Adaptive Control for Virtual Synchronous Generator Parameters Based on Soft Actor Critic
This paper introduces a model-free optimization method based on reinforcement learning (RL) aimed at resolving the issues of active power and frequency oscillations present in a traditional virtual synchronous generator (VSG). The RL agent utilizes the active power and frequency response of the VSG...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-03-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/24/7/2035 |
| _version_ | 1797212008803729408 |
|---|---|
| author | Chuang Lu Xiangtao Zhuan |
| author_facet | Chuang Lu Xiangtao Zhuan |
| author_sort | Chuang Lu |
| collection | DOAJ |
| description | This paper introduces a model-free optimization method based on reinforcement learning (RL) aimed at resolving the issues of active power and frequency oscillations present in a traditional virtual synchronous generator (VSG). The RL agent utilizes the active power and frequency response of the VSG as state information inputs and generates actions to adjust the virtual inertia and damping coefficients for an optimal response. Distinctively, this study incorporates a setting-time term into the reward function design, alongside power and frequency deviations, to avoid prolonged system transients due to over-optimization. The soft actor critic (SAC) algorithm is utilized to determine the optimal strategy. SAC, being model-free with fast convergence, avoids policy overestimation bias, thus achieving superior convergence results. Finally, the proposed method is validated through MATLAB/Simulink simulation. Compared to other approaches, this method more effectively suppresses oscillations in active power and frequency and significantly reduces the setting time. |
| first_indexed | 2024-04-24T10:35:33Z |
| format | Article |
| id | doaj.art-5cd2ce5aa8ac48febe479578de49e93d |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-24T10:35:33Z |
| publishDate | 2024-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-5cd2ce5aa8ac48febe479578de49e93d2024-04-12T13:26:02ZengMDPI AGSensors1424-82202024-03-01247203510.3390/s24072035Adaptive Control for Virtual Synchronous Generator Parameters Based on Soft Actor CriticChuang Lu0Xiangtao Zhuan1School of Electrical Engineering and Automation, Wuhan University, Wuhan 430072, ChinaSchool of Electrical Engineering and Automation, Wuhan University, Wuhan 430072, ChinaThis paper introduces a model-free optimization method based on reinforcement learning (RL) aimed at resolving the issues of active power and frequency oscillations present in a traditional virtual synchronous generator (VSG). The RL agent utilizes the active power and frequency response of the VSG as state information inputs and generates actions to adjust the virtual inertia and damping coefficients for an optimal response. Distinctively, this study incorporates a setting-time term into the reward function design, alongside power and frequency deviations, to avoid prolonged system transients due to over-optimization. The soft actor critic (SAC) algorithm is utilized to determine the optimal strategy. SAC, being model-free with fast convergence, avoids policy overestimation bias, thus achieving superior convergence results. Finally, the proposed method is validated through MATLAB/Simulink simulation. Compared to other approaches, this method more effectively suppresses oscillations in active power and frequency and significantly reduces the setting time.https://www.mdpi.com/1424-8220/24/7/2035reinforcement learningsoft actor criticvirtual synchronous generatorvirtual inertiadamping coefficientadaptive control |
| spellingShingle | Chuang Lu Xiangtao Zhuan Adaptive Control for Virtual Synchronous Generator Parameters Based on Soft Actor Critic Sensors reinforcement learning soft actor critic virtual synchronous generator virtual inertia damping coefficient adaptive control |
| title | Adaptive Control for Virtual Synchronous Generator Parameters Based on Soft Actor Critic |
| title_full | Adaptive Control for Virtual Synchronous Generator Parameters Based on Soft Actor Critic |
| title_fullStr | Adaptive Control for Virtual Synchronous Generator Parameters Based on Soft Actor Critic |
| title_full_unstemmed | Adaptive Control for Virtual Synchronous Generator Parameters Based on Soft Actor Critic |
| title_short | Adaptive Control for Virtual Synchronous Generator Parameters Based on Soft Actor Critic |
| title_sort | adaptive control for virtual synchronous generator parameters based on soft actor critic |
| topic | reinforcement learning soft actor critic virtual synchronous generator virtual inertia damping coefficient adaptive control |
| url | https://www.mdpi.com/1424-8220/24/7/2035 |
| work_keys_str_mv | AT chuanglu adaptivecontrolforvirtualsynchronousgeneratorparametersbasedonsoftactorcritic AT xiangtaozhuan adaptivecontrolforvirtualsynchronousgeneratorparametersbasedonsoftactorcritic |