

浏览全部资源
扫码关注微信
1.浙江工业大学信息工程学院,浙江省杭州市 310023
2.国网浙江省电力有限公司温岭市供电公司,浙江省台州市 317500
3.南洋理工大学电气与电子工程学院,新加坡 639798,新加坡
4.全省复杂系统智能感知与控制重点实验室,浙江省杭州市 310023
Received:25 May 2025,
Revised:2025-12-05,
Online First:18 December 2025,
Published:25 February 2026
移动端阅览
李锦泽,何晓敏,吴锦辉等.基于结构化神经网络的微电网二次调频控制[J].电力系统自动化,2026,50(4):133-141.
LI Jinze,HE Xiaomin,WU Jinhui,et al.Secondary Frequency Regulation for Microgrids Based on Structured Neural Networks[J].Automation of Electric Power Systems,2026,50(4):133-141.
李锦泽,何晓敏,吴锦辉等.基于结构化神经网络的微电网二次调频控制[J].电力系统自动化,2026,50(4):133-141. DOI: 10.7500/AEPS20250525005.
LI Jinze,HE Xiaomin,WU Jinhui,et al.Secondary Frequency Regulation for Microgrids Based on Structured Neural Networks[J].Automation of Electric Power Systems,2026,50(4):133-141. DOI: 10.7500/AEPS20250525005.
随着微电网系统复杂性与不确定性的日益增加,设计兼具稳定性和输出跟踪能力的二次调频控制方法对系统安全可靠运行至关重要。为此,提出一种基于结构化神经网络的微电网二次调频控制方法。首先,基于物理系统中广泛存在的平衡点独立无源性,将微电网的二次调频控制问题建模为严格单调的比例-积分(PI)控制结构,并将PI参数化为严格凸神经网络(SCNN)的梯度。其次,采用带有可调系数的Softplus-
β
激活函数构建SCNN,在保证其通用逼近能力的同时,有效适应微电网多变的通信约束。此外,将由SCNN构造的严格凸函数的梯度作为Lyapunov函数,进一步给出了系统端到端的稳定性证明。仿真结果表明,相较于其他可能导致系统不稳定的非结构化神经网络控制方法,所提方法不仅可以保证系统稳定性,而且在暂态和稳态性能上均优于传统控制方法。
With the increasing complexity and uncertainty of microgrid systems
designing secondary frequency regulation control methods that combine both stability and output tracking capabilities is crucial for the safe and reliable operation of the system. To this end
this paper proposes a secondary frequency regulation method for microgrids based on structured neural networks. First
by leveraging the equilibrium point independent passivity widely present in physical systems
the secondary frequency regulation problem for microgrids is formulated as a strictly monotonic proportional-integral (PI) control structure
and the PI parameters are parameterized as the gradient of a strictly convex neural network (SCNN). Second
the SCNN is constructed using a Softplus-
β
activation function with tunable coefficients
which not only ensures its universal approximation capability but also effectively adapts to the diverse communication constraints in microgrids. Furthermore
by employing the gradient of the strictly convex function constructed by the SCNN as a Lyapunov function
an end-to-end stability proof for the system is provided. Simulation results show that
compared with other unstructured neural network control methods which may lead t
o system instability
the proposed method not only guarantees system stability but also outperforms traditional control methods in both transient and steady-state performance.
姚建国 , 杨胜春 , 王珂 , 等 . 智能电网“源-网-荷”互动运行控制概念及研究框架 [J]. 电力系统自动化 , 2012 , 36 ( 21 ): 1 - 6 .
YAO Jianguo , YANG Shengchun , WANG Ke , et al . Concept and research framework of “source-grid-load”interactive operation control in smart grid [J]. Automation of Electric Power Systems , 2012 , 36 ( 21 ): 1 - 6 .
新华社 . 习近平主持召开中央财经委员会第九次会议 [EB/OL].( 2021-03-15 )[ 2025-01-15 ]. http://www.gov.cn/xinwen/2021-03/15/content_5593154.htm http://www.gov.cn/xinwen/2021-03/15/content_5593154.htm .
Xinhua News Agency . XI Jinping presided over the 9th Meeting of the Central Financial and Economic Affairs Commission [EB/OL]. ( 2021-03-15 )[ 2025-01-15 ]. http://www.gov.cn/xinwen/2021-03/15/content_5593154.htm http://www.gov.cn/xinwen/2021-03/15/content_5593154.htm .
任大伟 , 肖晋宇 , 侯金鸣 , 等 . 双碳目标下我国新型电力系统的构建与演变研究 [J]. 电网技术 , 2022 , 46 ( 10 ): 3831 - 3839 .
REN Dawei , XIAO Jinyu , HOU Jinming , et al . Research on the construction and evolution of new power system under dual carbon goals [J]. Power System Technology , 2022 , 46 ( 10 ): 3831 - 3839 .
苏 译, Jiashen TEH , 柏智 , 等 . 考虑不确定性扰动的含海量资源配电网弹性研究综述 [J]. 电力系统自动化 , 2022 , 46 ( 16 ): 17 - 30 .
SU Yi , Jiashen TEH , BAI Zhi , et al . Review of research on resilience of distribution network with massive resources considering uncertainty disturbance [J]. Automation of Electric Power Systems , 2022 , 46 ( 16 ): 17 - 30 .
鲁宗相 , 王彩霞 , 闵勇 , 等 . 微电网研究综述 [J]. 电力系统自动化 , 2007 , 31 ( 19 ): 100 - 107 .
LU Zongxiang , WANG Caixia , MIN Yong , et al . Overview on microgrid research [J]. Automation of Electric Power Systems , 2007 , 31 ( 19 ): 100 - 107 .
RAFIEE A , BATMANI Y , BEVRANI H , et al . Robust MIMO controller design for VSC-based microgrids: sequential loop closing concept and quantitative feedback theory [J]. IEEE Transactions on Smart Grid , 2021 , 13 ( 1 ): 129 - 138 .
JOSHI A , AYGUN A I , KAMALASADAN S , et al . Inverter-angle-induced optimized frequency regulation approach for AC-DC microgrids using consensus-based identification [J]. IEEE Transactions on Industry Applications , 2022 , 58 ( 5 ): 6780 - 6792 .
郭蕾 , 苏建徽 , 施永 . 微网孤岛运行模式下的调频控制策略 [J]. 电力系统自动化 , 2017 , 41 ( 8 ): 110 - 115 .
GUO Lei , SU Jianhui , SHI Yong . Frequency regulation control strategy for microgrid in islanded mode [J]. Automation of Electric Power Systems , 2017 , 41 ( 8 ): 110 - 115 .
郑永伟 , 陈民铀 , 李闯 , 等 . 自适应调节下垂系数的微电网控制策略 [J]. 电力系统自动化 , 2013 , 37 ( 7 ): 6 - 11 .
ZHENG Yongwei , CHEN Minyou , LI Chuang , et al . A microgrid control strategy based on adaptive drooping coefficient adjustment [J]. Automation of Electric Power Systems , 2013 , 37 ( 7 ): 6 - 11 .
GANJIAN-ABOUKHEILI M , SHAHABI M , SHAFIEE Q , et al . Linear quadratic regulator based smooth transition between microgrid operation modes [J]. IEEE Transactions on Smart Grid , 2021 , 12 ( 6 ): 4854 - 4864 .
TAO L , WANG P , MA X , et al . Robustness optimization through modified linear active disturbance rejection control for high-voltage load interface in microgrid [J]. IEEE Transactions on Industrial Electronics , 2022 , 70 ( 4 ): 3909 - 3919 .
KAZEMI M V , SADATI S J , GHOLAMIAN S A . Adaptive frequency control of microgrid based on fractional order control and a data-driven control with stability analysis [J]. IEEE Transactions on Smart Grid , 2021 , 13 ( 1 ): 381 - 392 .
李志军 , 苗庆玉 , 郭燕龙 , 等 . 具有时变增益的分布式有限时间二次调频策略 [J]. 电力系统自动化 , 2024 , 48 ( 14 ): 139 - 146 .
LI Zhijun , MIAO Qingyu , GUO Yanlong , et al . Distributed finite-time secondary frequency regulation strategy with time-varying gain [J]. Automation of Electric Power Systems , 2024 , 48 ( 14 ): 139 - 146 .
苏小玲 , 韩民晓 , 孙海 . 基于自适应全局滑模控制的微电网稳定控制策略 [J]. 中国电机工程学报 , 2014 , 34 ( 31 ): 5534 - 5541 .
SU Xiaoling , HAN Minxiao , SUN Hai . Stability control strategy of microgrid based on adaptive global sliding mode control [J]. Proceedings of the CSEE , 2014 , 34 ( 31 ): 5534 - 5541 .
BACCINO F , CONTE F , GRILLO S , et al . An optimal model-based control technique to improve wind farm participation to frequency regulation [J]. IEEE Transactions on Sustainable Energy , 2014 , 6 ( 3 ): 993 - 1003 .
李得民 , 吴在军 , 赵波 , 等 . 基于模型预测控制的孤岛微电网二次调节策略 [J]. 电力系统自动化 , 2019 , 43 ( 10 ): 60 - 67 .
LI Demin , WU Zaijun , ZHAO Bo , et al . Secondary regulation strategy for islanded microgrid based on model predictive control [J]. Automation of Electric Power Systems , 2019 , 43 ( 10 ): 60 - 67 .
方琰 , 黎静华 , 兰飞 , 等 . 独立微电网电动机负载参与快速频率响应的调频方法 [J]. 电力系统自动化 , 2025 , 49 ( 17 ): 122 - 132 .
FANG Yan , LI Jinghua , LAN Fei , et al . Frequency regulation method for motor loads participating in fast frequency response in independent microgrids [J]. Automation of Electric Power Systems , 2025 , 49 ( 17 ): 122 - 132 .
沈珺 , 柳伟 , 李虎成 , 等 . 基于强化学习的多微电网分布式二次优化控制 [J]. 电力系统自动化 , 2020 , 44 ( 5 ): 198 - 206 .
SHEN Jun , LIU Wei , LI Hucheng , et al . Reinforcement learning based distributed secondary optimal control for multiple microgrids [J]. Automation of Electric Power Systems , 2020 , 44 ( 5 ): 198 - 206 .
卢开诚 , 刘铠诚 , 董树锋 . 基于模糊单神经元PI的微电网频率自适应控制 [J]. 电力工程技术 , 2022 , 41 ( 5 ): 131 - 139 .
LU Kaicheng , LIU Kaicheng , DONG Shufeng . Microgrid frequency adaptive control based on fuzzy single neuron PI controller [J]. Electric Power Engineering Technology , 2022 , 41 ( 5 ): 131 - 139 .
SHAN Y , HU J , SHEN B . Distributed secondary frequency control for AC microgrids using load power forecasting based on artificial neural network [J]. IEEE Transactions on Industrial Informatics , 2023 , 20 ( 2 ): 1651 - 1662 .
符杨 , 张语涵 , 田书欣 , 等 . 基于混合量测的新能源电力系统动态频率预测方法 [J]. 中国电机工程学报 , 2024 , 44 ( 5 ): 1823 - 1836 .
FU Yang , ZHANG Yuhan , TIAN Shuxin , et al . Dynamic frequency prediction method for new energy power systems based on hybrid measurements [J]. Proceedings of the CSEE , 2024 , 44 ( 5 ): 1823 - 1836 .
CUI W , JIANG Y , ZHANG B , et al . Structured neural-PI control with end-to-end stability and output tracking guarantees [J]. Advances in Neural Information Processing Systems , 2023 , 36 : 68434 - 68457 .
CUI W , JIANG Y , ZHANG B , et al . Structured neural-PI control for networked systems: stability and steady-state optimality guarantees [J/OL]. [ 2025-05-25 ]. https://arxiv.org/abs/2305.17777 https://arxiv.org/abs/2305.17777 .
GUERRERO J M , VASQUEZ J C , MATAS J , et al . Hierarchical control of droop-controlled AC and DC microgrids—a general approach toward standardization [J]. IEEE Transactions on Industrial Electronics , 2010 , 58 ( 1 ): 158 - 172 .
GUO F , WEN C , MAO J , et al . Distributed secondary voltage and frequency restoration control of droop-controlled inverter-based microgrids [J]. IEEE Transactions on Industrial Electronics , 2015 , 62 ( 7 ): 4355 - 4364 .
CHENG D , TARN T J , ISIDORI A . Global external linearization of nonlinear systems via feedback [J]. IEEE Transactions on Automatic Control , 1985 , 30 ( 8 ): 808 - 811 .
ARCAK M , MEISSEN C , PACKARD A . Networks of dissipative systems: compositional certification of stability, performance, and safety [M]. Germany : Springer , 2016 .
AMOS B , XU L , KOLTER J Z . Input convex neural networks [C]// Proceedings of the 34th International Conference on Machine Learning(PMLR) , August 6-11 , 2017 , Sydney,Australia : 146 - 155 .
CHEN Y , SHI Y , ZHANG B . Optimal control via neural networks: a convex approach [J/OL]. [ 2025-05-25 ]. https://arxiv.org/abs/1805.11835 https://arxiv.org/abs/1805.11835 .
BOYD S P , VANDENBERGHE L . Convex optimization [M]. Cambridge : Cambridge University Press , 2004 .
0
Views
0
下载量
0
CSCD
Publicity Resources
Related Articles
Related Author
Related Institution
京公网安备11010802024621