Robust Stability Analysis and PINN-Based Monitoring for Hybrid Power Systems Under Heavy Loading Constraints

Thunyaput  Kittiphotiklang; Praphat  Phuangchuen; Somchat  Sonasang; Thananan  Chooseang; Wasan  Phetphimoon; Siriwat  Ninlawat; Prakasit  Prabpal

doi:10.53848/ssstj.v13i2.1720

Authors

Thunyaput Kittiphotiklang Institute of Vocational Education Eastern Region
Praphat Phuangchuen Institute of Vocational Education Eastern Region
Somchat Sonasang Nakhon Phanom University
Thananan Chooseang Pathum Thani Technical College
Wasan Phetphimoon Kamphaeng Phet Rajabhat University
Siriwat Ninlawat Nakhon Phanom University
Prakasit Prabpal Udon Thani Technical College

DOI:

https://doi.org/10.53848/ssstj.v13i2.1720

Keywords:

Physics-Informed Neural Networks (PINNs), Small-signal stability, Waterbed effect, , Hybrid power systems, Participation factor, Inverter-based resources (IBRs)

Abstract

In this paper, the IEEE 39-bus system is used to analyze stability limits for hybrid power systems at high load levels. Consensus diagram via Participation Factor analysis identifies critical oscillations from generators G6 and G7 to exceed a 1.7 load factor, introducing Right-Half Plane poles that will impair control performance (Waterbed Effect). Applying a solid analytical approach, we demonstrate that the system physics limits the sensitivity peak. This is a warning indicator created by a Physics-Informed Neural Network trained on eigenvalue data. Simulations assure that it can accurately mark the most critical nodes as risky nodes and provide a theoretical stability limit, allowing more reliable integration of Inverter-Based Resources in smart grids.

References

Al-Ismail, F. S. (2024). Physics informed neural networks-based AC optimal power flow under high RES penetration. IEEE Access, 12, 189297–189306. https://doi.org/10.1109/access.2024.3514362

Bagheri, Z., Ayyanar, R., Vittal, V., & Khorsand, M. (2025). Enhanced grid support through current limiting for inverter-based resources ensuring compliance with recent LVRT grid codes. 2025 IEEE Power & Energy Society General Meeting (PESGM) (pp. 1–5). IEEE.

Baldan, M., Di Barba, P., & Lowther, D. A. (2023). Physics-informed neural networks for inverse electromagnetic problems. IEEE Transactions on Magnetics, 59(5), 7001705.https://doi.org/10.1109/tmag.2023.3247023

Brendel, P., Medvedev, V., & Rosskopf, A. (2024). Convolutional physics-informed neural networks for fast prediction of core losses in axisymmetric transformers. IEEE Transactions on Magnetics, 60(12), 7201704. https://doi.org/10.1109/tmag.2024.3431703

Chen, L., Saikumar, N., Baldi, S., & HosseinNia, S. H. (2018). Beyond the waterbed effect: Development of fractional order CRONE control with non-linear reset. 2018 Annual American Control Conference (ACC), (pp. 545–552). IEEE.

Dong, Z., Ingalalli, A., Al Mamun, M., Bharati, G., Kamalasadan, S., Chakraborty, S., Paudyal, S., & Ashok, A. (2024). An EMT-phasor co-simulation setup for studying reconfiguration of distribution system with inverter based resources. 2024 IEEE Power & Energy Society General Meeting (PESGM) (pp. 1–5). IEEE.

Ebrahimzadeh, E., Blaabjerg, F., Wang, X., & Bak, C. L. (2018). Bus participation factor analysis for harmonic instability in power electronics based power systems. IEEE Transactions on Power Electronics, 33(12), 10341–10351. https://doi.org/10.1109/tpel.2018.2803846

Fang, Z. (2022). A high-efficient hybrid physics-informed neural networks based on convolutional neural network. IEEE Transactions on Neural Networks and Learning Systems, 33(10), 5514–5526. https://doi.org/10.1109/TNNLS.2021.3070878

Guo, Z., Nguyen, B., & Sabariego, R. V. (2025). Physics-informed neural network for solving 1-D nonlinear time-domain magneto-quasi-static problems. IEEE Transactions on Magnetics, 61(5), 7200709.https://doi.org/10.1109/tmag.2025.3553236

Hong, G., Huang, L., Ju, P., Yu, Y., Sun, B., & Xin, H. (2026). Waterbed effects in power converters: Root of paradox between system stability margin and response speed. Journal of Modern Power Systems and Clean Energy, 1–12.

Huang, K., Xia, T., & Sun, K. (2026). Time-variant nonlinear participation factors for power systems. IEEE Transactions on Power Systems, 41(5), 3460–3477. https://doi.org/10.1109/tpwrs.2026.3673329

Huang, X., & Alkhalifah, T. (2023). GaborPINN: Efficient physics-informed neural networks using multiplicative filtered networks. IEEE Geoscience and Remote Sensing Letters, 20, 3003405.https://doi.org/10.1109/lgrs.2023.3330774

Huang, Z., Chen, D., Qiu, Y., & Ying, K. (2024). Optimization of resource allocation for distributed energy consumption based on a meta-heuristic algorithm. 2024 3rd International Conference on Energy and Electrical Power Systems (ICEEPS), 48, 198–201.

Kini, R. L., Drigal, N., Jiang, Y., Vartanian, C., Maple, S., & Kolln, J. (2025). Integration of distributed energy resources for microgrid. 2025 IEEE PES Grid Edge Technologies Conference & Exposition (Grid Edge) (pp. 1–5). IEEE.

Kongjeen, Y., Pilalum, P., Deeum, S., Suthamno, K., Klayklueng, T., Marsong, S., Ratchapan, R., Buayai, K., Kerdchuen, K., Sa-nga-ngam, W., & Bhumkittipich, K. (2025). Multi-objective optimization of distributed generation placement in electric bus transit systems integrated with flash charging station using enhanced multi-objective grey wolf optimization technique and consensus-based decision support. Energies, 18(14), 3638. https://doi.org/10.3390/en18143638

Leoncini, M., Dago, A., Bertolini, A., Gasparini, A., Levantino, S., & Ghioni, M. (2023). A compact high-efficiency boost converter with time-based control, RHP zero-elimination, and tracking error compensation. IEEE Transactions on Power Electronics, 38(3), 3100–3113.https://doi.org/10.1109/tpel.2022.3222613

Li, K., Tan, S.-C., & Hui, R. (2021). Dynamic response and stability margin improvement of wireless power receiver systems via right-half-plane zero elimination. IEEE Transactions on Power Electronics, 36(10), 11196–11207. https://doi.org/10.1109/tpel.2021.3074324

Liao, Y., & Wang, X. (2020). Impedance-based stability analysis for interconnected converter systems with open-loop RHP poles. IEEE Transactions on Power Electronics, 35(4), 4388–4397.https://doi.org/10.1109/tpel.2019.2939636

Lin, Q., Wen, B., & Burgos, R. (2024). RHP poles trajectory study for D-Q impedance-based stability monitoring using a power-hardware-in-the-loop testbed. IEEE Journal of Emerging and Selected Topics in Power Electronics, 12(2), 1560–1572. https://doi.org/10.1109/jestpe.2023.3312337

Liu, H., & Zhang, D. (2017). Two-phase interleaved inverse-coupled inductor boost without right half-plane zeros. IEEE Transactions on Power Electronics, 32(3), 1844–1859.https://doi.org/10.1109/tpel.2016.2565723

Mahmood, Z. I., Zhang, Y., Cui, H., & Ali, A. (2026). Adaptive frequency control for inverter-based resources via equivalent inertia-based deep reinforcement learning. 2026 IEEE Electrical Energy Storage Applications and Technologies Conference (EESAT) (pp. 1–5). IEEE.

Nathasarma, R., & Roy, B. K. (2023). Physics-informed long-short-term memory neural network for parameters estimation of nonlinear systems. IEEE Transactions on Industry Applications, 59(5), 5376–5384. https://doi.org/10.1109/tia.2023.3280896

Poorali, B., & Adib, E. (2019). Right-half-plane zero elimination of boost converter using magnetic coupling with forward energy transfer. IEEE Transactions on Industrial Electronics, 66(11), 8454–8462. https://doi.org/10.1109/tie.2019.2891408

Sahoo, A. K., Kumar Sahoo, S., & Chakraverty, S. (2025). CL-PINN: A physics-informed neural networks framework for equatorial tsunami wave propagation in geophysical ocean. IEEE Access, 13, 149174–149186. https://doi.org/10.1109/access.2025.3602179

Sajjadi, M., Huang, K., & Sun, K. (2026). Efficient high-order participation factor computation via batch-structured tensor contraction. IEEE Transactions on Power Systems, 41(1), 789–792.https://doi.org/10.1109/tpwrs.2025.3631327

Stoica, P., Li, J., & Ninness, B. (2004). The waterbed effect in spectral estimation. IEEE Signal Processing Magazine, 21(3), 88–100. https://doi.org/10.1109/msp.2004.1296549

Thaitae, N., Summatta, C., Prabpal, P., Yosrueangsak, B., & Sonasang, S. (2023). Hybrid PV and BES for EV charging stations in microgrid systems. Proceedings of the 20th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology (ECTI-CON) (pp. 1–4). https://doi.org/10.1109/ECTI-CON58255.2023.10153262

Thakar, S., Ramasubramanian, D., Matevosyan, J., Najafabadi, F. R., & O’Malley, M. (2024). System services from inverter based resources for reliable operation. 2024 IEEE Power & Energy Society General Meeting (PESGM) (pp. 1–5). IEEE.

Veerachary, M., & Anu. (2022). Stability analysis of coupled-inductor-based buck converter: Participation factors approach. IEEE Transactions on Industry Applications, 58(4), 4967–4979.https://doi.org/10.1109/tia.2022.3174191

Waheed, U. B. (2022). Kronecker neural networks overcome spectral bias for PINN-based wavefield computation. IEEE Geoscience and Remote Sensing Letters, 19, 8029805. https://doi.org/10.1109/lgrs.2022.3209901

Wang, J., Wang, D., Wang, S., & Li, W. (2025). Modeling of permanent magnet eddy current coupler based on unsupervised physics-informed radial-based function neural networks. IEEE Transactions on Magnetics, 61(3), 4900210. https://doi.org/10.1109/tmag.2025.3529855

Xia, T., & Sun, K. (2022). Time-variant nonlinear participation factors considering resonances in power systems. 2022 IEEE Power & Energy Society General Meeting (PESGM) (pp. 01–05). IEEE.

Xin, Z., & Khazaei, J. (2025). Data-centric linear sate feedback control of inverter-based resources (IBRs) using Willems’ fundamental lemma. 2025 14th International Conference on Renewable Energy Research and Applications (ICRERA) (pp. 551–555). IEEE.

Zhang, Y., Fu, H., Qin, Y., Wang, K., & Ma, J. (2022). Physics-informed deep neural network for inhomogeneous magnetized plasma parameter inversion. IEEE Antennas and Wireless Propagation Letters, 21(4), 828–832. https://doi.org/10.1109/lawp.2022.3149889

Zhi-you, X., Li, L., & Di, B. (2010). Equivalent expression of participation factor for weak buses ranking of static voltage static voltage stability. 2010 International Conference on Intelligent System Design and Engineering Application (pp. 676–679). IEEE.

Zhu, S., & Chen, W. (2024). Majorization in Poisson- and Bode-type integrals for multivariable systems: Evenness and k-waterbed effect. IEEE Transactions on Automatic Control, 69(12), 8690–8705.https://doi.org/10.1109/tac.2024.3414550

Zou, J., Liu, C., Song, C., & Zhao, P. (2023). Numerical solver-independent seismic wave simulation using task-decomposed physics-informed neural networks. IEEE Geoscience and Remote Sensing Letters, 20, 3002905. https://doi.org/10.1109/lgrs.2023.3308080

Zou, X., Xie, Y., Duan, Z., Yang, Y., & Liu, Y. (2024). Physics-informed data-driven control strategy classification for inverter based resources during transients. 2024 IEEE Power & Energy Society General Meeting (PESGM) (pp. 1–5). IEEE.