基于深度强化学习的中点钳位型三相有源电力滤波器直流电压与电容平衡协同控制

Abstract
Figure/Table
References
Related Citation (15)

Download: PDF (5948 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract To address the inherent flaws of the traditional control schemes for neutral-point-clamped three-phase active power filters, including the coupling between direct current bus voltage regulation and neutral-point voltage balancing, slow dynamic response of proportional-integral (PI) controllers, parameter tuning that relies on engineering experience, and poor disturbance rejection performance, this paper proposes a coordinated control strategy for direct current side voltage based on the deep deterministic policy gradient algorithm. This strategy constructs a Markov decision process tailored to the high- frequency switching characteristics and dual control objectives of the active power filter, devises a composite reward function, and imposes a gradient-based penalty on voltage errors via the second-order Euclidean norm, so as to achieve unified error-free control of direct current bus voltage stabilization and split capacitor voltage balancing. Simulation verification through Matlab/Simulink demonstrates that under typical operating conditions including capacitor parameter mismatch, direct current voltage startup, and grid voltage sags, compared with the traditional proportional-integral control, the proposed method reduces the direct current bus voltage regulation time by 57.1%, shortens the neutral-point capacitor balancing adjustment time by 55.6%, and lowers the total harmonic distortion of the grid-side current to 2.57%. The proposed method also exhibits stronger robustness under grid disturbances, which provides a novel approach for direct current side multi-objective coordinated control of this type of active power filters.

Key words： active power filter neutral-point-clamped coordinated control of DC voltage deep reinforcement learning

Received: 19 March 2026

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	XIE Zihang
	HUANG Yanguo

Cite this article:

XIE Zihang,HUANG Yanguo. Coordinated control of DC voltage and capacitance balance in a neutral-point-clamped three-phase active power filter based on deep reinforcement learning[J]. Electrical Engineering, 2026, 27(9): 1-10.

URL:

https://dqjs.cesmedia.cn/EN/Y2026/V27/I9/1

[1] 张昱祺, 王波, 金萧, 等. 基于附加电流控制的并网逆变器输出谐波抑制策略[J]. 智慧电力, 2023, 51(6): 34-40.
[2] 张淼, 文俊铭, 吴事煜, 等. 混合型有源电力滤波器双闭环控制[J]. 电机与控制学报, 2023, 27(4): 119-126.
[3] 黄春光, 刘建春, 武明科. 一种逆变器的并网-谐波治理综合控制方法[J]. 电气技术, 2024, 25(11): 30-36.
[4] 唐爱红, 宋幸, 尚宇菲, 等. 基于分布式潮流控制器的海上风电系统谐波治理方法和控制策略[J]. 电力系统自动化, 2024, 48(2): 20-28.
[5] 刘可, 赵正奎, 张文倩, 等. 弱电网下LCL型APF强鲁棒性控制方法[J]. 南方电网技术, 2024, 18(12): 96-106.
[6] Dash D K, Sadhu P K, Shrivastav A K.Dynamic optimization of active power filters in grid-tied photovoltaic systems using partial reinforcement learning[J]. Neural Computing and Applications, 2025, 37: 15605-15634.
[7] 侯世玺, 汪成, 付士利, 等. 有源电力滤波器神经终端滑模控制[J]. 太阳能学报, 2023, 44(2): 279-287.
[8] 张敏, 孙孝峰, 朱艳萍, 等. 驻波移相有源电力滤波器在环形配电网中的应用[J]. 电工技术学报, 2025, 40(1): 203-216.
[9] 刘琛, 吕世轩, 刘宗沛, 等. 模块化多电平有源电力滤波器误差反馈模型预测控制策略[J]. 电力建设, 2024, 45(3): 107-115.
[10] 汪颖, 钟啟明, 刘育权, 等. 新型电力系统的电能质量扰动治理关键技术综述及展望[J]. 中国电机工程学报, 2025, 45(22): 8670-8690.
[11] 张旗, 蔡逢煌, 黄丽梅, 等. 单相程控电流源PI+重复控制[J]. 电工技术学报, 2019, 34(增刊1): 163-170.
[12] Errouissi R, Al-Durra A.Design of PI controller together with active damping for grid-tied LCL filter systems using disturbance observer-based control approach[C]//2017 IEEE Industry Applications Society Annual Meeting, Cincinnati, OH, USA, 2017: 1-8.
[13] 刘文阳, 王辉, 张展鹏. 不平衡负载四桥臂APF的改进滑模控制策略研究[J]. 计算机仿真, 2022, 39(3): 113-118, 219.
[14] 侯世玺, 韩洁楠, 汪成, 等. 基于自组织特征选择模糊神经网络的有源电力滤波器二阶终端滑模控制[J/OL]. 控制理论与应用, 2025-07-18. https://link.cnki.net/urlid/44.1240.tp.20250717.1032.016.
[15] 张远, 史丽萍, 成方状, 等. 基于改进虚拟多矢量的APF模型预测控制[J]. 电力电子技术, 2022, 56(10): 133-136.
[16] Balouji E, Bäckstrüm K, McKelvey T. Deep rein- forcement learning based grid-forming inverter[C]//2023 IEEE Industry Applications Society Annual Meeting (IAS), Nashville, TN, USA, 2023: 1-9.
[17] 王佳宁, 杨仁海, 姚张浩, 等. 基于深度强化学习的有源中点钳位逆变器效率优化设计[J]. 电子与信息学报, 2023, 45(9): 3311-3320.
[18] Tu Zhenghong, Zhang Wei, Liu Wenxin.Deep reinforcement learning control for pulsed power load online deployment in DC shipboard integrated power system[J]. IEEE Transactions on Power Systems, 2023, 38(4): 3557-3567.
[19] 侯世玺, 付士利, 储云迪. 基于情感神经网络的有源电力滤波器智能终端滑模控制[J]. 控制与决策, 2022, 37(8): 2067-2076.
[20] 全欢, 彭显刚, 刘涵予, 等. 基于深度强化学习的配电网实时电压优化控制方法[J]. 电网技术, 2023, 47(5): 2029-2038.
[21] 韩保军, 高强, 代飞, 等. 基于协同奖励函数多目标强化学习的智能频率控制策略研究[J]. 电力科学与技术学报, 2023, 38(2): 18-29.
[22] 朱涛, 海迪, 李文云, 等. 基于深度确定性策略梯度算法的配电网最优电压实时控制[J]. 电网与清洁能源, 2024, 40(6): 121-129.