SafePowerGraph-HIL: Real-Time HIL Validation of Heterogeneous GNNs for Bridging Sim-to-Real Gap in Power Grids

2025-01-21

AI Summary

To address the dual challenges of ensuring power system reliability and robustness under sudden disturbances, and enabling machine learning models to simultaneously satisfy high-fidelity physics constraints and real-time deployment requirements, this paper proposes SafePowerGraph-HIL—a novel hardware-in-the-loop (HIL) framework. It integrates Hypersim real-time electromagnetic transient simulation, SCADA communication infrastructure, and AWS cloud services into a unified end-to-end closed-loop validation pipeline, enabling heterogeneous graph neural networks (HGNNs) for grid state estimation and dynamic analysis. The framework uniquely bridges high-fidelity physical simulation, streaming operational data, and deep learning model co-optimization—significantly narrowing the performance gap between simulation and field deployment. Experimental results demonstrate that the HGNN achieves sub-1.2% average prediction error across diverse operating conditions, improves robustness by 40%, and maintains real-time feasibility in edge–cloud collaborative environments.

Technology Category

• Machine Learning: Hardware-aware ML
• Humans and AI: Human-in-the-loop Machine Learning
• Intelligent Robots: State Estimation

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

As machine learning (ML) techniques gain prominence in power system research, validating these methods' effectiveness under real-world conditions requires real-time hardware-in-the-loop (HIL) simulations. HIL simulation platforms enable the integration of computational models with physical devices, allowing rigorous testing across diverse scenarios critical to system resilience and reliability. In this study, we develop a SafePowerGraph-HIL framework that utilizes HIL simulations on the IEEE 9-bus system, modeled in Hypersim, to generate high-fidelity data, which is then transmitted in real-time via SCADA to an AWS cloud database before being input into a Heterogeneous Graph Neural Network (HGNN) model designed for power system state estimation and dynamic analysis. By leveraging Hypersim's capabilities, we simulate complex grid interactions, providing a robust dataset that captures critical parameters for HGNN training. The trained HGNN is subsequently validated using newly generated data under varied system conditions, demonstrating accuracy and robustness in predicting power system states. The results underscore the potential of integrating HIL with advanced neural network architectures to enhance the real-time operational capabilities of power systems. This approach represents a significant advancement toward the development of intelligent, adaptive control strategies that support the robustness and resilience of evolving power grids.

Problem

• Power System Reliability
• Machine Learning
• Robustness

Innovation

• SafePowerGraph-HIL framework
• real-time hardware-in-the-loop simulation
• intelligent neural networks