Estimate Three-Phase Distribution Line Parameters With Physics-Informed Graphical Learning Method
This work addresses the need for accurate network parameter estimation in power distribution systems, which is crucial for modeling, monitoring, and control, representing an incremental improvement over prior methods.
The paper tackles the problem of estimating three-phase distribution line parameters, such as series resistance and reactance, using a physics-informed graphical learning algorithm that relies on smart meter data, achieving high accuracy and outperforming existing methods.
Accurate estimates of network parameters are essential for modeling, monitoring, and control in power distribution systems. In this paper, we develop a physics-informed graphical learning algorithm to estimate network parameters of three-phase power distribution systems. Our proposed algorithm uses only readily available smart meter data to estimate the three-phase series resistance and reactance of the primary distribution line segments. We first develop a parametric physics-based model to replace the black-box deep neural networks in the conventional graphical neural network (GNN). Then we derive the gradient of the loss function with respect to the network parameters and use stochastic gradient descent (SGD) to estimate the physical parameters. Prior knowledge of network parameters is also considered to further improve the accuracy of estimation. Comprehensive numerical study results show that our proposed algorithm yields high accuracy and outperforms existing methods.