Learning-driven load frequency control for islanded microgrid using graph networks-based deep reinforcement learning

As the complexity of microgrid systems, the randomness of load disturbances, and the data dimensionality increase, traditional load frequency control methods for microgrids are no longer capable of handling such highly complex and nonlinear control systems. This can result in this can result in significant frequency fluctuations and oscillations, potentially leading to blackouts in microgrids. To address the random power disturbances introduced by a large amount of renewable energy, this paper proposes a Learning-Driven Load Frequency Control (LD-LFC) method. Additionally, a Graph Convolution Neural Networks -Proximal Policy Optimization (GCNN -PPO) algorithm is introduced, which enhances the random power disturbances introduced by a large amount of renewable energy. Algorithm is introduced, which enhances the perception ability of the reinforcement learning agent regarding grid state data by embedding a graph convolutional network. The effectiveness of this approach is validated through simulations on the isolated microgrid Load Frequency Control (LFC) model of China Southern Grid (CSG).