Physics-Informed Neural Networks for Enhanced State Estimation in Unbalanced Distribution Power Systems

Physics-Informed Neural Networks for Enhanced State Estimation in Unbalanced Distribution Power Systems

State estimation in distribution power systems is increasingly challenged by the proliferation of distributed energy resources (DERs), bidirectional power flows, and the growing complexity of unbalanced network topologies. Physics-Informed Neural Networks (PINNs) offer a compelling solution by integ...

Full description

Saved in:
Bibliographic Details
Main Authors: Petros Iliadis, Stefanos Petridis, Angelos Skembris, Dimitrios Rakopoulos, Elias Kosmatopoulos
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Applied Sciences
Subjects:
physics-informed neural network
state estimation
distribution networks
unbalanced power systems
data-driven modeling
Online Access:https://www.mdpi.com/2076-3417/15/13/7507
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:State estimation in distribution power systems is increasingly challenged by the proliferation of distributed energy resources (DERs), bidirectional power flows, and the growing complexity of unbalanced network topologies. Physics-Informed Neural Networks (PINNs) offer a compelling solution by integrating machine learning with the physical laws that govern power system behavior. This paper introduces a PINN-based framework for state estimation in unbalanced distribution systems, leveraging available data and embedded physical knowledge to improve accuracy, computational efficiency, and robustness across diverse operating scenarios. The proposed method is evaluated on four IEEE test feeders—IEEE 13, 34, 37, and 123—using synthetic datasets generated via OpenDSS to emulate realistic operating scenarios, and demonstrates significant improvements over baseline models. Notably, the PINN achieves up to a 97% reduction in current estimation errors while maintaining high voltage prediction accuracy. Extensive simulations further assess model performance under noisy inputs and partial observability, where the PINN consistently outperforms conventional data-driven approaches. These results highlight the method’s ability to generalize under uncertainty, accelerate convergence, and preserve physical consistency in simulated real-world conditions without requiring large volumes of labeled training data.
ISSN:2076-3417

Similar Items