SenseFlow: A Physics-Informed and Self-Ensembling Iterative Framework for Power Flow Estimation

2025-05-18

AI Summary

To address insufficient modeling of network sparsity and the neglect of the Slack node’s physical role in power system state estimation, this paper proposes an end-to-end framework integrating physics-informed priors with self-ensembling iterative optimization. We introduce a virtual-node attention mechanism to explicitly encode grid topological sparsity and a Slack-gated feed-forward module to enforce the Slack node’s dominant physical constraint on phase-angle prediction. Furthermore, we propose Sliding-Average-driven Self-Ensembling Iterative Estimation (SeIter), enabling progressive, high-accuracy approximation of both voltage magnitudes and phase angles. Evaluated on multiple-scale power grid datasets, our method reduces voltage magnitude and phase-angle estimation errors by 32.7% and 41.5%, respectively, over state-of-the-art approaches. It demonstrates strong robustness against measurement noise and superior cross-topology generalization capability.

Technology Category

• Intelligent Robots: State Estimation
• Search and Optimization: Learning to Search
• Reasoning under Uncertainty: Stochastic Optimization

Application Category

• User Modeling, Personalization and Recommendation: User privacy protection in personalized systems
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Power flow estimation plays a vital role in ensuring the stability and reliability of electrical power systems, particularly in the context of growing network complexities and renewable energy integration. However, existing studies often fail to adequately address the unique characteristics of power systems, such as the sparsity of network connections and the critical importance of the unique Slack node, which poses significant challenges in achieving high-accuracy estimations. In this paper, we present SenseFlow, a novel physics-informed and self-ensembling iterative framework that integrates two main designs, the Physics-Informed Power Flow Network (FlowNet) and Self-Ensembling Iterative Estimation (SeIter), to carefully address the unique properties of the power system and thereby enhance the power flow estimation. Specifically, SenseFlow enforces the FlowNet to gradually predict high-precision voltage magnitudes and phase angles through the iterative SeIter process. On the one hand, FlowNet employs the Virtual Node Attention and Slack-Gated Feed-Forward modules to facilitate efficient global-local communication in the face of network sparsity and amplify the influence of the Slack node on angle predictions, respectively. On the other hand, SeIter maintains an exponential moving average of FlowNet's parameters to create a robust ensemble model that refines power state predictions throughout the iterative fitting process. Experimental results demonstrate that SenseFlow outperforms existing methods, providing a promising solution for high-accuracy power flow estimation across diverse grid configurations.

Problem

• Addresses power flow estimation challenges in complex electrical systems
• Improves accuracy by handling network sparsity and Slack node importance
• Integrates physics-informed and self-ensembling methods for robust predictions

Innovation

• Physics-Informed Power Flow Network for voltage prediction
• Self-Ensembling Iterative process for robust estimation
• Virtual Node Attention for efficient global-local communication