Adaptive Control for Virtual Synchronous Generator Parameters Based on Soft Actor Critic
Open Access
Abstract
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.Keywords
Funding Information
- National Natural Science Foundation of China (U22B20100)
This publication has 33 references indexed in Scilit:
- Research on adaptive optimal control strategy of virtual synchronous generator inertia and damping parametersIET Power Electronics, 2023
- Reinforcement learning algorithms: A brief surveyExpert Systems with Applications, 2023
- An adaptive VSG control strategy of battery energy storage system for power system frequency stability enhancementInternational Journal of Electrical Power & Energy Systems, 2023
- DDPG-Based Joint Time and Energy Management in Ambient Backscatter-Assisted Hybrid Underlay CRNsIEEE Transactions on Communications, 2022
- Reinforcement learning for automatic quadrilateral mesh generation: A soft actor–critic approachNeural Networks, 2022
- High penetration of inverter-based power sources with VSG control impact on electromechanical oscillation of power systemInternational Journal of Electrical Power & Energy Systems, 2022
- A deep reinforcement learning based method for real-time path planning and dynamic obstacle avoidanceNeurocomputing, 2022
- Deep reinforcement learning based control for Autonomous Vehicles in CARLAMultimedia Tools and Applications, 2022
- Adaptive Virtual Inertia Control Strategy of VSG for Micro-Grid Based on Improved Bang-Bang Control StrategyIEEE Access, 2019
- Human-level control through deep reinforcement learningNature, 2015