{"id":9323,"date":"2026-07-25T19:43:09","date_gmt":"2026-07-25T11:43:09","guid":{"rendered":"\/jase\/?post_type=tkuisotope&p=9323"},"modified":"2026-07-25T22:28:54","modified_gmt":"2026-07-25T14:28:54","slug":"jase-202610-33-058","status":"publish","type":"tkuisotope","link":"\/jase\/?tkuisotope=jase-202610-33-058","title":{"rendered":"Research on Optimal Control Strategies Based on Deep Reinforcement Learning under Differential Algebraic Equation Constraints"},"content":{"rendered":"\n
\n
\n

<\/i> 2026<\/a><\/p>\n<\/div>\n\n\n\n

\n

<\/i> Volume 33<\/a><\/p>\n<\/div>\n\n\n\n

\n
\n
\n
\n

Guoxing Si<\/i><\/a><\/p>\n\n\n\n

Basic Department of Zhengzhou Vocational College of Industrial Safety, Zhengzhou, Henan, 451192, China<\/p>\n<\/div>\n\n\n\n

\n

Received: March 12, 2026
Accepted: June 19, 2026
Publication Date: July 25, 2026<\/p>\n<\/div>\n<\/div>\n\n\n\n

\"\u4e0a\u50b3\u5716\u7247\"\n\n\n

Illustration of ADSCO for topology control<\/p>\n<\/div>\n<\/div>\n\n\n\n

<\/i> Copyright <\/strong>The Author(s). This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0)<\/a>, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are cited.<\/p>\n\n\n\n

Download Citation:\u00a0 BibTeX <\/a>| http:\/\/dx.doi.org\/10.6180\/jase.202610_33.058<\/a>\u00a0\u00a0<\/p>\n\n\n\n

Download PDF<\/a><\/p>\n\n\n\n

<\/div>\n\n\n\n

Optimal control of differential-algebraic equations represents a major challenge due to the intricate relationship between the state dynamics and the algebraic constraints, especially for large-scale power transmission systems with discrete topology actions. The limitations of conventional controllers and unconstrained deep reinforcement learning algorithms lie in the failure to ensure the feasibility, safety, and long-term stability of the system while
maintaining the DAE simulation consistency. To overcome the limitations of the existing solutions, the present work proposes a structured DRL approach, which integrates the Attentive Differentiable Structure for Control Optimization and the Policy Embedded Gradient Field Navigation algorithms. The ADSCO method represents the grid observations and the topology actions using a shared latent space, while the attentive energy modeling ensures the state-action compatibility using feasibility-aware signals from the DAE constraints. The PEGFN method refines the policy outputs using the constraint-informed gradient field defined on the relaxed action simplex. The effectiveness of the proposed method was tested using the L2RPN and RL2Grid test cases and proved to give better results compared to both previous methods and the current best reinforcement learning algorithms. Specifically speaking about the paper under discussion, \u2019simulation consistency with respect to DAEs\u2019 is the property that ensures that all control measures that are implemented within the proposed framework are consistent with the dynamics of the power system represented by DAEs.<\/p>\n\n\n\n

Keywords: Optimal control (OC), DRL, differential-algebraic systems, interpretable AI, intelligent systems<\/em><\/p>\n\n\n\n

<\/div>\n\n\n\n
\n
\n
\n
\n
\n
    \n
  1. [1] H. Zhou, S. Zhang, J. Peng, S. Zhang, J. Li, H. Xiong, and W. Zhang. \u201cInformer: Beyond efficient transformer for long sequence time-series forecasting\u201d. In: Proceedings of the AAAI conference on artificial intelligence. 35. 12. 2021, 11106\u201311115. DOI: https:\/\/doi.org\/10.1609\/aaai.v35i12.17325<\/a>.<\/li>\n
  2. [2] A. Angelopoulos, E. Candes, and R. J. Tibshirani, (2023) \u201cConformal pid control for time series prediction\u201d Advances in neural information processing systems 36: 23047\u201323074. DOI: https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/17325<\/a>.<\/li>\n
  3. [3] L. Shen and J. Kwok. \u201cNon-autoregressive conditional diffusion models for time series prediction\u201d. In: International Conference on Machine Learning. PMLR. 2023, 31016\u201331029. DOI: https:\/\/proceedings.mlr.press\/v202\/shen23d.html<\/a>.<\/li>\n
  4. [4] M. S. Sial, Q. Fu, and T. Vianna Brugni, (2022) \u201cAllocation of Interline Power Flow Controller-Based Congestion Management in Deregulated Power System\u201d Advances in Engineering and Intelligence Systems 1(01): 65\u201374. DOI: https:\/\/doi.org\/10.22034\/aeis.2022.148478<\/a>.<\/li>\n
  5. [5] X. Wen and W. Li, (2023) \u201cTime series prediction based on LSTM-attention-LSTM model\u201d IEEE access 11: 48322\u201348331. DOI: https:\/\/doi.org\/10.1109\/ACCESS.2023.3276628<\/a>.<\/li>\n
  6. [6] L. Ren, Z. Jia, Y. Laili, and D. Huang, (2023) \u201cDeep learning for time-series prediction in IIoT: progress, challenges, and prospects\u201d IEEE transactions on neural networks and learning systems 35(11): 15072\u201315091. DOI: https:\/\/doi.org\/10.1109\/TNNLS.2023.3291371<\/a>.<\/li>\n
  7. [7] Y. Li, K. Wu, and J. Liu, (2023) \u201cSelf-paced ARIMA for robust time series prediction\u201d Knowledge-Based Systems 269: 110489. DOI: https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0950705123002393<\/a>.<\/li>\n
  8. [8] Y. Wang, (2024) \u201cEnhancing transient stability of DFIG-based wind turbine systems using deep learning-controlled resistance-based fault current limiters\u201d Advances in Engineering and Intelligence Systems 3(01): 10\u201322. DOI: https:\/\/doi.org\/10.22034\/aeis.2024.423904.1139<\/a>.<\/li>\n
  9. [9] D. M. Durairaj and B. K. Mohan, (2022) \u201cA convolutional neural network based approach to financial time series prediction\u201d Neural Computing and Applications 34(16): 13319\u201313337. DOI: https:\/\/doi.org\/10.1007\/s00521-022-07143-2<\/a>.<\/li>\n
  10. [10] L. Yin, L. Wang, T. Li, S. Lu, J. Tian, Z. Yin, X. Li, and W. Zheng, (2023) \u201cU-Net-LSTM: time series-enhanced lake boundary prediction model\u201d Land 12(10): 1859. DOI: https:\/\/doi.org\/10.3390\/land12101859<\/a>.<\/li>\n
  11. [11] C. Yu, F. Wang, Z. Shao, T. Sun, L. Wu, and Y. Xu. \u201cDsformer: A double sampling transformer for multivariate time series long-term prediction\u201d. In: Proceedings of the 32nd ACM international conference on information and knowledge management. 2023, 3062\u20133072. DOI: https:\/\/doi.org\/10.1145\/3583780.361485<\/a>.<\/li>\n
  12. [12] W. Zheng and G. Chen, (2021) \u201cAn accurate GRU-based power time-series prediction approach with selective state updating and stochastic optimization\u201d IEEE Transactions on Cybernetics 52(12): 13902\u201313914. DOI: https:\/\/doi.org\/10.1109\/TCYB.2021.3121312<\/a>.<\/li>\n
  13. [13] B. Lindemann, T. M\u00fcller, H. Vietz, N. Jazdi, and M. Weyrich, (2021) \u201cA survey on long short-term memory networks for time series prediction\u201d Procedia Cirp 99: 650\u2013655. DOI: https:\/\/doi.org\/10.1016\/j.procir.2021.03.088<\/a>.<\/li>\n
  14. [14] R. Chandra, S. Goyal, and R. Gupta, (2021) \u201cEvaluation of deep learning models for multi-step ahead time series prediction\u201d Ieee Access 9: 83105\u201383123. DOI: https:\/\/doi.org\/10.1109\/ACCESS.2021.3085085<\/a>.<\/li>\n
  15. [15] J. Fan, K. Zhang, Y. Huang, Y. Zhu, and B. Chen, (2023) \u201cParallel spatio-temporal attention-based TCN for multivariate time series prediction\u201d Neural Computing and Applications 35(18): 13109\u201313118. DOI: https:\/\/link.springer.com\/article\/10.1007\/s00521-021-05958-z<\/a>.<\/li>\n
  16. [16] M. Hou, C. Xu, Z. Li, Y. Liu, W. Liu, E. Chen, and J. Bian. \u201cMulti-granularity residual learning with confidence estimation for time series prediction\u201d. In: Proceedings of the ACM Web Conference 2022. 2022, 112\u2013121. DOI: https:\/\/doi.org\/10.1145\/3485447.351205<\/a>.<\/li>\n
  17. [17] H. V. Dudukcu, M. Taskiran, Z. G. C. Taskiran, and T. Yildirim, (2023) \u201cTemporal Convolutional Networks with RNN approach for chaotic time series prediction\u201d Applied soft computing 133: 109945. DOI: https:\/\/doi.org\/10.1016\/j.asoc.2022.109945<\/a>.<\/li>\n
  18. [18] I. Amalou, N. Mouhni, and A. Abdali, (2022) \u201cMultivariate time series prediction by RNN architectures for energy consumption forecasting\u201d Energy Reports 8: 1084\u20131091. DOI: https:\/\/doi.org\/10.1016\/j.egyr.2022.07.139<\/a>.<\/li>\n
  19. [19] Y. Xiao, H. Yin, Y. Zhang, H. Qi, Y. Zhang, and Z. Liu, (2021) \u201cA dual-stage attention-based Conv-LSTM network for spatio-temporal correlation and multivariate time series prediction\u201d International Journal of Intelligent Systems 36(5): 2036\u20132057. DOI: https:\/\/doi.org\/10.1002\/int.22370<\/a>.<\/li>\n
  20. [20] J. Wang, W. Jiang, Z. Li, and Y. Lu, (2021) \u201cA new multi-scale sliding window LSTM framework (MSSW-LSTM): a case study for GNSS time-series prediction\u201d Remote Sensing 13(16): 3328. DOI: https:\/\/doi.org\/10.3390\/rs13163328<\/a>.<\/li>\n
  21. [21] M. Xu, M. Han, C. P. Chen, and T. Qiu, (2018) \u201cRecurrent broad learning systems for time series prediction\u201d IEEE transactions on cybernetics 50(4): 1405\u20131417. DOI: https:\/\/doi.org\/10.1109\/TCYB.2018.2863020<\/a>.<\/li>\n
  22. [22] W. Zheng and J. Hu, (2022) \u201cMultivariate time series prediction based on temporal change information learning method\u201d IEEE Transactions on Neural Networks and Learning Systems 34(10): 7034\u20137048. DOI: https:\/\/doi.org\/10.1109\/TNNLS.2021.3137178<\/a>.<\/li>\n
  23. [23] Y. Sun, S. Dang, W. Fang, W. Huang, and Y. Xu, (2025) \u201cDesign and analysis of electricity anomaly detection and diagnosis models based on generative adversarial networks\u201d International Journal of High Speed Electronics and Systems 34(04): 2540330. DOI: https:\/\/doi.org\/10.1142\/S0129156425403304<\/a>.<\/li>\n
  24. [24] W. R. Moskolai, W. Abdou, A. Dipanda, and Kolyang, (2021) \u201cApplication of deep learning architectures for satellite image time series prediction: A review\u201d Remote Sensing 13(23): 4822. DOI: https:\/\/doi.org\/10.3390\/rs13234822<\/a>.<\/li>\n
  25. [25] Z. Karevan and J. A. Suykens, (2020) \u201cTransductive LSTM for time-series prediction: An application to weather forecasting\u201d Neural Networks 125: 1\u20139. DOI: https:\/\/doi.org\/10.1016\/j.neunet.2019.12.030<\/a>.<\/li>\n
  26. [26] S. Wang, H. Wu, X. Shi, T. Hu, H. Luo, L. Ma, J. Zhang, and J. Zhou. \u201cTimemixer: Decomposable multiscale mixing for time series forecasting\u201d. In: International conference on learning representations. 2024. 2024, 38626\u201338652. DOI: https:\/\/iclr.cc\/paper_files\/paper\/2024\/hash\/a7ac8a21e5a27e7ab31a5f42a0117bdb-Abstract-Conference.html<\/a>.<\/li>\n
  27. [27] A. Wachi, X. Shen, and Y. Sui, (2024) \u201cA survey of constraint formulations in safe reinforcement learning\u201d arXiv preprint arXiv:2402.02025: DOI: https:\/\/doi.org\/10.48550\/arXiv.2402.02025<\/a>.<\/li>\n
  28. [28] W. Zhao, T. He, R. Chen, T. Wei, and C. Liu, (2023) \u201cState-wise safe reinforcement learning: A survey\u201d arXiv preprint arXiv:2302.03122: DOI: https:\/\/doi.org\/10.48550\/arXiv.2302.03122<\/a>.<\/li>\n
  29. [29] H. Wang, S. Bo, S. M. Fazeli, A. Yavari, B. Liu, Q. Zhao, and J. Liu, (2026) \u201cConstrained stabilization control via safe reinforcement learning and control Lyapunov value function\u201d Control Engineering Practice 174: 107065. DOI: https:\/\/doi.org\/10.1016\/j.conengprac.2026.107065<\/a>.<\/li>\n
  30. [30] S. Bandyopadhyay and S. Bhasin, (2025) \u201cLagrangian-based online safe reinforcement learning for state-constrained systems\u201d Automatica 179: 112458. DOI: https:\/\/doi.org\/10.1016\/j.automatica.2025.112458<\/a>.<\/li>\n
  31. [31] M. Opmeer and O. Staffans, (2024) \u201cOn linear quadratic optimal control and algebraic Riccati equations for infinite-dimensional differential-algebraic equations\u201d DAE Panel 2: DOI: https:\/\/doi.org\/10.52825\/dae-p.v2i.1388<\/a>.<\/li>\n
  32. [32] A. Ilchmann, T. Reis, L. Biegler, S. Campbell, C. F\u00fchrer, R. M\u00e4rz, S. Trenn, P. Kunkel, R. Riaza, V. H. Linh, et al. Differential-algebraic equations forum. 2017. Springer, 2013. DOI: https:\/\/doi.org\/10.1007\/978-3-642-27555-5<\/a>.<\/li>\n
  33. [33] H. Gernandt and T. Reis, (2024) \u201cLinear-quadratic optimal control for abstract differential-algebraic equations\u201d IFAC-PapersOnLine 58(17): 310\u2013315. DOI: https:\/\/doi.org\/10.1016\/j.ifacol.2024.10.187<\/a>.<\/li>\n
  34. [34] J. Wang, Z. Peng, X. Wang, C. Li, and J. Wu, (2020) \u201cDeep fuzzy cognitive maps for interpretable multivariate time series prediction\u201d IEEE transactions on fuzzy systems 29(9): 2647\u20132660. DOI: https:\/\/doi.org\/10.1109\/TFUZZ.2020.3005293<\/a>.<\/li>\n
  35. [35] S. Karasu and A. Altan, (2022) \u201cCrude oil time series prediction model based on LSTM network with chaotic Henry gas solubility optimization\u201d Energy 242: 122964. DOI: https:\/\/doi.org\/10.1016\/j.energy.2021.122964<\/a>.<\/li>\n
  36. [36] J. Wen, J. Yang, B. Jiang, H. Song, and H. Wang, (2020) \u201cBig data driven marine environment information forecasting: a time series prediction network\u201d IEEE transactions on fuzzy systems 29(1): 4\u201318. DOI: https:\/\/doi.org\/10.1109\/TFUZZ.2020.3012393<\/a>.<\/li>\n
  37. [37] M. A. Morid, O. R. L. Sheng, and J. Dunbar, (2023) \u201cTime series prediction using deep learning methods in healthcare\u201d ACM Transactions on Management Information Systems 14(1): 1\u201329. DOI: https:\/\/doi.org\/10.1145\/3531326<\/a>.<\/li>\n
  38. [38] H. Zhang, J. Zeng, J. Ma, Y. Fang, C. Ma, Z. Yao, and Z. Chen, (2021) \u201cTime series prediction of microseismic multi-parameter related to rockburst based on deep learning\u201d Rock Mechanics and Rock Engineering 54(12): 6299\u20136321. DOI: https:\/\/doi.org\/10.1007\/s00603-021-02614-9<\/a>.<\/li>\n
  39. [39] H. Widiputra, A. Mailangkay, and E. Gautama, (2021) \u201cMultivariate CNN-LSTM model for multiple parallel financial time-series prediction\u201d Complexity 2021(1): 9903518. DOI: https:\/\/doi.org\/10.1155\/2021\/9903518<\/a>.<\/li>\n
  40. [40] M. Hammad Saeed, S. Iqbal, M. Sohail, and U. Akram, (2023) \u201cAn optimal adaptive control of DC-Microgrid with the aim of accurate current sharing and voltage regulation according to the load variation and gray-wolf optimization\u201d Advances in Engineering and Intelligence Systems 2(03): 50\u201360. DOI: https:\/\/doi.org\/10.22034\/aeis.2023.406515.1110<\/a>.<\/li>\n
  41. [41] S. Nurpatsha, (2025) \u201cA New Analysis of Web Customer Service Text Classification of Alexa Virtual Assistant Commands Using a Deep Learning Model\u201d Journal of Artificial Intelligence and System Modelling 3(02): 76\u201390. DOI: https:\/\/doi.org\/10.22034\/jaism.2025.515660.1120<\/a>.<\/li>\n<\/ol>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n\n\n\n

    <\/p>\n","protected":false},"author":3,"template":"wp-custom-template-detail-4-aricles","meta":{"_uag_custom_page_level_css":""},"categories":[12,1483,6],"tags":[1672],"acf":[],"uagb_featured_image_src":[],"uagb_author_info":{"display_name":"\u6797\u923a\u6db5","author_link":"\/jase\/?author=3"},"uagb_comment_info":0,"uagb_excerpt":" Copyright The Author(s). This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are cited. Download Citation:\u00a0 BibTeX | http:\/\/dx.doi.org\/10.6180\/jase.202610_33.058\u00a0\u00a0 Download PDF Optimal control of differential-algebraic equations represents a major challenge due to…","_links":{"self":[{"href":"\/jase\/index.php?rest_route=\/wp\/v2\/tkuisotope\/9323"}],"collection":[{"href":"\/jase\/index.php?rest_route=\/wp\/v2\/tkuisotope"}],"about":[{"href":"\/jase\/index.php?rest_route=\/wp\/v2\/types\/tkuisotope"}],"author":[{"embeddable":true,"href":"\/jase\/index.php?rest_route=\/wp\/v2\/users\/3"}],"wp:attachment":[{"href":"\/jase\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=9323"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"\/jase\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=9323"},{"taxonomy":"post_tag","embeddable":true,"href":"\/jase\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=9323"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}