Wang","year":"2019","unstructured":"Wang Y, Liu H, Zheng W, Xia Y, Li Y, Chen P, et al. Multi-objective workflow scheduling with deep-q-network-based multi-agent reinforcement learning. IEEE Access. 2019;7:39974\u201382.","journal-title":"IEEE Access"},{"key":"1325_CR35","unstructured":"Narayanan D, Santhanam K, Kazhamiaka F, Phanishayee A, Zaharia M. Heterogeneity-aware cluster scheduling policies for deep learning workloads. In: 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20). 2020; 481\u2013498. USENIX Association, Virtual."},{"issue":"1","key":"1325_CR36","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1109\/TPDS.2021.3079202","volume":"33","author":"G Yeung","year":"2022","unstructured":"Yeung G, Borowiec D, Yang R, Friday A, Harper R, Garraghan P. Horus: interference-aware and prediction-based scheduling in deep learning systems. IEEE Trans Parallel Distrib Syst. 2022;33(1):88\u2013100.","journal-title":"IEEE Trans Parallel Distrib Syst"},{"issue":"1","key":"1325_CR37","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1109\/TNET.2022.3190797","volume":"31","author":"H Wang","year":"2022","unstructured":"Wang H, Liu Z, Shen H. Machine learning feature based job scheduling for distributed machine learning clusters. IEEE ACM Trans Netw. 2022;31(1):58\u201373.","journal-title":"IEEE ACM Trans Netw"},{"issue":"9","key":"1325_CR38","doi-asserted-by":"publisher","first-page":"3040","DOI":"10.1109\/TCAD.2021.3120534","volume":"41","author":"A Hosny","year":"2022","unstructured":"Hosny A, Reda S. Characterizing and optimizing EDA flows for the cloud. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems. 2022;41(9):3040\u201351.","journal-title":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems"},{"issue":"2","key":"1325_CR39","doi-asserted-by":"publisher","first-page":"7452","DOI":"10.1002\/cpe.7452","volume":"35","author":"Q Qiao","year":"2023","unstructured":"Qiao Q, Chen L, Cai H, Zhang H, Yao Z. An online workflow scheduling algorithm considering license limitation in heterogeneous environment. Concurr Comput Pract Experience. 2023;35(2):7452.","journal-title":"Concurr Comput Pract Experience"},{"key":"1325_CR40","unstructured":"Sutton RS, Mcallester D, Singh S, Mansour Y. Policy gradient methods for reinforcement learning with function approximation. In: Advances in Neural Information Processing Systems. 1999; 1057\u20131063."},{"issue":"1","key":"1325_CR41","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1093\/biomet\/57.1.97","volume":"57","author":"WK Hastings","year":"1970","unstructured":"Hastings WK. Monte Carlo sampling methods using Markov chains and their applications. Biometrika. 1970;57(1):97\u2013109.","journal-title":"Biometrika"}],"container-title":["Journal of Big Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s40537-025-01325-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s40537-025-01325-0","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s40537-025-01325-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,23]],"date-time":"2025-12-23T14:30:55Z","timestamp":1766500255000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s40537-025-01325-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,23]]},"references-count":41,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["1325"],"URL":"https:\/\/doi.org\/10.1186\/s40537-025-01325-0","relation":{},"ISSN":["2196-1115"],"issn-type":[{"value":"2196-1115","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,23]]},"assertion":[{"value":"6 June 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 October 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 December 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The data are simulated according to our own cluster, no consent required.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"The authors declare no competing interests.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"276"}}