{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T18:46:27Z","timestamp":1774291587403,"version":"3.50.1"},"reference-count":66,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2023,11,6]],"date-time":"2023-11-06T00:00:00Z","timestamp":1699228800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,11,6]],"date-time":"2023-11-06T00:00:00Z","timestamp":1699228800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100009224","name":"Advanced Research Projects Agency","doi-asserted-by":"publisher","award":["OPEN 2018 Program"],"award-info":[{"award-number":["OPEN 2018 Program"]}],"id":[{"id":"10.13039\/100009224","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Mach Learn"],"published-print":{"date-parts":[[2024,5]]},"DOI":"10.1007\/s10994-023-06422-w","type":"journal-article","created":{"date-parts":[[2023,11,6]],"date-time":"2023-11-06T17:01:42Z","timestamp":1699290102000},"page":"2675-2700","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":21,"title":["Efficient learning of power grid voltage control strategies via model-based deep reinforcement learning"],"prefix":"10.1007","volume":"113","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0224-7245","authenticated-orcid":false,"given":"Ramij Raja","family":"Hossain","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0730-4309","authenticated-orcid":false,"given":"Tianzhixi","family":"Yin","sequence":"additional","affiliation":[]},{"given":"Yan","family":"Du","sequence":"additional","affiliation":[]},{"given":"Renke","family":"Huang","sequence":"additional","affiliation":[]},{"given":"Jie","family":"Tan","sequence":"additional","affiliation":[]},{"given":"Wenhao","family":"Yu","sequence":"additional","affiliation":[]},{"given":"Yuan","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Qiuhua","family":"Huang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,11,6]]},"reference":[{"key":"6422_CR1","doi-asserted-by":"publisher","DOI":"10.1787\/5f517ddb-en","volume-title":"An energy sector roadmap to carbon neutrality in China","author":"IE Agency","year":"2021","unstructured":"International Energy Agency (2021). An energy sector roadmap to carbon neutrality in China. OECD Publishing."},{"key":"6422_CR2","doi-asserted-by":"crossref","unstructured":"Atkeson, C. G., & Santamaria, J. C. (1997). A comparison of direct and model-based reinforcement learning. In Proceedings of international conference on robotics and automation (Vol. 4, pp. 3557\u20133564).","DOI":"10.1109\/ROBOT.1997.606886"},{"key":"6422_CR3","unstructured":"Australian Energy Market Operator (2017). Black system South Australia 28 September 2016: Final report. https:\/\/aemo.com.au\/"},{"issue":"1","key":"6422_CR4","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s42162-018-0066-7","volume":"2","author":"S Balduin","year":"2019","unstructured":"Balduin, S., Tr\u00f6schel, M., & Lehnhoff, S. (2019). Towards domain-specific surrogate models for smart grid co-simulation. Energy Informatics, 2(1), 1\u201319.","journal-title":"Energy Informatics"},{"key":"6422_CR5","unstructured":"Birol, F., & Kant, A. (2022). India\u2019s clean energy transition is rapidly underway, benefiting the entire world."},{"key":"6422_CR6","doi-asserted-by":"crossref","unstructured":"Brosinsky, C., Westermann, D., & Krebs, R. (2018). Recent and prospective developments in power system control centers: Adapting the digital twin technology for application in power system control centers. In 2018 IEEE international energy conference (ENERGYCON) (pp. 1\u20136).","DOI":"10.1109\/ENERGYCON.2018.8398846"},{"key":"6422_CR7","unstructured":"California ISO (2013). California ISO-fast facts. https:\/\/www.caiso.com\/documents\/flexibleresourceshelprenewables_fastfacts.pdf"},{"issue":"6","key":"6422_CR8","doi-asserted-by":"publisher","first-page":"1029","DOI":"10.35833\/MPCE.2020.000552","volume":"8","author":"D Cao","year":"2020","unstructured":"Cao, D., Hu, W., Zhao, J., Zhang, G., Zhang, B., Liu, Z., Chen, Z., & Blaabjerg, F. (2020). Reinforcement learning and its applications in modern power and energy systems: A review. Journal of Modern Power Systems and Clean Energy, 8(6), 1029\u20131042.","journal-title":"Journal of Modern Power Systems and Clean Energy"},{"issue":"8","key":"6422_CR9","doi-asserted-by":"publisher","first-page":"1556","DOI":"10.3390\/en12081556","volume":"12","author":"J Cao","year":"2019","unstructured":"Cao, J., Zhang, W., Xiao, Z., & Hua, H. (2019). Reactive power optimization for transient voltage stability in energy internet via deep reinforcement learning approach. Energies, 12(8), 1556.","journal-title":"Energies"},{"key":"6422_CR10","doi-asserted-by":"publisher","first-page":"117982","DOI":"10.1016\/j.apenergy.2021.117982","volume":"306","author":"D Cao","year":"2022","unstructured":"Cao, D., Zhao, J., Hu, W., Ding, F., Yu, N., Huang, Q., & Chen, Z. (2022). Model-free voltage control of active distribution system with PVs using surrogate model-based deep reinforcement learning. Applied Energy, 306, 117982.","journal-title":"Applied Energy"},{"issue":"4","key":"6422_CR11","doi-asserted-by":"publisher","first-page":"2336","DOI":"10.1109\/TII.2020.3001095","volume":"17","author":"C Chen","year":"2020","unstructured":"Chen, C., Cui, M., Li, F., Yin, S., & Wang, X. (2020). Model-free emergency frequency control based on reinforcement learning. IEEE Transactions on Industrial Informatics, 17(4), 2336\u20132346.","journal-title":"IEEE Transactions on Industrial Informatics"},{"issue":"4","key":"6422_CR12","doi-asserted-by":"publisher","first-page":"2935","DOI":"10.1109\/TSG.2022.3154718","volume":"13","author":"X Chen","year":"2022","unstructured":"Chen, X., Qu, G., Tang, Y., Low, S., & Li, N. (2022). Reinforcement learning for selective key applications in power systems: Recent advances and future challenges. IEEE Transactions on Smart Grid, 13(4), 2935\u20132958.","journal-title":"IEEE Transactions on Smart Grid"},{"key":"6422_CR13","unstructured":"Deisenroth, M., & Rasmussen, C. E. (2011). Pilco: A model-based and data-efficient approach to policy search. In Proceedings of the 28th international conference on machine learning (ICML-11) (pp. 465\u2013472)."},{"issue":"1","key":"6422_CR14","doi-asserted-by":"publisher","first-page":"814","DOI":"10.1109\/TPWRS.2019.2941134","volume":"35","author":"J Duan","year":"2019","unstructured":"Duan, J., Shi, D., Diao, R., Li, H., Wang, Z., Zhang, B., Bian, D., & Yi, Z. (2019). Deep-reinforcement-learning-based autonomous voltage control for power grid operations. IEEE Transactions on Power Systems, 35(1), 814\u2013817.","journal-title":"IEEE Transactions on Power Systems"},{"key":"6422_CR15","unstructured":"Fetting, C. (2020), The european green deal. ESDN Report, December (2020)"},{"key":"6422_CR16","doi-asserted-by":"publisher","first-page":"118762","DOI":"10.1016\/j.apenergy.2022.118762","volume":"313","author":"Y Gao","year":"2022","unstructured":"Gao, Y., & Yu, N. (2022). Model-augmented safe reinforcement learning for Volt\u2013VAR control in power distribution networks. Applied Energy, 313, 118762.","journal-title":"Applied Energy"},{"key":"6422_CR17","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1016\/j.arcontrol.2019.09.008","volume":"48","author":"M Glavic","year":"2019","unstructured":"Glavic, M. (2019). (Deep) reinforcement learning for electric power system control and related problems: A short review and perspectives. Annual Reviews in Control, 48, 22\u201335.","journal-title":"Annual Reviews in Control"},{"issue":"4","key":"6422_CR18","doi-asserted-by":"publisher","first-page":"3271","DOI":"10.1109\/TPWRS.2020.3041774","volume":"36","author":"N Hatziargyriou","year":"2021","unstructured":"Hatziargyriou, N., Milanovic, J., Rahmann, C., Ajjarapu, V., Canizares, C., Erlich, I., Hill, D., Hiskens, I., Kamwa, I., Pal, B., Pourbeik, P., Sanchez-Gasca, J., Stankovic, A., Van Cutsem, T., Vittal, V., & Vournas, C. (2021). Definition and classification of power system stability-revisited and extended. IEEE Transactions on Power Systems, 36(4), 3271\u20133281.","journal-title":"IEEE Transactions on Power Systems"},{"key":"6422_CR19","doi-asserted-by":"publisher","first-page":"4848","DOI":"10.1109\/TPWRS.2021.3084469","volume":"36","author":"RR Hossain","year":"2021","unstructured":"Hossain, R. R., Huang, Q., & Huang, R. (2021). Graph convolutional network-based topology embedded deep reinforcement learning for voltage stability control. IEEE Transactions on Power Systems, 36, 4848\u20134851.","journal-title":"IEEE Transactions on Power Systems"},{"key":"6422_CR20","doi-asserted-by":"crossref","unstructured":"Huang, R., Jin, S., Chen, Y., Diao, R., Palmer, B., Huang, Q., & Huang, Z. (2017). Faster than real-time dynamic simulation for large-size power system with detailed dynamic models using high-performance computing platform. In 2017 IEEE power and energy society general meeting (pp. 1\u20135).","DOI":"10.1109\/PESGM.2017.8274505"},{"key":"6422_CR21","doi-asserted-by":"publisher","first-page":"4168","DOI":"10.1109\/TPWRS.2022.3155117","volume":"37","author":"R Huang","year":"2022","unstructured":"Huang, R., Chen, Y., Yin, T., Huang, Q., Tan, J., Yu, W., Li, X., Li, A., & Du, Y. (2022). Learning and fast adaptation for grid emergency control via deep meta reinforcement learning. IEEE Transactions on Power Systems, 37, 4168\u20134178.","journal-title":"IEEE Transactions on Power Systems"},{"issue":"1","key":"6422_CR22","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1109\/TPWRS.2021.3095179","volume":"37","author":"R Huang","year":"2021","unstructured":"Huang, R., Chen, Y., Yin, T., Li, X., Li, A., Tan, J., Yu, W., Liu, Y., & Huang, Q. (2021). Accelerated derivative-free deep reinforcement learning for large-scale grid emergency voltage control. IEEE Transactions on Power Systems, 37(1), 14\u201325.","journal-title":"IEEE Transactions on Power Systems"},{"issue":"2","key":"6422_CR23","doi-asserted-by":"publisher","first-page":"1171","DOI":"10.1109\/TSG.2019.2933191","volume":"11","author":"Q Huang","year":"2019","unstructured":"Huang, Q., Huang, R., Hao, W., Tan, J., Fan, R., & Huang, Z. (2019). Adaptive power system emergency control using deep reinforcement learning. IEEE Transactions on Smart Grid, 11(2), 1171\u20131182.","journal-title":"IEEE Transactions on Smart Grid"},{"key":"6422_CR24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.epsr.2019.02.027","volume":"172","author":"Q Huang","year":"2019","unstructured":"Huang, Q., Huang, R., Palmer, B. J., Liu, Y., Jin, S., Diao, R., Chen, Y., & Zhang, Y. (2019). A generic modeling and development approach for WECC composite load model. Electric Power Systems Research, 172, 1\u201310.","journal-title":"Electric Power Systems Research"},{"issue":"2","key":"6422_CR25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3054912","volume":"50","author":"A Hussein","year":"2017","unstructured":"Hussein, A., Gaber, M. M., Elyan, E., & Jayne, C. (2017). Imitation learning: A survey of learning methods. ACM Computing Surveys, 50(2), 1\u201325.","journal-title":"ACM Computing Surveys"},{"key":"6422_CR26","doi-asserted-by":"crossref","unstructured":"Jiang, C., Li, Z., Zheng, J., & Wu, Q. (2019). Power system emergency control to improve short-term voltage stability using deep reinforcement learning algorithm. In 2019 IEEE 3rd international electrical and energy conference (CIEEC) (pp. 1872\u20131877).","DOI":"10.1109\/CIEEC47146.2019.CIEEC-2019640"},{"issue":"3","key":"6422_CR27","first-page":"433","volume":"7","author":"M Kamel","year":"2021","unstructured":"Kamel, M., Dai, R., Wang, Y., Li, F., & Liu, G. (2021). Data-driven and model-based hybrid reinforcement learning to reduce stress on power systems branches. CSEE Journal of Power and Energy Systems, 7(3), 433\u2013442.","journal-title":"CSEE Journal of Power and Energy Systems"},{"issue":"6","key":"6422_CR28","doi-asserted-by":"publisher","first-page":"5525","DOI":"10.1109\/TPWRS.2021.3078446","volume":"36","author":"M Kamruzzaman","year":"2021","unstructured":"Kamruzzaman, M., Duan, J., Shi, D., & Benidris, M. (2021). A deep reinforcement learning-based multi-agent framework to enhance power system resilience using shunt resources. IEEE Transactions on Power Systems, 36(6), 5525\u20135536.","journal-title":"IEEE Transactions on Power Systems"},{"key":"6422_CR29","first-page":"1175","volume":"8","author":"J Li","year":"2021","unstructured":"Li, J., Chen, S., Wang, X., & Pu, T. (2021). Research on load shedding control strategy in power grid emergency state based on deep reinforcement learning. CSEE Journal of Power and Energy Systems, 8, 1175\u20131182.","journal-title":"CSEE Journal of Power and Energy Systems"},{"key":"6422_CR30","doi-asserted-by":"publisher","first-page":"108127","DOI":"10.1016\/j.ijepes.2022.108127","volume":"141","author":"B Lin","year":"2022","unstructured":"Lin, B., Wang, H., Zhang, Y., & Wen, B. (2022). Real-time power system generator tripping control based on deep reinforcement learning. International Journal of Electrical Power and Energy Systems, 141, 108127.","journal-title":"International Journal of Electrical Power and Energy Systems"},{"key":"6422_CR31","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1016\/j.neucom.2021.12.043","volume":"475","author":"X Li","year":"2022","unstructured":"Li, X., Wang, X., Zheng, X., Dai, Y., Yu, Z., Zhang, J. J., Bu, G., & Wang, F.-Y. (2022). Supervised assisted deep reinforcement learning for emergency voltage control of power systems. Neurocomputing, 475, 69\u201379.","journal-title":"Neurocomputing"},{"key":"6422_CR32","unstructured":"Luo, F. -M., Xu, T., Lai, H., Chen, X. -H., Zhang, W., & Yu, Y. (2022). A survey on model-based reinforcement learning. arXiv:2206.09328"},{"issue":"1","key":"6422_CR33","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1080\/02286203.2019.1655701","volume":"41","author":"M Mahmoud","year":"2021","unstructured":"Mahmoud, M., Abouheaf, M., & Sharaf, A. (2021). Reinforcement learning control approach for autonomous microgrids. International Journal of Modelling and Simulation, 41(1), 1\u201310.","journal-title":"International Journal of Modelling and Simulation"},{"key":"6422_CR34","unstructured":"Mania, H., Guy, A., & Recht, B. (2018). Simple random search of static linear policies is competitive for reinforcement learning. In Advances in neural information processing systems (Vol. 31)."},{"key":"6422_CR35","unstructured":"Moritz, P., Nishihara, R., Wang, S., Tumanov, A., Liaw, R., Liang, E., Elibol, M., Yang, Z., Paul, W., Jordan, M. I., & Stoica, I., (2018). Ray: A distributed framework for emerging AI applications. In 13th USENIX symposium on operating systems design and implementation) (pp. 561\u2013577)."},{"key":"6422_CR36","unstructured":"Moya, C., Lin, G., Zhao, T., & Yue, M. (2023). On approximating the dynamic response of synchronous generators via operator learning: A step towards building deep operator-based power grid simulators. arXiv preprint arXiv:2301.12538"},{"key":"6422_CR37","doi-asserted-by":"crossref","unstructured":"Nagabandi, A., Kahn, G., Fearing, R. S., & Levine, S. (2018). Neural network dynamics for model-based deep reinforcement learning with model-free fine-tuning. In 2018 IEEE international conference on robotics and automation (ICRA) (pp. 7559\u20137566).","DOI":"10.1109\/ICRA.2018.8463189"},{"key":"6422_CR38","doi-asserted-by":"crossref","unstructured":"Nair, A., McGrew, B., Andrychowicz, M., Zaremba, W., & Abbeel, P. (2018). Overcoming exploration in reinforcement learning with demonstrations. In 2018 IEEE international conference on robotics and automation (ICRA) (pp. 6292\u20136299).","DOI":"10.1109\/ICRA.2018.8463162"},{"issue":"2\u20133","key":"6422_CR39","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1016\/j.robot.2004.03.003","volume":"47","author":"J Nakanishi","year":"2004","unstructured":"Nakanishi, J., Morimoto, J., Endo, G., Cheng, G., Schaal, S., & Kawato, M. (2004). Learning from demonstration and adaptation of biped locomotion. Robotics and Autonomous Systems, 47(2\u20133), 79\u201391.","journal-title":"Robotics and Autonomous Systems"},{"key":"6422_CR40","doi-asserted-by":"publisher","first-page":"110618","DOI":"10.1016\/j.rser.2020.110618","volume":"137","author":"A Perera","year":"2021","unstructured":"Perera, A., & Kamalaruban, P. (2021). Applications of reinforcement learning in energy systems. Renewable and Sustainable Energy Reviews, 137, 110618.","journal-title":"Renewable and Sustainable Energy Reviews"},{"key":"6422_CR41","unstructured":"PJM (2021). Exelon transmission planning criteria. https:\/\/www.pjm.com\/-\/media\/planning\/planning-criteria\/exelon-planning-criteria.ashx?la=en"},{"key":"6422_CR42","unstructured":"Plappert, M., Houthooft, R., Dhariwal, P., Sidor, S., Chen, R. Y., Chen, X., Asfour, T., Abbeel, P., & Andrychowicz, M. (2017). Parameter space noise for exploration. arXiv preprint arXiv:1706.01905"},{"key":"6422_CR43","unstructured":"Pomerleau, D. A. (1988). Alvinn: An autonomous land vehicle in a neural network. In Advances in neural information processing systems (Vol. 1, pp. 305\u2013313)."},{"issue":"2","key":"6422_CR44","doi-asserted-by":"publisher","first-page":"791","DOI":"10.1109\/TPWRS.2006.873022","volume":"21","author":"EG Potamianakis","year":"2006","unstructured":"Potamianakis, E. G., & Vournas, C. D. (2006). Short-term voltage instability: Effects on synchronous and induction machines. IEEE Transactions on Power Systems, 21(2), 791\u2013798.","journal-title":"IEEE Transactions on Power Systems"},{"key":"6422_CR45","doi-asserted-by":"publisher","first-page":"3507","DOI":"10.1109\/TPWRS.2020.3041866","volume":"36","author":"G Qiu","year":"2020","unstructured":"Qiu, G., Liu, Y., Zhao, J., Liu, J., Wang, L., Liu, T., & Gao, H. (2020). Analytic deep learning-based surrogate model for operational planning with dynamic TTC constraints. IEEE Transactions on Power Systems, 36, 3507\u20133519.","journal-title":"IEEE Transactions on Power Systems"},{"issue":"1","key":"6422_CR46","first-page":"12348","volume":"22","author":"A Raffin","year":"2021","unstructured":"Raffin, A., Hill, A., Gleave, A., Kanervisto, A., Ernestus, M., & Dormann, N. (2021). Stable-baselines3: Reliable reinforcement learning implementations. The Journal of Machine Learning Research, 22(1), 12348\u201312355.","journal-title":"The Journal of Machine Learning Research"},{"key":"6422_CR47","doi-asserted-by":"publisher","first-page":"106817","DOI":"10.1016\/j.ress.2020.106817","volume":"197","author":"R Rocchetta","year":"2020","unstructured":"Rocchetta, R., & Patelli, E. (2020). A post-contingency power flow emulator for generalized probabilistic risks assessment of power grids. Reliability Engineering and System Safety, 197, 106817.","journal-title":"Reliability Engineering and System Safety"},{"key":"6422_CR48","doi-asserted-by":"publisher","first-page":"339","DOI":"10.1016\/j.apenergy.2017.10.126","volume":"210","author":"R Rocchetta","year":"2018","unstructured":"Rocchetta, R., Zio, E., & Patelli, E. (2018). A power-flow emulator approach for resilience assessment of repairable power grids subject to weather-induced failures and data deficiency. Applied energy, 210, 339\u2013350.","journal-title":"Applied energy"},{"key":"6422_CR49","unstructured":"Ross, S., Gordon, G., & Bagnell, D. (2011). A reduction of imitation learning and structured prediction to no-regret online learning. In Proceedings of the fourteenth international conference on artificial intelligence and statistics (pp. 627\u2013635)."},{"key":"6422_CR50","first-page":"1040","volume":"9","author":"S Schaal","year":"1997","unstructured":"Schaal, S., et al. (1997). Learning from demonstration. Advances in Neural Information Processing Systems, 9, 1040\u20131046.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"6422_CR51","unstructured":"Schneider, J. G. (1997). Exploiting model uncertainty estimates for safe dynamic control learning. In Advances in neural information processing systems (pp. 1047\u20131053)."},{"issue":"2","key":"6422_CR52","doi-asserted-by":"publisher","first-page":"1073","DOI":"10.1109\/TSG.2020.3035127","volume":"12","author":"H Shuai","year":"2020","unstructured":"Shuai, H., & He, H. (2020). Online scheduling of a residential microgrid via Monte-Carlo tree search and a learned model. IEEE Transactions on Smart Grid, 12(2), 1073\u20131087.","journal-title":"IEEE Transactions on Smart Grid"},{"issue":"1","key":"6422_CR53","doi-asserted-by":"publisher","first-page":"315","DOI":"10.1109\/TII.2021.3072594","volume":"18","author":"T Su","year":"2021","unstructured":"Su, T., Liu, Y., Zhao, J., & Liu, J. (2021). Deep belief network enabled surrogate modeling for fast preventive control of power system transient stability. IEEE Transactions on Industrial Informatics, 18(1), 315\u2013326.","journal-title":"IEEE Transactions on Industrial Informatics"},{"key":"6422_CR54","doi-asserted-by":"publisher","first-page":"286","DOI":"10.1016\/j.ijepes.2019.04.011","volume":"111","author":"J Sun","year":"2019","unstructured":"Sun, J., Zhu, Z., Li, H., Chai, Y., Qi, G., Wang, H., & Hu, Y. H. (2019). An integrated critic-actor neural network for reinforcement learning with application of DERs control in grid frequency regulation. International Journal of Electrical Power and Energy Systems, 111, 286\u2013299.","journal-title":"International Journal of Electrical Power and Energy Systems"},{"key":"6422_CR55","volume-title":"Reinforcement Learning: An Introduction","author":"R Sutton","year":"2018","unstructured":"Sutton, R., & Barto, A. (2018). Reinforcement learning: An introduction. MIT Press."},{"issue":"2","key":"6422_CR56","doi-asserted-by":"publisher","first-page":"480","DOI":"10.1109\/61.127040","volume":"7","author":"CW Taylor","year":"1992","unstructured":"Taylor, C. W. (1992). Concepts of undervoltage load shedding for voltage stability. IEEE Transactions on Power Delivery, 7(2), 480\u2013488.","journal-title":"IEEE Transactions on Power Delivery"},{"key":"6422_CR57","unstructured":"United Nations (2023). Intergovernmental Panel on Climate Change longer report. https:\/\/www.ipcc.ch\/report\/ar6\/syr\/"},{"key":"6422_CR58","unstructured":"US Department of Energy (2021). How we\u2019re moving to net-zero by 2050. https:\/\/www.energy.gov\/articles\/how-were-moving-net-zero-2050"},{"key":"6422_CR59","unstructured":"Vu, T. L., Mukherjee, S., Huang, R., & Huang, Q. (2021). Safe reinforcement learning for grid voltage control. arXiv preprint arXiv:2112.01484"},{"key":"6422_CR60","unstructured":"Wang, T., Bao, X., Clavera, I., Hoang, J., Wen, Y., Langlois, E., Zhang, S., Zhang, G., Abbeel, P., & Ba, J. (2019). Benchmarking model-based reinforcement learning. arXiv preprint arXiv:1907.02057"},{"key":"6422_CR61","doi-asserted-by":"publisher","first-page":"116722","DOI":"10.1016\/j.apenergy.2021.116722","volume":"289","author":"X Wang","year":"2021","unstructured":"Wang, X., Liu, Y., Zhao, J., Liu, C., Liu, J., & Yan, J. (2021). Surrogate model enabled deep reinforcement learning for hybrid energy community operation. Applied Energy, 289, 116722.","journal-title":"Applied Energy"},{"key":"6422_CR62","doi-asserted-by":"publisher","first-page":"2720","DOI":"10.1109\/TPWRS.2021.3130413","volume":"37","author":"J Xie","year":"2021","unstructured":"Xie, J., & Sun, W. (2021). Distributional deep reinforcement learning-based emergency frequency control. IEEE Transactions on Power Systems, 37, 2720\u20132730.","journal-title":"IEEE Transactions on Power Systems"},{"key":"6422_CR63","unstructured":"Yang, Y., Caluwaerts, K., Iscen, A., Zhang, T., Tan, J., & Sindhwani, V. (2020). Data efficient reinforcement learning for legged robots. In Proceedings of the conference on robot learning. Proceedings of machine learning research (Vol. 100, pp. 1\u201310)."},{"issue":"2","key":"6422_CR64","doi-asserted-by":"publisher","first-page":"1653","DOI":"10.1109\/TPWRS.2018.2881359","volume":"34","author":"Z Yan","year":"2018","unstructured":"Yan, Z., & Xu, Y. (2018). Data-driven load frequency control for stochastic power systems: A deep reinforcement learning method with continuous action search. IEEE Transactions on Power Systems, 34(2), 1653\u20131656.","journal-title":"IEEE Transactions on Power Systems"},{"issue":"6","key":"6422_CR65","doi-asserted-by":"publisher","first-page":"4599","DOI":"10.1109\/TPWRS.2020.2999890","volume":"35","author":"Z Yan","year":"2020","unstructured":"Yan, Z., & Xu, Y. (2020). A multi-agent deep reinforcement learning method for cooperative load frequency control of a multi-area power system. IEEE Transactions on Power Systems, 35(6), 4599\u20134608.","journal-title":"IEEE Transactions on Power Systems"},{"key":"6422_CR66","doi-asserted-by":"crossref","unstructured":"Zhang, J., Lu, C., Fang, C., Ling, X., & Zhang, Y. (2018). Load shedding scheme with deep reinforcement learning to improve short-term voltage stability. In 2018 IEEE innovative smart grid technologies-Asia (ISGT Asia) (pp. 13\u201318).","DOI":"10.1109\/ISGT-Asia.2018.8467877"}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-023-06422-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10994-023-06422-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-023-06422-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:06:32Z","timestamp":1764266792000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10994-023-06422-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,6]]},"references-count":66,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2024,5]]}},"alternative-id":["6422"],"URL":"https:\/\/doi.org\/10.1007\/s10994-023-06422-w","relation":{},"ISSN":["0885-6125","1573-0565"],"issn-type":[{"value":"0885-6125","type":"print"},{"value":"1573-0565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11,6]]},"assertion":[{"value":"5 April 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 September 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 October 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 November 2023","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}