Engineering Hybrid Physics-Informed Neural Networks for Next-Generation Electricity Systems: A State-of-the-Art Review

This article provides a state-of-the-art review of physics-informed machine learning (PIML) methods for electricity systems. It addresses how governing physical equations are embedded directly into neural network training to overcome data scarcity and ensure physical consistency. The review covers hybrid architectures that combine data-driven learning with domain-specific physics, targeting applications in system design, real-time monitoring, and control for Industry 4.0.