基于DDPG自适应协同控制的VSG频率调节策略

陈冰文; 李永刚; 郭潇镁; 王贳骇

doi:10.19783/j.cnki.pspc.260214

欢迎来到能源电力期刊网！

English Version 期刊登录

您当前的位置：

首页 >

文章列表页 >

基于DDPG自适应协同控制的VSG频率调节策略

应用研究 | 更新时间：2026-09-23

- 基于DDPG自适应协同控制的VSG频率调节策略
- A frequency regulation strategy for VSG based on DDPG and adaptive coordinated control
- 电力系统保护与控制 2026年54卷第18期
- 作者机构：
  
  新能源电力系统国家重点实验室 (华北电力大学),北京,102206
- 作者简介：
- 基金信息：
- DOI：10.19783/j.cnki.pspc.260214
  中图分类号：
- 纸质出版：2026
- 稿件说明：
移动端阅览
陈冰文, 李永刚, 郭潇镁, 等. 基于DDPG自适应协同控制的VSG频率调节策略[J]. 电力系统保护与控制, 2026,54(18).

CHEN Bingwen, LI Yonggang, GUO Xiaomei, et al. A frequency regulation strategy for VSG based on DDPG and adaptive coordinated control[J]. Power System Protection and Control, 2026, 54(18).
陈冰文, 李永刚, 郭潇镁, 等. 基于DDPG自适应协同控制的VSG频率调节策略[J]. 电力系统保护与控制, 2026,54(18). DOI： 10.19783/j.cnki.pspc.260214.

CHEN Bingwen, LI Yonggang, GUO Xiaomei, et al. A frequency regulation strategy for VSG based on DDPG and adaptive coordinated control[J]. Power System Protection and Control, 2026, 54(18). DOI： 10.19783/j.cnki.pspc.260214.

摘要

针对虚拟同步发电机(virtual synchronous generator

VSG) 固定惯量阻尼控制策略在并离网运行条件下频率动态性能不足的问题，提出一种融合深度确定性策略梯度算法(deep deterministic policy gradient

DDPG)与非线性自适应控制的协同参数调节策略。首先，通过VSG小信号模型分析惯量、阻尼和二次调频参数对系统动态响应的影响，设定参数的调节范围。然后，设计扰动敏感型自适应策略来调节系统阻尼和二次调频系数。并将上述策略嵌入DDPG的离线训练中，通过奖励/惩罚机制优化扰动条件下VSG惯量输出，进一步提升系统频率响应性能。最后，通过在线仿真验证所提策略在并/离网工况下的优越性。结果表明，所提协同控制策略能够有效抑制频率波动，提高参数响应速度，改善系统动态性能。

Abstract

To address the insufficient frequency dynamic performance of virtual synchronous generator (VSG) systems with fixed inertia and damping control under both grid-connected and islanded operating conditions

an adaptive coordinated parameter regulation strategy integrating the deep deterministic policy gradient (DDPG) algorithm with nonlinear adaptive control is proposed. First

the effects of inertia

damping

and secondary frequency control coefficients on the dynamic characteristics of the VSG are analyzed using a small-signal model

and the feasible regulation ranges of these parameters are determined. Subsequently

a disturbance-sensitive nonlinear adaptive strategy is developed to regulate the damping and secondary frequency regulation coefficients. Furthermore

the proposed strategy is embedded into the offline training process of the DDPG algorithm

where a reward/penalty mechanism is constructed to optimize the inertia output of the VSG under disturbance conditions

thereby further enhancing the system frequency response performance. Finally

simulation studies under both grid-connected and islanded operating scenarios are conducted to evaluate the effectiveness of the proposed strategy. The results demonstrate that the proposed coordinated control strategy can effectively suppress frequency fluctuations

accelerate parameter response

and enhance the overall dynamic performance of the system.

关键词

Keywords

references

ZHONG Qingchang, WEISS G. Synchronverters: inverters that mimic synchronous generators[J]. IEEE Transactions on Industrial Electronics, 2011, 58(4): 1259-1267.

YAO Fengjun, ZHAO Jinbin, LI Xiangjun, et al. RBF neural network based virtual synchronous generator control with improved frequency stability[J]. IEEE Transactions on Industrial Informatics, 2020, 17(6): 4014-4024.

OBOREH-SNAPPS O, SHE B, FAHAD S, et al. Virtual synchronous generator control using twin delayed deep deterministic policy gradient method[J]. IEEE Transactions on Energy Conversion, 2023, 39(1): 214-228.

ZHANG Kun, ZHANG Changhua, XU Zihao, et al. A virtual synchronous generator control strategy with Q-learning to damp low frequency oscillation[C] // 2020 Asia Energy and Electrical Engineering Symposium (AEEES), May 28-31, 2020, Chengdu, China: 111-115.

SKIPAREV V, BELIKOV J, PETLENKOV E. Reinforcement learning based approach for virtual inertia control in microgrids with renewable energy sources[C] // 2020 IEEE PES Innovative Smart Grid Technologies Europe (ISGT-Europe), October 26-28, 2020, The Hague, Netherlands: 1020-1024.

LI Yushuai, GAO Wei, HUANG Shuo, et al. Data-driven optimal control strategy for virtual synchronous generator via deep reinforcement learning approach[J]. Journal of Modern Power Systems and Clean Energy, 2021, 9(4): 919-929.

BENHMIDOUCH Z, MOUFID S, AIT-OMAR A, et al. A novel reinforcement learning policy optimization based adaptive VSG control technique for improved frequency stabilization in AC microgrids[J]. Electric Power Systems Research, 2024, 230.

YIN Xiuxing, LEI Meizhen. Jointly improving energy efficiency and smoothing power oscillations of integrated offshore wind and photovoltaic power: a deep reinforcement learning approach[J]. Protection and Control of Modern Power Systems, 2023, 8(2): 1-11.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

应用多参数协同自适应方法的虚拟同步发电机控制策略

基于虚拟惯性自适应算法的电动汽车控制策略

面向低压配电网的VSG复功率自适应虚拟阻抗解耦策略

考虑策略安全层动态修正的配电网电压优化控制

基于二重前馈自抗扰的构网型光伏微电网稳频控制策略