The paper applies a hard-constrained probabilistic factor graph neural network to distribution system state estimation with sparse measurements and non-Gaussian noise.
See LICENSE fileDistribution SystemsState EstimationProbabilistic Factor Graph Neural Network
PR-Smoother is an amortized smoother for prescribed-simulator data assimilation, supporting non-Gaussian posterior estimation over physical state variables in high-dimensional simulators with calibration compatibility.
See LICENSE fileData AssimilationNon-Gaussian SmoothingAmortized Inference
A systematic review of physics-informed machine learning applications in electricity system design, monitoring, and control, focusing on hybrid architectures and physics constraint embedding methods.
See LICENSE filePhysics-Informed LearningElectricity SystemsElectromagnetic Simulation