TY - GEN
T1 - Adaptive Control of Converter Parameters Based on DDPG Algorithm
AU - Zhi, Jirong
AU - Zhang, Lufeng
AU - Wang, Liguo
AU - Sidorov, Denis
AU - Dreglea, Aliona
AU - Zheng, Xuemei
N1 - Publisher Copyright:
© Beijing Paike Culture Commu. Co., Ltd. 2026.
PY - 2026
Y1 - 2026
N2 - To improve the control issues of large-scale wind power grid connection, the optimization of control parameters for virtual synchronous generator (VSG) is of vital importance for system stability. This paper proposes an adaptive control strategy for grid-forming converters based on the Deep Deterministic Policy Gradient (DDPG) algorithm to solve the problems of dynamic oscillation of active power and frequency during grid connection, and to enhance the system response speed. Firstly, the mathematical model and characteristics of VSG are analyzed, relevant formulas are derived, root locus curves are plotted, and the ranges and adaptive rules of virtual inertia J and virtual damping coefficient D are obtained. Then, an adaptive parameter controller model is built based on the DDPG algorithm, and the algorithm flow and reward function are detailed. Through simulation comparisons between fixed parameter control and DDPG algorithm optimization control, the results verify the effectiveness of the algorithm in actual operation and providing strong support for the optimization operation of grid-forming converters and wind farms.
AB - To improve the control issues of large-scale wind power grid connection, the optimization of control parameters for virtual synchronous generator (VSG) is of vital importance for system stability. This paper proposes an adaptive control strategy for grid-forming converters based on the Deep Deterministic Policy Gradient (DDPG) algorithm to solve the problems of dynamic oscillation of active power and frequency during grid connection, and to enhance the system response speed. Firstly, the mathematical model and characteristics of VSG are analyzed, relevant formulas are derived, root locus curves are plotted, and the ranges and adaptive rules of virtual inertia J and virtual damping coefficient D are obtained. Then, an adaptive parameter controller model is built based on the DDPG algorithm, and the algorithm flow and reward function are detailed. Through simulation comparisons between fixed parameter control and DDPG algorithm optimization control, the results verify the effectiveness of the algorithm in actual operation and providing strong support for the optimization operation of grid-forming converters and wind farms.
KW - Adaptive control
KW - DDPG
KW - Deep reinforcement learning
KW - Grid-forming converters
KW - Virtual synchronous generator
UR - https://www.scopus.com/pages/publications/105042765679
U2 - 10.1007/978-981-92-0549-3_25
DO - 10.1007/978-981-92-0549-3_25
M3 - 会议稿件
AN - SCOPUS:105042765679
SN - 9789819205486
T3 - Lecture Notes in Electrical Engineering
SP - 237
EP - 245
BT - The Proceedings of 2025 International Conference of Electrical, Electronic and Networked Energy Systems - Volume 1
A2 - Jia, Limin
A2 - Qi, Lei
A2 - Liu, Zhuangzhuang
A2 - Chen, Hao
A2 - Xu, Xianfeng
A2 - Wei, Baoquan
PB - Springer Science and Business Media Deutschland GmbH
T2 - International Conference of Electrical, Electronic and Networked Energy Systems, EENES 2025
Y2 - 31 October 2025 through 2 November 2025
ER -