{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T04:44:05Z","timestamp":1777697045663,"version":"3.51.4"},"reference-count":34,"publisher":"SAGE Publications","issue":"6","license":[{"start":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T00:00:00Z","timestamp":1756857600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"funder":[{"name":"China Southern Power Grid Corporation's science and technology projects"},{"name":"Research and Application of Key Technologies for the Scenario-based Artificial Intelligence Platform of Power Systems at the Southern Grid's Central Dispatching Office","award":["ZDKJXM20230017"],"award-info":[{"award-number":["ZDKJXM20230017"]}]}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Intelligent Decision Technologies"],"published-print":{"date-parts":[[2025,11]]},"abstract":"<jats:p>With the expansion of the scale of power grids and the increase in uncertainty of renewable energy, the grid section overload problem is becoming increasingly prominent. The current grid section overload control method overlooks the coupling relationship between the control of each section, leading to the flow adjustment of one section causing overload in other sections. Additionally, the traditional strength of learning control suffers from problems of overestimation and high computational cost. This paper focuses on the power grid generator control as the object, utilizing the GAT model to dynamically extract node topology features and leveraging the advantages of the KAN model's lightweight nonlinear processing. It combines D3QN to control over-limit generators in the power grid section, thereby improving control accuracy. The study first uses GAT to calculate the embedding matrix of the power grid node, and uses KAN to calculate the embedding representation of the section task. Then, a multi-section task attribution graph is generated based on node embedding and task embedding, and a weighted pooling strategy is used to extract the final power grid diagram feature representation based on the embedding matrix and the multi-section task attribution graph. Finally, the power grid diagram feature representation is used as the input of the D3QN model to achieve accurate and dynamic over-limit control of generators in power grid sections. The experiment was conducted based on the IEEE 39-node system, and the results were refined into three dimensions: discrimination accuracy, dynamic response, and computational efficiency. The results showed that the relative error of the GAT-KAN-D3QN model was only 4.3%, which was 1.4% lower than the DQN-DDPG method, and the scheduling efficiency reached 92.7%. The results show that the reinforcement learning (RL) method in this paper can effectively improve the control accuracy and can better cope with the dynamic changes and uncertainties in the power grid, solving the key contradiction of \u201caccuracy-efficiency trade-off\u201d.<\/jats:p>","DOI":"10.1177\/18724981251372270","type":"journal-article","created":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T13:08:57Z","timestamp":1756904937000},"page":"4254-4277","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":0,"title":["Grid section overload control method based on reinforcement learning"],"prefix":"10.1177","volume":"19","author":[{"given":"Wei","family":"Jiang","sequence":"first","affiliation":[{"name":"Power Dispatch and Control Center of China Southern Power Grid"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huijie","family":"Gu","sequence":"additional","affiliation":[{"name":"Power Dispatch and Control Center of China Southern Power Grid"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yubin","family":"He","sequence":"additional","affiliation":[{"name":"Power Dispatch and Control Center of China Southern Power Grid"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huashi","family":"Zhao","sequence":"additional","affiliation":[{"name":"Power Dispatch and Control Center of China Southern Power Grid"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yin","family":"Lian","sequence":"additional","affiliation":[{"name":"Xingyi Power Supply Bureau of Guizhou Power Co., Ltd., Xingyi, Guizhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","published-online":{"date-parts":[[2025,9,3]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3299351"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/OJPEL.2023.3246728"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11356-023-29653-9"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.3389\/fenrg.2024.1367287"},{"key":"e_1_3_2_6_2","first-page":"30","article-title":"Voltage regulation strategy of distribution network with decentralized wind power based on cluster partition","volume":"16","author":"Su S","year":"2023","unstructured":"Su S, Lei J, Yan Y, et al. Voltage regulation strategy of distribution network with decentralized wind power based on cluster partition. Recent Adv Electr Electron Eng (Formerly Recent Pat Electr Electron Eng) 2023; 16: 30\u201344.","journal-title":"Recent Adv Electr Electron Eng (Formerly Recent Pat Electr Electron Eng)"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.2516\/stet\/2024092"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.2516\/stet\/2024042"},{"key":"e_1_3_2_9_2","first-page":"5934","article-title":"Data-driven voltage\/var optimization control of active distribution network considering the reliability of photovoltaic power supply","volume":"44","author":"Bo Z","year":"2023","unstructured":"Bo Z, Yuan GAO, Tiecheng LI, et al. Data-driven voltage\/var optimization control of active distribution network considering the reliability of photovoltaic power supply. Proc CSEE 2023; 44: 5934\u20135946.","journal-title":"Proc CSEE"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.3390\/en17194998"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.3390\/en17215244"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.3389\/fenrg.2022.1097319"},{"key":"e_1_3_2_13_2","first-page":"18","article-title":"Cooperative voltage control method of multiple devices in AC\/DC distribution networks based on DQN and DDPG","volume":"40","author":"Zhaoyang H","year":"2023","unstructured":"Zhaoyang H, Qianyu Z, Shouxiang W, et al. Cooperative voltage control method of multiple devices in AC\/DC distribution networks based on DQN and DDPG. Distrib Util 2023; 40: 18\u201325.","journal-title":"Distrib Util"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1049\/gtd2.12783"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2022.3220569"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1007\/s13042-023-01796-8"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.3389\/fenrg.2023.1253206"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.3390\/e25030546"},{"key":"e_1_3_2_19_2","first-page":"377","article-title":"Integrated power information operation and maintenance system based on D3QN algorithm with experience replay","volume":"27","author":"Yang Y","year":"2024","unstructured":"Yang Y, Li H, Jing D. Integrated power information operation and maintenance system based on D3QN algorithm with experience replay. Int J Comput Sci Eng 2024; 27: 377\u2013384.","journal-title":"Int J Comput Sci Eng"},{"key":"e_1_3_2_20_2","first-page":"47","article-title":"Newton-Raphson method based power flow analysis and dynamic security assessment","volume":"7","author":"Li J","year":"2023","unstructured":"Li J, Hu Y. Newton-Raphson method based power flow analysis and dynamic security assessment. Int J New Dev Eng Soc 2023; 7: 47\u201354.","journal-title":"Int J New Dev Eng Soc"},{"key":"e_1_3_2_21_2","first-page":"147","article-title":"Improved newton-raphson method with simplified Jacobian matrix and optimized iteration rate for power flow calculation of power system","volume":"25","author":"Cui J","year":"2024","unstructured":"Cui J, Zhao G, Qin H, et al. Improved newton-raphson method with simplified Jacobian matrix and optimized iteration rate for power flow calculation of power system. Proc Rom Acad Ser a-Math Phys Tech Sci Inf Sci 2024; 25: 147\u2013156.","journal-title":"Proc Rom Acad Ser a-Math Phys Tech Sci Inf Sci"},{"key":"e_1_3_2_22_2","first-page":"89","article-title":"A comparative study of gauss-seidel and newton-raphson methods in power flow analysis","volume":"6","author":"Samburi N","year":"2025","unstructured":"Samburi N, Nor AFM. A comparative study of gauss-seidel and newton-raphson methods in power flow analysis. Multidiscip Appl Res Innovation 2025; 6: 89\u201395.","journal-title":"Multidiscip Appl Res Innovation"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.3390\/en17020384"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.3390\/en18061531"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.3390\/s25030733"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.3390\/pr13030873"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1049\/gtd2.12795"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.3390\/en17246454"},{"key":"e_1_3_2_29_2","first-page":"474","article-title":"Research on flexible integrated scheduling under stochastic processing times based on improved D3QN algorithm","volume":"37","author":"Li X","year":"2025","unstructured":"Li X, Ren X, Zhou Y, et al. Research on flexible integrated scheduling under stochastic processing times based on improved D3QN algorithm. J Syst Simul 2025; 37: 474\u2013486.","journal-title":"J Syst Simul"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1049\/rpg2.12911"},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-023-08568-z"},{"key":"e_1_3_2_32_2","first-page":"65441","article-title":"Meta-AdaM: an meta-learned adaptive optimizer with momentum for few-shot learning","volume":"36","author":"Sun S","year":"2023","unstructured":"Sun S, Gao H. Meta-AdaM: an meta-learned adaptive optimizer with momentum for few-shot learning. Adv Neural Inf Process Syst 2023; 36: 65441\u201365455.","journal-title":"Adv Neural Inf Process Syst"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.3934\/mbe.2024054"},{"key":"e_1_3_2_34_2","first-page":"26204","article-title":"A communication-efficient distributed gradient clipping algorithm for training deep neural networks","volume":"35","author":"Liu M","year":"2022","unstructured":"Liu M, Zhuang Z, Lei Y, et al. A communication-efficient distributed gradient clipping algorithm for training deep neural networks. Adv Neural Inf Process Syst 2022; 35: 26204\u201326217.","journal-title":"Adv Neural Inf Process Syst"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1002\/int.23001"}],"container-title":["Intelligent Decision Technologies"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/18724981251372270","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/18724981251372270","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/18724981251372270","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T09:21:41Z","timestamp":1777454501000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/18724981251372270"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,3]]},"references-count":34,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,11]]}},"alternative-id":["10.1177\/18724981251372270"],"URL":"https:\/\/doi.org\/10.1177\/18724981251372270","relation":{},"ISSN":["1872-4981","1875-8843"],"issn-type":[{"value":"1872-4981","type":"print"},{"value":"1875-8843","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,3]]}}}