Improving Reactive Power Management and Voltage Profiles in Hybrid Renewable Energy Grids using Heterogeneous Context-Aware Graph Convolutional Network

With the growing integration of renewable energy sources (RES) into power grids (PG), managing reactive power and maintaining voltage stability have become critical challenges. This paper proposes a novel approach using a Heterogeneous Context-Aware Graph Convolutional Network (HCAGCN) to improve reactive power management and voltage profiles in hybrid renewable energy grids (REG). The objective of the proposed method is to improve the voltage profile, reduces the power loss. The proposed HCAGCN approach effectively models complex relationships among various components in hybrid REG, enabling dynamic adjustment of reactive power and enhancing overall voltage stability. By then, the proposed method is implemented in MATLAB platform and evaluated their performance with various existing methods such as Artificial Neural Network (ANN), Firefly Algorithm (FA), Kronecker Neural Network (KNN), Genetic Algorithm (GA), and Ant Lion Optimization (ALO). The HCAGCN technique achieves the lowest current THD at 0.81% and voltage THD at 3.49%, significantly outperforming the numerous existing methods.