A Load Margin Calculation Method Using a Physics-Informed Neural Network
Source abstract
Abstract
The development of new tools to assist the system operator has been crucial in modern power systems due to the system complexity and operational challenges. Among these tools, the system’s load margin, which indicates the maximum load level allowed without instability occurring, stands out. The physical characteristics of the modern power system in the stability threshold condition and the abundant data from Phasor Measurement Units (PMUs) can be used by machine learning techniques to predict the load margins of power systems. This paper proposes a new Physics-Informed Neural Network for computing the precise value of the load margin of power systems equipped with PMUs adopting experimental and physical knowledge in the training process through three loss functions. A PMU allocation procedure is applied to reduce the number of PINN entries. Case studies applying the proposed PINN are performed on the IEEE 68-bus system, and comparative analyses are conducted with traditional Artificial Neural Networks (ANNs), Graph Neural Networks (GNNs) and Physics-Guided Neural Networks (PGNNs). Results show better Root Mean Square Error values for the proposed PINN compared to the ANN, GNN and PGNN for different numbers of PMUs allocated in the test system.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Power System Optimization and Stability · Power Systems Fault Detection · Frequency Control in Power Systems
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Electrical Engineering, Federal University of Rio de Janeiro, Rio de Janeiro 21941-909, Brazil
Funding
Fundação de Amparo à Pesquisa do Estado de São Paulo · Coordenação de Aperfeicoamento de Pessoal de Nível Superior
References (67)
Show source-provided references
1. Power System Resilience: Current Practices, Challenges, and Future Directions10.1109/ACCESS.2020.2968586 ↗
2. Challenges of renewable energy penetration on power system flexibility: A survey10.1016/j.esr.2020.100539 ↗
3. A review of key power system stability challenges for large-scale PV integration10.1016/j.rser.2014.09.027 ↗
4. A survey on smart grid technologies and applications10.1016/j.renene.2019.08.092 ↗
5. Gao, J., Xu, H., Yang, Y., Niu, H., Liang, J., and Dong, H. (2024). A Multi-Mode Recognition Method for Broadband Oscillation Based on Compressed Sensing and EEMD. Appl. Sci., 14.10.3390/app142411484 ↗
6. Muftić Dedović, M., Mujezinović, A., Dautbašić, N., Alihodžić, A., Memić, A., and Avdaković, S. (2024). Estimation of Power System Inertia with the Integration of Converter-Interfaced Generation via MEMD during a Large Disturbance. Appl. Sci., 14.10.3390/app14020681 ↗
7. Radhoush, S., Vannoy, T., Liyanage, K., Whitaker, B.M., and Nehrir, H. (2023). Distribution System State Estimation Using Hybrid Traditional and Advanced Measurements for Grid Modernization. Appl. Sci., 13.10.3390/app13126938 ↗
8. Real-Time Monitoring of Short-Term Voltage Stability Using PMU Data10.1109/TPWRS.2013.2258946 ↗
9. Estimating the Voltage Stability Margin Using PMU Measurements10.1109/TPWRS.2015.2477426 ↗
10. Adhikari, P.M., Vanfretti, L., Chang, H., and Kar, K. (2023). Real-Time Control of a Battery Energy Storage System Using a Reconfigurable Synchrophasor-Based Control System. Energies, 16.10.3390/en16196909 ↗
11. A Reduced-Order Robust Wide-Area Damping Control for Wind-PV-Thermal-Bundled Power System Considering Operational Uncertainties and Communication Resilience10.1109/ACCESS.2024.3370677 ↗
12. A robust damping control for battery energy storage integrated power systems to mitigate inter-area oscillations10.1016/j.ijepes.2024.109885 ↗
13. A novel wide-area control for general application to inverter-based resources in power systems10.1016/j.ijepes.2024.110086 ↗
14. A Decentralized Wide-Area Voltage Control Scheme for Coordinated Secondary Voltage Regulation Using PMUs10.1109/TPWRS.2024.3381553 ↗
15. A PMU-based back-up protection scheme for fault detection considering uncertainties10.1016/j.ijepes.2022.108592 ↗
16. Wide-Area backup protection against asymmetrical faults in the presence of renewable energy sources10.1016/j.ijepes.2022.108528 ↗
17. Fose, N., Krishnamurthy, S., and Moodley, P. (2024). Improved Control Technique for Enhancing Power System Stability in Out-of-Step Conditions. Energies, 17.10.3390/en17164086 ↗
18. Cutsem, T., and Vournas, C. (1998). Voltage Stability of Electric Power Systems, Springer.10.1007/978-0-387-75536-6 ↗
19. The continuation power flow: A tool for steady state voltage stability analysis10.1109/59.141737 ↗
20. CPFLOW: A practical tool for tracing power system steady-state stationary behavior due to load and generation variations10.1109/59.387897 ↗
21. An approach for monitoring and updating the load margin of power systems in dynamic security assessment10.1016/j.epsr.2021.107365 ↗
22. Online voltage stability and load margin assessment using wide area measurements10.1016/j.ijepes.2019.01.021 ↗
23. A novel method for online voltage stability assessment based on PMU measurements and Thevenin equivalent10.1049/gtd2.12400 ↗
24. Load Margin Assessment of Power Systems Using Artificial Neural Network and Genetic Algorithms10.1016/j.ifacol.2022.04.155 ↗
25. Application of artificial neural networks in voltage stability assessment10.1109/59.476054 ↗
26. A method for monitoring the load margin of power systems under load growth variations10.1016/j.segan.2022.100677 ↗
27. Application of cascaded neural network for prediction of voltage stability margin in a solar and wind integrated power system10.1016/j.engappai.2024.109368 ↗
28. Samy, A.K., and Venkadesan, A. (2022, January 25–27). Evaluation of Voltage Stability Margin in a Power System using an Artificial Neural Network. Proceedings of the 2022 IEEE 10th Power India International Conference (PIICON), Delhi, India.10.1109/PIICON56320.2022.10045272 ↗
29. Shahir, F.M., and Shirazi, P.S. (2020, January 11–12). Monitoring of Voltage Stability Margin by Artificial Neural Network. Proceedings of the 2020 IEEE-HYDCON, Hyderabad, India.10.1109/HYDCON48903.2020.9242707 ↗
30. Dinavahi, V.R., and Srivastava, S.C. (2001, January 15–19). ANN based voltage stability margin prediction. Proceedings of the 2001 Power Engineering Society Summer Meeting. Conference Proceedings (Cat. No.01CH37262), Vancouver, BC, Canada.10.1109/PESS.2001.970256 ↗
31. Load Margin Assessment of Power Systems using Recurrent Neural Network and Greylag Goose Optimization10.1016/j.ifacol.2024.07.587 ↗
32. Graph Neural Networks for Voltage Stability Margins with Topology Flexibilities10.1109/OAJPE.2022.3223962 ↗
33. Online estimation of voltage stability margin via deep neural network with consideration of the local structures in power grid10.1002/2050-7038.12590 ↗
34. Construction of decision tree based on C4.5 algorithm for online voltage stability assessment10.1016/j.ijepes.2019.105793 ↗
35. Li, W., Zhang, P., Su, S., Meng, X., Ding, C., and Wang, Y. (2018, January 4–6). Comparison of Decision Tree Attribute Selection Methods for Static Voltage Stability Margin Assessment. Proceedings of the 2018 IEEE 2nd International Electrical and Energy Conference (CIEEC), Beijing, China.10.1109/CIEEC.2018.8745858 ↗
36. Static voltage stability margin prediction considering new energy uncertainty based on graph attention networks and long short-term memory networks10.1049/rpg2.12731 ↗
37. Fang, H., Xu, R., Zhu, X., Zhao, K., Zhang, P., Ren, C., Li, Q., and Xu, Y. (2019, January 7–9). Knowledge Acquisition of Online Static Voltage Stability Margin Assessment Based on Random Forest Algorithm. Proceedings of the 2019 IEEE 3rd International Electrical and Energy Conference (CIEEC), Beijing, China.10.1109/CIEEC47146.2019.CIEEC-2019197 ↗
38. Li, S., and Ajjarapu, V. (2017, January 16–20). Real-time monitoring of long-term voltage stability via convolutional neural network. Proceedings of the 2017 IEEE Power & Energy Society General Meeting, Chicago, IL, USA.10.1109/PESGM.2017.8274406 ↗
39. Genetic algorithm based support vector machine for on-line voltage stability monitoring10.1016/j.ijepes.2015.05.002 ↗
40. Misyris, G.S., Venzke, A., and Chatzivasileiadis, S. (2020, January 2–6). Physics-Informed Neural Networks for Power Systems. Proceedings of the 2020 IEEE Power & Energy Society General Meeting (PESGM), Montreal, QC, Canada.10.1109/PESGM41954.2020.9282004 ↗
41. Applications of Physics-Informed Neural Networks in Power Systems—A Review10.1109/TPWRS.2022.3162473 ↗
42. Physics-informed graphical neural network for power system state estimation10.1016/j.apenergy.2023.122602 ↗
43. Physics-Informed Neural Networks for AC Optimal Power Flow10.1016/j.epsr.2022.108412 ↗
44. Optimal Power Flow With Physics-Informed Typed Graph Neural Networks10.1109/TPWRS.2024.3394371 ↗
45. Physics-informed machine learning with optimization-based guarantees: Applications to AC power flow10.1016/j.ijepes.2023.109741 ↗
46. Computationally efficient data synthesis for AC-OPF: Integrating Physics-Informed Neural Network solvers and active learning10.1016/j.apenergy.2024.124714 ↗
47. Bayesian Physics-informed Neural Networks for system identification of inverter-dominated power systems10.1016/j.epsr.2024.110860 ↗
48. Physics-informed neural networks for phase locked loop transient stability assessment10.1016/j.epsr.2024.110790 ↗
49. Physics-Guided Neural Network for Load Margin Assessment of Power Systems10.1109/TPWRS.2023.3266236 ↗
50. Bento, M.E.C. (2024). Load Margin Assessment of Power Systems Using Physics-Informed Neural Network with Optimized Parameters. Energies, 17.10.3390/en17071562 ↗
51. Physics-Informed Neural Network for Load Margin Assessment of Power Systems with Optimal Phasor Measurement Unit Placement10.3390/electricity5040039 ↗
52. Physics-informed neural networks for time-domain simulations: Accuracy, computational cost, and flexibility10.1016/j.epsr.2023.109748 ↗
53. PINNSim: A simulator for power system dynamics based on Physics-Informed Neural Networks10.1016/j.epsr.2024.110796 ↗
54. Stiasny, J., Misyris, G.S., and Chatzivasileiadis, S. (July, January 8). Physics-Informed Neural Networks for Non-linear System Identification for Power System Dynamics. Proceedings of the 2021 IEEE Madrid PowerTech, Madrid, Spain.10.1109/PowerTech46648.2021.9495063 ↗
55. A novel frequency-domain physics-informed neural network for accurate prediction of 3D spatio-temporal wind fields in wind turbine applications10.1016/j.apenergy.2025.125526 ↗
56. A hybrid model-data-driven framework for inverse load identification of interval structures based on physics-informed neural network and improved Kalman filter algorithm10.1016/j.apenergy.2024.122740 ↗
57. Ajjarapu, V. (2007). Computational Techniques for Voltage Stability Assessment and Control, Springer.10.1007/978-0-387-32935-2 ↗
58. Rogers, G., Elliott, R.T., Trudnowski, D.J., Wilches-Bernal, F., Osipov, D., and Chow, J.H. (2025). Power System Oscillations: An Introduction to Oscillation Analysis and Control, Springer Nature.10.1007/978-3-031-80581-3 ↗
59. Bento, M.E.C., and Ramos, R.A. (2018, January 5–10). A Method for Dynamic Security Assessment of Power Systems with Simultaneous Consideration of Hopf and Saddle-Node Bifurcations. Proceedings of the 2018 IEEE Power & Energy Society General Meeting (PESGM), Portland, OR, USA.
60. Computing the Load Margin of Power Systems Using Crow Search Algorithm10.1016/j.ifacol.2022.04.045 ↗
61. Bento, M.E.C., and Ramos, R.A. (2021, January 2–5). Computing the Load Margin of Power Systems Using Particle Swarm Optimization. Proceedings of the 2021 IEEE Texas Power and Energy Conference (TPEC), College Station, TX, USA.10.1109/TPEC51183.2021.9384941 ↗
62. Canizares, C., Fernandes, T., Geraldi, E., Gerin-Lajoie, L., Gibbard, M., Hiskens, I., Kersulis, J., Kuiava, R., Lima, L., and DeMarco, F. (2025, August 01). Benchmark Systems for Small-Signal Stability Analysis and Control, Available online: https://resourcecenter.ieee-pes.org/publications/technical-reports/pestr18.
63. Rahman, T.K.A., and Jasmon, G.B. (1995, January 21–23). A new technique for voltage stability analysis in a power system and improved loadflow algorithm for distribution network. Proceedings of the 1995 International Conference on Energy Management and Power Delivery EMPD ’95, Singapore.
64. Training feedforward networks with the Marquardt algorithm10.1109/72.329697 ↗
65. A generalized learning paradigm exploiting the structure of feedforward neural networks10.1109/72.548172 ↗
66. (2025, August 01). MATLAB. Mathworks Inc. Available online: https://www.mathworks.com/products/matlab.html.
67. Benchmark Models for the Analysis and Control of Small-Signal Oscillatory Dynamics in Power Systems10.1109/TPWRS.2016.2561263 ↗