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...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-07-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/13/7507 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1839632328508309504 |
|---|---|
| author | Petros Iliadis Stefanos Petridis Angelos Skembris Dimitrios Rakopoulos Elias Kosmatopoulos |
| author_facet | Petros Iliadis Stefanos Petridis Angelos Skembris Dimitrios Rakopoulos Elias Kosmatopoulos |
| author_sort | Petros Iliadis |
| collection | DOAJ |
| description | 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. |
| format | Article |
| id | doaj-art-cc9ca488687e4adb8071176d2be3f037 |
| institution | Matheson Library |
| issn | 2076-3417 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-cc9ca488687e4adb8071176d2be3f0372025-07-11T14:36:50ZengMDPI AGApplied Sciences2076-34172025-07-011513750710.3390/app15137507Physics-Informed Neural Networks for Enhanced State Estimation in Unbalanced Distribution Power SystemsPetros Iliadis0Stefanos Petridis1Angelos Skembris2Dimitrios Rakopoulos3Elias Kosmatopoulos4Department of Electrical and Computer Engineering, Democritus University of Thrace, 67100 Xanthi, GreeceDepartment of Electrical and Computer Engineering, Democritus University of Thrace, 67100 Xanthi, GreeceSUSTENERGO CERTH Spin-off P.C., 50100 Kozani, GreeceSUSTENERGO CERTH Spin-off P.C., 50100 Kozani, GreeceDepartment of Electrical and Computer Engineering, Democritus University of Thrace, 67100 Xanthi, GreeceState 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.https://www.mdpi.com/2076-3417/15/13/7507physics-informed neural networkstate estimationdistribution networksunbalanced power systemsdata-driven modeling |
| spellingShingle | Petros Iliadis Stefanos Petridis Angelos Skembris Dimitrios Rakopoulos Elias Kosmatopoulos Physics-Informed Neural Networks for Enhanced State Estimation in Unbalanced Distribution Power Systems Applied Sciences physics-informed neural network state estimation distribution networks unbalanced power systems data-driven modeling |
| title | Physics-Informed Neural Networks for Enhanced State Estimation in Unbalanced Distribution Power Systems |
| title_full | Physics-Informed Neural Networks for Enhanced State Estimation in Unbalanced Distribution Power Systems |
| title_fullStr | Physics-Informed Neural Networks for Enhanced State Estimation in Unbalanced Distribution Power Systems |
| title_full_unstemmed | Physics-Informed Neural Networks for Enhanced State Estimation in Unbalanced Distribution Power Systems |
| title_short | Physics-Informed Neural Networks for Enhanced State Estimation in Unbalanced Distribution Power Systems |
| title_sort | physics informed neural networks for enhanced state estimation in unbalanced distribution power systems |
| topic | physics-informed neural network state estimation distribution networks unbalanced power systems data-driven modeling |
| url | https://www.mdpi.com/2076-3417/15/13/7507 |
| work_keys_str_mv | AT petrosiliadis physicsinformedneuralnetworksforenhancedstateestimationinunbalanceddistributionpowersystems AT stefanospetridis physicsinformedneuralnetworksforenhancedstateestimationinunbalanceddistributionpowersystems AT angelosskembris physicsinformedneuralnetworksforenhancedstateestimationinunbalanceddistributionpowersystems AT dimitriosrakopoulos physicsinformedneuralnetworksforenhancedstateestimationinunbalanceddistributionpowersystems AT eliaskosmatopoulos physicsinformedneuralnetworksforenhancedstateestimationinunbalanceddistributionpowersystems |