Power system state estimation is a critical task for ensuring stable grid operation and serves as the foundation of grid control and analysis. Conventional approaches largely involve field measurements, network topology, and manual anomaly detection, which present significant limitations, particularly while dealing with dynamic and complex power systems. In recent years, deep learning techniques have been progressively applied in this field to overcome the shortcomings of conventional approaches, which are based on mathematical models and static analysis. However, existing deep learning techniques primarily focus on power system security analysis and computational resource management. In spite of the powerful capabilities in supervised learning tasks, the lack of interpretability still makes deep learning models less convincing, and thus might hinder their practical applications. In response to this issue, we apply a computational model for power system state estimation based on the Kolmogorov–Arnold network (KAN) model with learnable activation functions, visualization capabilities, and pruning features. From the perspective of feature interpretability, we find the influence of bus features on the model output, such as bus voltage magnitude. Moreover, through analysis of the internal structure of the model, we uncover a possibility of potential mechanisms of power system state estimation. Experimental results show that our study not only enhances the interpretability of power system state estimation but also effectively ensures grid security and stability through state estimation.
Transient stability assessments and state prediction are critical tasks for power system security. The increasing integration of renewable energy sources has introduced significant uncertainties into these tasks. While AI has shown great potential, most existing AI-based approaches focus on single tasks, such as either stability assessments or state prediction, limiting their practical applicability. In power system operations, these two tasks are inherently coupled, as system states directly influence stability conditions. To address these challenges, this paper presents a multi-task learning framework based on spatiotemporal graph convolutional networks that efficiently performs both tasks. The proposed framework employs a spatiotemporal graph convolutional encoder to capture system topology features and integrates a self-attention U-shaped residual decoder to enhance prediction accuracy. Additionally, a Multi-Exit Network branch with confidence-based exit points enables efficient and reliable transient stability assessments. Experimental results on IEEE standard test systems and real-world power grids demonstrate the framework’s superiority as compared to state-of-the-art AI models, achieving a 48.1% reduction in prediction error, a 6.3% improvement in the classification F1 score, and a 52.1% decrease in inference time, offering a robust solution for modern power system monitoring and safety assessments.
This paper addresses the challenge of achieving fast and accurate transient stability analysis and emergency control in power systems, which are crucial for reliable grid operation under disturbances. To this end, we propose a spatio-temporal graph deep learning approach leveraging Diffusion Convolutional Gated Recurrent Units (DCGRUs) for transient stability assessment and coherent generator group prediction. Unlike traditional methods, our approach explicitly represents transient responses as spatio-temporal graph data, capturing both topological and dynamic dependencies. The DCGRU model effectively extracts these features, and the predicted coherent generator groups are incorporated into the single-machine infinite-bus equivalence method to design an emergency generator tripping scheme. Simulation analysis results on both benchmark and real-world power grids validate the proposed method’s feasibility and effectiveness in enhancing transient stability analysis and emergency control.