Dynamic Control Strategy of Multilayer Perceptron for Multiple Virtual Synchronous Machine Feed-in Systems Considering Damped-Inertia Coupling Oscillation Constraints
Chen Yanbo, Ma Jiahao, Liu Zhenxiang, Huang Tao, Zhang Zhi
School of Electrical and Electronic Engineering North China Electric Power University Beijing 102206 China
Abstract：With the acceleration of the pace of transformation of the energy structure, the scale of grid access for renewable energy, represented by wind and solar energy, has expanded significantly. The virtual synchronous generator (VSG) control method is often employed to enhance the weak damping and low inertia characteristics of new power systems, thereby providing support capabilities for the power grid. However, a high proportion of virtual synchronous generator access exacerbates the active power oscillation and frequency deviation problems in the system. Still, it lacks an in-depth study on the coupling characteristics of control parameters between multiple units. This paper proposes a dynamic control strategy for a parallel virtual synchronous generator system that considers damped inertial coupled oscillation constraints. Based on the coupling characteristics between multiple units, a dynamic control model using a multi-layer perceptron (MLP) neural network is designed. First, this paper derives the active power transfer function of a multi-machine parallel system and analyzes the damping characteristics of inertially coupled oscillations. In multi-machine parallel systems, the active oscillation characteristics are mainly affected by the unit with the smallest inertial damping ratio. Secondly, based on the rated capacity of the virtual synchronous generator, the dynamic characteristics of a single unit and the oscillation characteristics of multiple machines are comprehensively considered. The adjustment parameters of each unit are then divided into intervals. Finally, based on the obtained dynamic interval constraints, a multi-layer perceptron neural network dynamic control model is constructed for each unit. By monitoring the frequency changes and frequency deviations of each unit in real-time, the virtual inertia and damping coefficients of each unit are dynamically decoupled, reducing the active power and frequency oscillations of the system. Compared with traditional fixed parameters and existing dynamic control strategies, the proposed method can better suppress active power oscillation and reduce adjustment time. Compared with the technique without coupled oscillation constraints between units, the proposed method accelerates the dynamic adjustment speed when the power is suddenly changed. Further experiments demonstrate that the control strategy based on the MLP neural network exhibits good noise robustness. The following conclusions can be drawn. The coupling relationship between the active oscillation characteristics and virtual inertia and damping coefficients in the parallel system is analyzed, and a coupling constraint that considers the oscillation characteristics of multiple machines is established. A dynamic control strategy suitable for a multi-machine parallel system is proposed, considering the stability and dynamic response characteristics of single-machine and multi-machine parameters. The multi-layer perceptron neural network realizes real-time decoupling control of the virtual inertia and damping coefficients of each unit. Compared to existing control methods, the proposed method effectively suppresses frequency and power overshoot while reducing the dynamic adjustment time.
[1] 黄萌, 舒思睿, 李锡林, 等. 面向同步稳定性的电力电子并网变流器分析与控制研究综述[J]. 电工技术学报, 2024, 39(19): 5978-5994. Huang Meng, Shu Sirui, Li Xilin, et al.A review of synchronization-stability-oriented analysis and control of power electronic grid-connected converters[J]. Transactions of China Electrotechnical Society, 2024, 39(19): 5978-5994. [2] Liu Zhenxiang, Chen Yanbo, Zhang Zhi, et al.Identification of vulnerable nodes and sensitivity analysis of control parameters for multiple grid- connected converter systems[J]. IEEE Transactions on Sustainable Energy, 2025, 16(3): 1602-1612. [3] 胡光, 庄可好, 高晖胜, 等. 低惯量交流系统并网变流器次/超同步振荡分析[J]. 电工技术学报, 2024, 39(8): 2250-2264. Hu Guang, Zhuang Kehao, Gao Huisheng, et al.Sub/super synchronous oscillation analysis of grid-connected converter in low inertia AC system[J]. Transactions of China Electrotechnical Society, 2024, 39(8): 2250-2264. [4] Chen Yanbo, Li Xiaoxue, Zhang Zhi.Risk assessment of rail transit systems with variable renewable energy based on uncertain random theory[J]. International Journal of Electrical Power & Energy Systems, 2025, 164: 110441. [5] 李兆伟, 方勇杰, 吴雪莲, 等. 频率紧急控制中动作时延和措施量对低惯量系统控制有效性的影响[J]. 电工技术学报, 2024, 39(17): 5394-5405. Li Zhaowei, Fang Yongjie, Wu Xuelian, et al.Influence of action delay and amount on the control effectiveness of low inertia systems in frequency emergency control[J]. Transactions of China Elec- trotechnical Society, 2024, 39(17): 5394-5405. [6] 刘思佳, 刘海涛, 张隽, 等. 基于等效阻抗的虚拟同步机电压支撑影响因素分析与改进控制策略研究[J]. 电工技术学报, 2025, 40(9): 2738-2751. Liu Sijia, Liu Haitao, Zhang Jun, et al.Research on the analysis of virtual synchronous generator voltage support influence factors and improvement control strategies based on equivalent impedance[J]. Transactions of China Electrotechnical Society, 2025, 40(9): 2738-2751. [7] Tong Wenxuan, Lu Zhengang, Chen Yanbo, et al.Enhancing modular gravity energy storage plants: a hybrid strategy for optimal unit capacity con- figuration[J]. Applied Energy, 2025, 378: 124774. [8] 赵冬梅, 宋晨铭, 冯向阳, 等. 100%新能源场景下考虑频率稳定约束的源网荷储一体化系统储能优化配置[J]. 电工技术学报, 2025, 40(7): 2146-2161. Zhao Dongmei, Song Chenming, Feng Xiangyang, et al.The optimal configuration of energy storage in the source-grid-load-storage integrated system con- sidering frequency stability constraints in 100% new energy scenarios[J]. Transactions of China Elec- trotechnical Society, 2025, 40(7): 2146-2161. [9] 王伟, 周少泽, 黄萌, 等. 构网型技术: 演进历程、功能定位与应用展望[J]. 电力系统自动化, 2025, 49(1): 1-13. Wang Wei, Zhou Shaoze, Huang Meng, et al.Grid- forming technologies: evolution history, function, and application prospects[J]. Automation of Electric Power Systems, 2025, 49(1): 1-13. [10] Xiong Xiaoling, Li Xinyue, Luo Bochen, et al.An additional damping torque method for low-frequency stability enhancement of virtual synchronous generators[J]. IEEE Transactions on Power Elec- tronics, 2024, 39(12): 15858-15869. [11] Li Jin, Wen Buying, Wang Huaiyuan.Adaptive virtual inertia control strategy of VSG for micro-grid based on improved Bang-Bang control strategy[J]. IEEE Access, 2019, 7: 39509-39514. [12] Alipoor J, Miura Y, Ise T.Power system stabilization using virtual synchronous generator with alternating moment of inertia[J]. IEEE Journal of Emerging and Selected Topics in Power Electronics, 2015, 3(2): 451-458. [13] Mentesidi K, Garde R, Aguado M, et al.Imple- mentation of a fuzzy logic controller for virtual inertia emulation[C]//2015 International Symposium on Smart Electric Distribution Systems and Tech- nologies (EDST), Vienna, Austria, 2015: 606-611. [14] 曾国辉, 廖鸿飞, 赵晋斌, 等. 直流微网双向DC/DC变换器虚拟惯量和阻尼系数自适应控制策略[J]. 电力系统保护与控制, 2022, 50(6): 65-73. Zeng Guohui, Liao Hongfei, Zhao Jinbin, et al.A self-adaptive control strategy of virtual inertia and a damping coefficient for bidirectional DC-DC con- verters in a DC microgrid[J]. Power System Pro- tection and Control, 2022, 50(6): 65-73. [15] 张兴伟, 谭丽平, 陈文浩, 等. 基于二次系统优化的储能变流器惯性提升方法[J]. 电力系统保护与控制, 2021, 49(8): 128-135. Zhang Xingwei, Tan Liping, Chen Wenhao, et al.Inertia lifting method of energy storage converter based on secondary system optimization[J]. Power System Protection and Control, 2021, 49(8): 128-135. [16] 王亚军, 杨立波, 马斌, 等. 虚拟同步机惯量及阻尼系数协调优化方法[J]. 电力系统保护与控制, 2022, 50(19): 88-98. Wang Yajun, Yang Libo, Ma Bin, et al.Coordination and optimization strategy of virtual inertia and damping coefficient of a virtual synchronous generator[J]. Power System Protection and Control, 2022, 50(19): 88-98. [17] Li Meiyi, Huang Wentao, Tai Nengling, et al.A dual-adaptivity inertia control strategy for virtual synchronous generator[J]. IEEE Transactions on Power Systems, 2020, 35(1): 594-604. [18] 黄林彬, 辛焕海, 黄伟, 等. 含虚拟惯量的电力系统频率响应特性定量分析方法[J]. 电力系统自动化, 2018, 42(8): 31-38. Huang Linbin, Xin Huanhai, Huang Wei, et al.Quantified analysis method of frequency response characteristics for power systems with virtual inertia[J]. Automation of Electric Power Systems, 2018, 42(8): 31-38. [19] 任碧莹, 邱姣姣, 刘欢, 等. 基于虚拟同步发电机双机并联系统的参数自调节优化控制策略[J]. 电工技术学报, 2019, 34(1): 128-138. Ren Biying, Qiu Jiaojiao, Liu Huan, et al.Optimization control strategy of self-adjusting parameter based on dual-parallel virtual synchronous generators[J]. Transactions of China Electrotechnical Society, 2019, 34(1): 128-138. [20] 王振浩, 张越, 成龙, 等. 多参数协同自适应的改进虚拟同步控制策略[J]. 电网技术, 2023, 47(6): 2403-2414. Wang Zhenhao, Zhang Yue, Cheng Long, et al.Improved virtual synchronization control strategy with multi-parameter adaptive collaboration[J]. Power System Technology, 2023, 47(6): 2403-2414. [21] 张玉璇, 杜春水, 施其国, 等. 并联逆变器参数协同自适应VSG控制策略[J]. 电机与控制学报, 2024, 28(9): 47-59. Zhang Yuxuan, Du Chunshui, Shi Qiguo, et al.Parametric cooperative adaptive VSG control strategy for parallel inverters[J]. Electric Machines and Control, 2024, 28(9): 47-59. [22] 秦晓辉, 苏丽宁, 迟永宁, 等. 大电网中虚拟同步发电机惯量支撑与一次调频功能定位辨析[J]. 电力系统自动化, 2018, 42(9): 36-43. Qin Xiaohui, Su Lining, Chi Yongning, et al.Functional orientation discrimination of inertia support and primary frequency regulation of virtual synchronous generator in large power grid[J]. Auto- mation of Electric Power Systems, 2018, 42(9): 36-43. [23] 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, 2021, 17(6): 4014-4024. [24] 张赟宁, 郭钟仁, 张磊. 基于RBF神经网络的分数阶虚拟同步机控制策略[J/OL]. 电力系统及其自动化学报, 1-7[2025-02-20].https://link.cnki.net/doi/10.19635/j.cnki.csu-epsa.001536. Zhang Yunning, Guo Zhongren, Zhang Lei.Fractional- order virtual synchronous generator control strategy based on RBF neural networks[J/OL]. Proceedings of the CSU-EPSA, 1-7[2025-02-20].https://link.cnki.net/doi/10.19635/j.cnki.csu-epsa.001536. [25] 张子星, 赵晋斌, 曾志伟, 等. 基于RBF的VSG虚拟惯量和动态阻尼补偿自适应控制[J]. 电力系统保护与控制, 2024, 52(2): 155-164. Zhang Zixing, Zhao Jinbin, Zeng Zhiwei, et al.VSG virtual inertia and dynamic damping compensation adaptive control based on RBF[J]. Power System Protection and Control, 2024, 52(2): 155-164. [26] 奚鑫泽, 黄英博, 邢超.一种多虚拟同步机并联系统虚拟动态互阻尼控制方法[J/OL]. 电网技术, 1-10[2025-02-20]. https://link.cnki.net/doi/10.13335/j.1000-3673.pst.2024.0080. Xi Xinze, Huang Yingbo, Xing Chao.A virtual dynamic mutual damping control method for multi- VSGs parallel system[J/OL]. Power System Tech- nology, 1-10[2025-02-20]. https://link.cnki.net/doi/10.13335/j.1000-3673.pst.2024.0080. [27] 栗峰, 丁杰, 周才期, 等. 新型电力系统下分布式光伏规模化并网运行关键技术探讨[J]. 电网技术, 2024, 48(1): 184-199. Li Feng, Ding Jie, Zhou Caiqi, et al.Key technologies of large-scale grid-connected operation of distributed photovoltaic under new-type power system[J]. Power System Technology, 2024, 48(1): 184-199. [28] Xu Haizhen, Yu Changzhou, Liu Chun, et al.An improved virtual inertia algorithm of virtual syn- chronous generator[J]. Journal of Modern Power Systems and Clean Energy, 2020, 8(2): 377-386. [29] Li Dongdong, Zhu Qianwei, Lin Shunfu, et al.A self-adaptive inertia and damping combination control of VSG to support frequency stability[J]. IEEE Transa- ctions on Energy Conversion, 2017, 32(1): 397-398. [30] Long Bo, Liao Yong, Chong K T, et al.MPC- controlled virtual synchronous generator to enhance frequency and voltage dynamic performance in islanded microgrids[J]. IEEE Transactions on Smart Grid, 2021, 12(2): 953-964.
2026, Vol. 41 
