{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T20:20:34Z","timestamp":1774470034351,"version":"3.50.1"},"publisher-location":"Cham","reference-count":37,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032114419","type":"print"},{"value":"9783032114426","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T00:00:00Z","timestamp":1763942400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T00:00:00Z","timestamp":1763942400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-11442-6_4","type":"book-chapter","created":{"date-parts":[[2025,11,23]],"date-time":"2025-11-23T16:03:15Z","timestamp":1763913795000},"page":"51-65","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Soft Actor-Critic Reinforcement Learning for\u00a0Reactive Current Injection Protocols"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-5015-743X","authenticated-orcid":false,"given":"Mohana","family":"Fathollahi","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0673-6452","authenticated-orcid":false,"given":"Antonio","family":"Camacho","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9589-8199","authenticated-orcid":false,"given":"Cecilio","family":"Angulo","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1936-5387","authenticated-orcid":false,"given":"Jerrad","family":"Hampton","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,11,24]]},"reference":[{"key":"4_CR1","doi-asserted-by":"crossref","unstructured":"Murugesan, A., Durgadevi, K., Contractor, D., Rathod, Y.: Machine learning-driven intelligent voltage control in renewable-rich grids. J. Renew. Energy Syst. (2025). Graph-based MARL likely uses on-policy PG methods like PPO. https:\/\/www.sciencedirect.com\/science\/article\/abs\/pii\/S0378779625004602","DOI":"10.1016\/j.epsr.2025.111869"},{"key":"4_CR2","volume-title":"Learning and Sequential Decision Making","author":"AG Barto","year":"1989","unstructured":"Barto, A.G., Sutton, R.S., Watkins, C.: Learning and Sequential Decision Making, vol. 89. University of Massachusetts Amherst, MA (1989)"},{"key":"4_CR3","unstructured":"Brockman, G., et al.: OpenAI Gym. arXiv preprint arXiv:1606.01540 (2016)"},{"issue":"5","key":"4_CR4","doi-asserted-by":"publisher","first-page":"4120","DOI":"10.1109\/TPWRS.2020.3000652","volume":"35","author":"D Cao","year":"2020","unstructured":"Cao, D., Hu, W., Zhao, J., Huang, Q., Chen, Z., Blaabjerg, F.: A multi-agent deep reinforcement learning based voltage regulation using coordinated PV inverters. IEEE Trans. Power Syst. 35(5), 4120\u20134123 (2020)","journal-title":"IEEE Trans. Power Syst."},{"issue":"5","key":"4_CR5","doi-asserted-by":"publisher","first-page":"4137","DOI":"10.1109\/TSG.2021.3072251","volume":"12","author":"D Cao","year":"2021","unstructured":"Cao, D., et al.: Data-driven multi-agent deep reinforcement learning for distribution system decentralized voltage control with high penetration of PVs. IEEE Trans. Smart Grid 12(5), 4137\u20134150 (2021)","journal-title":"IEEE Trans. Smart Grid"},{"key":"4_CR6","doi-asserted-by":"crossref","unstructured":"Diao, R., Wang, Z., Shi, D., Chang, Q., Duan, J., Zhang, X.: Autonomous voltage control for grid operation using deep reinforcement learning. In: 2019 IEEE Power & Energy Society General Meeting (PESGM), pp.\u00a01\u20135. IEEE (2019)","DOI":"10.1109\/PESGM40551.2019.8973924"},{"key":"4_CR7","doi-asserted-by":"publisher","unstructured":"Fathollahi, M., Camacho\u00a0Santiago, A., Velasco, M., Mart\u00ed, P., Angulo\u00a0Bahon, C., Hampton, J.D.: Improving voltage ride-through procedures in distributed generation systems by reinforcement learning. In: Tall\u00f3n-Ballesteros, A. (ed.) Frontiers in Artificial Intelligence and Applications, pp. 274 \u2013 277. IOS Press (2024). https:\/\/doi.org\/10.3233\/FAIA240448","DOI":"10.3233\/FAIA240448"},{"key":"4_CR8","unstructured":"Fedus, W., et al.: Revisiting fundamentals of experience replay. In: International Conference on Machine Learning, pp. 3061\u20133071. PMLR (2020)"},{"key":"4_CR9","doi-asserted-by":"publisher","first-page":"109369","DOI":"10.1016\/j.rser.2019.109369","volume":"115","author":"A Fern\u00e1ndez-Guillam\u00f3n","year":"2019","unstructured":"Fern\u00e1ndez-Guillam\u00f3n, A., G\u00f3mez-L\u00e1zaro, E., Muljadi, E., Molina-Garc\u00eda, \u00c1.: Power systems with high renewable energy sources: a review of inertia and frequency control strategies over time. Renew. Sustain. Energy Rev. 115, 109369 (2019)","journal-title":"Renew. Sustain. Energy Rev."},{"issue":"1","key":"4_CR10","doi-asserted-by":"publisher","first-page":"6918","DOI":"10.1016\/j.ifacol.2017.08.1217","volume":"50","author":"M Glavic","year":"2017","unstructured":"Glavic, M., Fonteneau, R., Ernst, D.: Reinforcement learning for electric power system decision and control: past considerations and perspectives. IFAC-PapersOnLine 50(1), 6918\u20136927 (2017)","journal-title":"IFAC-PapersOnLine"},{"key":"4_CR11","unstructured":"Haarnoja, T., Tang, H., Abbeel, P., Levine, S.: Reinforcement learning with deep energy-based policies. In: International Conference on Machine Learning, pp. 1352\u20131361. PMLR (2017)"},{"key":"4_CR12","unstructured":"Haarnoja, T., et\u00a0al.: Soft actor-critic algorithms and applications. arXiv preprint arXiv:1812.05905 (2018)"},{"issue":"2","key":"4_CR13","doi-asserted-by":"publisher","first-page":"290","DOI":"10.1109\/TPWRS.2002.1007895","volume":"17","author":"P Heine","year":"2002","unstructured":"Heine, P., Pohjanheimo, P., Lehtonen, M., Lakervi, E.: A method for estimating the frequency and cost of voltage sags. IEEE Trans. Power Syst. 17(2), 290\u2013296 (2002)","journal-title":"IEEE Trans. Power Syst."},{"key":"4_CR14","unstructured":"Horton, H.: What caused the blackout in Spain and Portugal and did renewable energy play a part? (2025). http:\/\/bit.ly\/4ew5oFW"},{"key":"4_CR15","unstructured":"Hossain, R.R., et al.: Efficient learning of voltage control strategies via model-based deep reinforcement learning (2022). https:\/\/arxiv.org\/abs\/2212.02715"},{"issue":"10","key":"4_CR16","doi-asserted-by":"publisher","first-page":"11806","DOI":"10.1109\/TIE.2024.3349525","volume":"71","author":"JI I\u00f1iguez","year":"2024","unstructured":"I\u00f1iguez, J.I., Duarte, J.N., Camacho, A., Miret, J., Castilla, M.: Voltage support provided by three-phase three-wire inverters with independent reactive phase-current injection. IEEE Trans. Industr. Electron. 71(10), 11806\u201311816 (2024)","journal-title":"IEEE Trans. Industr. Electron."},{"key":"4_CR17","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: International Conference on Machine Learning, pp. 448\u2013456. PMLR (2015)"},{"key":"4_CR18","unstructured":"Jakob, W.: nanobind: tiny and efficient C++\/Python bindings (2022). https:\/\/github.com\/wjakob\/nanobind"},{"key":"4_CR19","doi-asserted-by":"publisher","first-page":"121804","DOI":"10.1109\/ACCESS.2021.3109050","volume":"9","author":"J Joshi","year":"2021","unstructured":"Joshi, J., Swami, A.K., Jately, V., Azzopardi, B.: A comprehensive review of control strategies to overcome challenges during LVRT in PV systems. IEEE Access 9, 121804\u2013121834 (2021)","journal-title":"IEEE Access"},{"issue":"2","key":"4_CR20","first-page":"3","volume":"1","author":"L Li","year":"2006","unstructured":"Li, L., Walsh, T.J., Littman, M.L.: Towards a unified theory of state abstraction for MDPs. AI &M 1(2), 3 (2006)","journal-title":"AI &M"},{"key":"4_CR21","unstructured":"Lowe, R., Wu, Y.I., Tamar, A., Harb, J., Pieter\u00a0Abbeel, O., Mordatch, I.: Multi-agent actor-critic for mixed cooperative-competitive environments. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"4_CR22","unstructured":"Oldeen, J., Sharma, V.: Reinforcement learning for grid voltage stability with FACTS. Master\u2019s thesis, University of Uppsala (2020). https:\/\/uu.diva-portal.org\/smash\/get\/diva2:1447070\/FULLTEXT01.pdf"},{"key":"4_CR23","doi-asserted-by":"crossref","unstructured":"Petrusev, A., Putratama, M.A., Rigo-Mariani, R., Debusschere, V., Reignier, P., Hadjsaid, N.: Reinforcement learning for robust voltage control in distribution grid under uncertainties (2023, unpublished manuscript). Uses two-stage RL with PPO (on-policy) and TD3PG. https:\/\/www.researchgate.net\/publication\/365485928_Reinforcement_learning_for_robust_voltage_control_in_distribution_grids_under_uncertainties","DOI":"10.2139\/ssrn.4093891"},{"key":"4_CR24","doi-asserted-by":"crossref","unstructured":"Puterman, M.L.: Markov decision processes. In: Handbook of Markov Decision Processes, vol. 2, pp. 331\u2013434 (1990)","DOI":"10.1016\/S0927-0507(05)80172-0"},{"key":"4_CR25","unstructured":"Raffin, A.: Getting SAC to work on a massive parallel simulator: an RL journey with off-policy algorithms. araffin.github.io, February 2025. https:\/\/araffin.github.io\/post\/sac-massive-sim\/"},{"issue":"268","key":"4_CR26","first-page":"1","volume":"22","author":"A Raffin","year":"2021","unstructured":"Raffin, A., Hill, A., Gleave, A., Kanervisto, A., Ernestus, M., Dormann, N.: Stable-baselines3: reliable reinforcement learning implementations. J. Mach. Learn. Res. 22(268), 1\u20138 (2021)","journal-title":"J. Mach. Learn. Res."},{"key":"4_CR27","unstructured":"Schmietendorf, K., Peinke, J., Kamps, O.: On the stability and quality of power grids subjected to intermittent feed-in. arXiv preprint arXiv:1611.08235 (2016)"},{"key":"4_CR28","doi-asserted-by":"publisher","first-page":"103535","DOI":"10.1016\/j.artint.2021.103535","volume":"299","author":"D Silver","year":"2021","unstructured":"Silver, D., Singh, S., Precup, D., Sutton, R.S.: Reward is enough. Artif. Intell. 299, 103535 (2021)","journal-title":"Artif. Intell."},{"key":"4_CR29","doi-asserted-by":"crossref","unstructured":"Soldati, P., Ghadimi, E., Demirel, B., Wang, Y., Gaigalas, R., Sintorn, M.: Design principles for model generalization and scalable AI integration in radio access networks. IEEE Commun. Mag. (2024)","DOI":"10.1109\/MCOM.001.2300812"},{"key":"4_CR30","doi-asserted-by":"crossref","unstructured":"Sun, Y., et al.: Optimization methods for optimal power flow problems in distribution networks: a brief review. In: 2023 8th Asia Conference on Power and Electrical Engineering (ACPEE), pp. 1400\u20131406. IEEE (2023)","DOI":"10.1109\/ACPEE56931.2023.10135989"},{"key":"4_CR31","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction, 2nd edn. The MIT Press (2018). http:\/\/incompleteideas.net\/book\/the-book-2nd.html"},{"key":"4_CR32","unstructured":"Sutton, R.S., Barto, A.G., et\u00a0al.: Reinforcement Learning: An Introduction, 2nd edn., vol. 1, no. 2, p. 25. MIT Press Cambridge (2018)"},{"issue":"3","key":"4_CR33","doi-asserted-by":"publisher","first-page":"308","DOI":"10.1049\/iet-rpg.2008.0070","volume":"3","author":"M Tsili","year":"2009","unstructured":"Tsili, M., Papathanassiou, S.: A review of grid code technical requirements for wind farms. IET Renew. Power Gener. 3(3), 308\u2013332 (2009)","journal-title":"IET Renew. Power Gener."},{"issue":"6","key":"4_CR34","doi-asserted-by":"publisher","first-page":"4644","DOI":"10.1109\/TPWRS.2020.2990179","volume":"35","author":"S Wang","year":"2020","unstructured":"Wang, S., et al.: A data-driven multi-agent autonomous voltage control framework using deep reinforcement learning. IEEE Trans. Power Syst. 35(6), 4644\u20134654 (2020)","journal-title":"IEEE Trans. Power Syst."},{"issue":"3","key":"4_CR35","doi-asserted-by":"publisher","first-page":"2313","DOI":"10.1109\/TSG.2019.2951769","volume":"11","author":"Q Yang","year":"2019","unstructured":"Yang, Q., Wang, G., Sadeghi, A., Giannakis, G.B., Sun, J.: Two-timescale voltage control in distribution grids using deep reinforcement learning. IEEE Trans. Smart Grid 11(3), 2313\u20132323 (2019)","journal-title":"IEEE Trans. Smart Grid"},{"issue":"1","key":"4_CR36","first-page":"213","volume":"6","author":"Z Zhang","year":"2019","unstructured":"Zhang, Z., Zhang, D., Qiu, R.C.: Deep reinforcement learning for power system applications: an overview. CSEE J. Power Energy Syst. 6(1), 213\u2013225 (2019)","journal-title":"CSEE J. Power Energy Syst."},{"key":"4_CR37","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Zhou, L., Shi, D., Zhao, X.: Coordinated frequency control through safe reinforcement learning (2022). https:\/\/arxiv.org\/abs\/2202.00530","DOI":"10.1109\/PESGM48719.2022.9916894"}],"container-title":["Lecture Notes in Computer Science","Artificial Intelligence XLII"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-11442-6_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T19:43:16Z","timestamp":1774467796000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-11442-6_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,24]]},"ISBN":["9783032114419","9783032114426"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-11442-6_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,24]]},"assertion":[{"value":"24 November 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SGAI-AI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Innovative Techniques and Applications of Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Cambridge","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 December 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 December 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"45","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"sgai2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/bcs-sgai.org\/ai2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}