Efficient and informative representation of system topologies is critical in AI-driven power system analysis (PSA). Despite a major breakthrough, recent approaches employing Graph Neural Networks (GNNs) face significant challenges in large-scale PSA, including high computational demands for sufficient labeled data and poor generalization to unseen topologies. To tackle these issues, we propose a self-supervised strategy for pre-training GNNs that enhances their expressiveness at both the individual node feature level and the whole graph structure. Integrating physics-informed techniques, our strategy allows GNNs to internalize fundamental principles applicable to multiple downstream tasks. We demonstrate that our method enables efficient training of GNNs on extensive topology datasets without supervision, effectively addressing the noted challenges. By pre-training GNNs with 145 million parameters on 20 million unlabeled topologies and subsequently fine-tuning them, we observe a significant performance improvement, averaging over 13%, compared to existing state-of-the-art (SOTA) methods across four challenging tasks.

The scale-up of AI models for analyzing largescale power systems necessitates a thorough understanding of their scaling properties. Existing studies on these properties provide only partial insights, showing that loss function decreases predictably with increased model scales; yet no scaling law for power system AI models has been established, and model performance remains unpredictable due to “emergent abilities”. This study pioneers the discussion on the emergent abilities of graph neural network (GNN) for analyzing large-scale power systems, revealing that model performance improves dramatically once model scale exceeds a threshold. Furthermore, we introduce an empirical power-law formula to quantify the relationship between this threshold and the power system size. Our theory accurately predicts the threshold for the appearance of emergent ability in large-scale power systems, including a synthetic 10,000- bus and a real-world 19,402-bus systems.

Several natural disasters worldwide have demonstrated that the severity of extreme weather events (EWEs) on power systems can be increased by adversely affecting renewable power. Generating renewable scenarios specific to EWEs is crucial for the effective implementation of resilience-oriented operations and planning in power systems that incorporate a high proportion of renewable energies. Despite the significant progress achieved recently, it remains a formidable challenge to produce high-quality samples from a limited dataset due to the low occurrence probability of EWEs. A conditional diffusion model-based method is firstly introduced to discern spatiotemporal correlations of renewable series assoicated with common conditional like diurnal, season, and temperature without suffering from prevalent issues like statistical assumptions and mode collapse. To guarantee the specificity of the generated samples to EWEs while maintaining diversity, a fine-tuning mechanism is proposed for the pre-trained diffusion models using a few-shot learning technology in conjunction with a self-supervised loss function. The effectiveness of the proposed method is verified on two real-world dataset. Numerical results demonstrate that the scenarios generated by the proposed method exhibit distinct advantages in terms of diversity and EWE-specific consistency. This facilitates scenario-based two-stage robust optimization and enhances the performance of resilience-oriented decisions in out-of-sample scenarios.

Assessment of total transfer capability (TTC) is vital for determining the permissible power transfer between two areas of an interconnected power system. In the context of heightened volatility and time-variability in power system operating states after integrating high proportions of renewable energy, data-driven inferential assessment methods emerge as promising alternatives, offering faster assessment capabilities compared to knowledge-based iterative methods. However, data-driven methods typically struggle to establish reliable connections between assessment outcomes and security standards, hindering the guarantee of conservatism. A hybrid algorithm, combining knowledge-based and data-driven techniques, is proposed to accurately and efficiently assess TTC while strictly complying with pre-established security and stability constraints. Data-driven inference accelerates knowledge-based iterative processes by rapidly identifying reasonable initial values and providing adaptive step sizes, while knowledge-based analysis guides data-driven methods through offering stability margin information. This mechanism leverages the speed of data-driven methods while maintaining conservatism through knowledge-based approaches. The effectiveness of the proposed method is verified on benchmarks, including the IEEE 30-bus system and a real-world power system, which also exhibits conservatism and robustness in the face of increasing renewable energy penetration.