Physics-Informed Learning for Predicting Transient Voltage Angles in Renewable Power Systems Under Gusty Conditions
As renewable energy penetration and extreme weather events increase, accurately predicting power system behavior is essential for reducing risks and enabling timely interventions. This study presents a physics-informed learning approach to forecast transient voltage angles in power systems with inte...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-06-01
|
| Series: | Electricity |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2673-4826/6/2/34 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849433462006611968 |
|---|---|
| author | Ruoqing Yin Liz Varga |
| author_facet | Ruoqing Yin Liz Varga |
| author_sort | Ruoqing Yin |
| collection | DOAJ |
| description | As renewable energy penetration and extreme weather events increase, accurately predicting power system behavior is essential for reducing risks and enabling timely interventions. This study presents a physics-informed learning approach to forecast transient voltage angles in power systems with integrated wind energy under gusty wind conditions. We developed a simulation framework that generates wind power profiles with significant gust-induced variations over a one-minute period. We evaluated the effectiveness of physics-informed neural networks (PINNs) by integrating them with LSTM (long short-term memory) and GRU (gated recurrent unit) architectures and compared their performance to standard LSTM and GRU models trained using only mean squared error (MSE) loss. The models were tested under three wind energy penetration scenarios—20%, 40%, and 60%. Results show that the predictive accuracy of PINN-based models improves as wind penetration increases, and the best-performing model varies depending on the penetration level. Overall, this study highlights the value of physics-informed learning for dynamic prediction under extreme weather conditions and provides practical guidance for selecting appropriate models based on renewable energy integration levels. |
| format | Article |
| id | doaj-art-013b90f396eb48b291422ea09b275484 |
| institution | Kabale University |
| issn | 2673-4826 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electricity |
| spelling | doaj-art-013b90f396eb48b291422ea09b2754842025-08-20T03:27:01ZengMDPI AGElectricity2673-48262025-06-01623410.3390/electricity6020034Physics-Informed Learning for Predicting Transient Voltage Angles in Renewable Power Systems Under Gusty ConditionsRuoqing Yin0Liz Varga1Department of Civil, Environmental and Geomatic Engineering, University College London, London WC1E 6BT, UKDepartment of Civil, Environmental and Geomatic Engineering, University College London, London WC1E 6BT, UKAs renewable energy penetration and extreme weather events increase, accurately predicting power system behavior is essential for reducing risks and enabling timely interventions. This study presents a physics-informed learning approach to forecast transient voltage angles in power systems with integrated wind energy under gusty wind conditions. We developed a simulation framework that generates wind power profiles with significant gust-induced variations over a one-minute period. We evaluated the effectiveness of physics-informed neural networks (PINNs) by integrating them with LSTM (long short-term memory) and GRU (gated recurrent unit) architectures and compared their performance to standard LSTM and GRU models trained using only mean squared error (MSE) loss. The models were tested under three wind energy penetration scenarios—20%, 40%, and 60%. Results show that the predictive accuracy of PINN-based models improves as wind penetration increases, and the best-performing model varies depending on the penetration level. Overall, this study highlights the value of physics-informed learning for dynamic prediction under extreme weather conditions and provides practical guidance for selecting appropriate models based on renewable energy integration levels.https://www.mdpi.com/2673-4826/6/2/34physics-informed neural networkrenewable energyextreme weather conditiondynamic state estimationpower system |
| spellingShingle | Ruoqing Yin Liz Varga Physics-Informed Learning for Predicting Transient Voltage Angles in Renewable Power Systems Under Gusty Conditions Electricity physics-informed neural network renewable energy extreme weather condition dynamic state estimation power system |
| title | Physics-Informed Learning for Predicting Transient Voltage Angles in Renewable Power Systems Under Gusty Conditions |
| title_full | Physics-Informed Learning for Predicting Transient Voltage Angles in Renewable Power Systems Under Gusty Conditions |
| title_fullStr | Physics-Informed Learning for Predicting Transient Voltage Angles in Renewable Power Systems Under Gusty Conditions |
| title_full_unstemmed | Physics-Informed Learning for Predicting Transient Voltage Angles in Renewable Power Systems Under Gusty Conditions |
| title_short | Physics-Informed Learning for Predicting Transient Voltage Angles in Renewable Power Systems Under Gusty Conditions |
| title_sort | physics informed learning for predicting transient voltage angles in renewable power systems under gusty conditions |
| topic | physics-informed neural network renewable energy extreme weather condition dynamic state estimation power system |
| url | https://www.mdpi.com/2673-4826/6/2/34 |
| work_keys_str_mv | AT ruoqingyin physicsinformedlearningforpredictingtransientvoltageanglesinrenewablepowersystemsundergustyconditions AT lizvarga physicsinformedlearningforpredictingtransientvoltageanglesinrenewablepowersystemsundergustyconditions |