Research on the Construction of a Short-Term Voltage Prediction Model Integrating Topological Data Analysis and Deep Neural Network under the Power System Resilience Assessment Framework

Hongjun Wang; Tao Li; Zhiliang Dong

doi:10.4108/ew.8896

Authors

Hongjun Wang Xinxiang Institute of Engineering
Tao Li Xinxiang Vocational and Technical College
Zhiliang Dong Shanxi Zaokuang Hongdunjie Coal and Electricity Co., Ltd

DOI:

https://doi.org/10.4108/ew.8896

Abstract

INTRODUCTION: This paper examines the stability of small disturbances in wind farm grid-connected systems within the framework of power system resilience. With increasing renewable integration, minor disturbances can escalate into cascading failures, threatening grid reliability.

OBJECTIVES: The goal is to build a short-term voltage prediction model by integrating Topological Data Analysis (TDA) with Deep Belief Networks (DBN) and to propose a coordinated reactive power control strategy that enhances system dynamic performance under small disturbances.

METHODS: The study adopts a VSC-HVDC system based on Modular Multilevel Converters (MMC) to model wind farm connectivity. A cluster-based reactive power control approach is applied by grouping wind turbines with similar operational characteristics. Small disturbance signals are simulated, and both unified and decentralised Doubly Fed Induction Generator (DFIG) control schemes are compared using impedance modelling and time-domain analysis.

RESULTS: Simulations indicate that small AC-side disturbances have a significant impact on reactive power and system voltage, whereas DC-side faults affect frequency stability. The decentralised DFIG coordination strategy achieved a lower network loss (0.467 MW) compared to the unified approach (0.473 MW) while also improving reactive power allocation and system responsiveness.

CONCLUSION: By combining TDA and DBN with decentralised control, the proposed model enhances the stability of small disturbances in wind-integrated power systems. It enhances fault tolerance, mitigates power fluctuations, and facilitates the resilient operation of renewable-rich grids.

Downloads

Download data is not yet available.

References

[1] Wen, T., Zhang, Z., Lin, X., Li, Z., Chen, C., & Wang, Z. (2020). Research on modelling and the operation strategy of a hydrogen-battery hybrid energy storage system for flexible wind farm grid connection. IEEE Access, 8, 79347-79356. https://doi.org/10.1109/ACCESS.2020.2998365 DOI: https://doi.org/10.1109/ACCESS.2020.2990581

[2] Ahmed, S. A. M., & Abd El Sattar, M. (2019). Dynamic performance and effectiveness of voltage disturbances on the improvement of power quality for grid-connected DFIG system-based wind farm. Journal of Electrical Engineering, Electronics, Control and Computer Science, 5(3), 25-30.

[3] Dong, W., Du, W., Xie, X., & Wang, H. F. (2021). An approximate aggregated impedance model of a grid-connected wind farm for the study of small-signal stability. IEEE Transactions on Power Systems, 37(5), 3847-3861. https://doi.org/10.1109/TPWRS.2021.3071105 DOI: https://doi.org/10.1109/TPWRS.2021.3138107

[4] Nobela, O. N., Bansal, R. C., & Justo, J. J. (2019). A review of power quality compatibility of wind energy conversion systems with the South African utility grid. Renewable Energy Focus, 31, 63-72. https://doi.org/10.1016/j.ref.2019.04.005 DOI: https://doi.org/10.1016/j.ref.2019.10.001

[5] Tazay, A. F., Ibrahim, A. M. A., Noureldeen, O., & Hamdan, I. (2020). Modelling, control, and performance evaluation of grid-tied hybrid PV/wind power generation system: A case study of Gabel El-Zeit region, Egypt. IEEE Access, 8, 96528-96542. https://doi.org/10.1109/ACCESS.2020.2999795 DOI: https://doi.org/10.1109/ACCESS.2020.2993919

[6] Alagarsundaram, P., Ramamoorthy, S. K., Mazumder, D., Malathy, V., & Soni, M. (2024, August). A Short-Term Load Forecasting model using Restricted Boltzmann Machines and a Bi-directional Gated Recurrent Unit. In 2024 Second International Conference on Networks, Multimedia and Information Technology (NMITCON) (pp. 1-5). IEEE. DOI: https://doi.org/10.1109/NMITCON62075.2024.10699152

[7] Yang, P., Dong, X., Li, Y., Kuang, L., Zhang, J., He, B., & Wang, Y. (2019). Research on primary frequency regulation control strategy of wind-thermal power coordination. IEEE Access, 7, 144766-144776. https://doi.org/10.1109/ACCESS.2019.2948363 DOI: https://doi.org/10.1109/ACCESS.2019.2946192

[8] Zhao, S., Wang, N., Li, R., Gao, B., Shao, B., & Song, S. (2019). Sub-synchronous control interaction between direct-drive PMSG-based wind farms and compensated grids. International Journal of Electrical Power & Energy Systems, 109, 609-617. https://doi.org/10.1016/j.ijepes.2019.01.050 DOI: https://doi.org/10.1016/j.ijepes.2019.02.021

[9] Tao, S., Xu, Q., Feijóo, A., & Zheng, G. (2020). Joint optimization of wind turbine microsite and cabling in an offshore wind farm. IEEE Transactions on Smart Grid, 12(1), 834-844. https://doi.org/10.1109/TSG.2020.2955889 DOI: https://doi.org/10.1109/TSG.2020.3022378

[10] Zhou, J., Li, B., Zhang, D., Yuan, J., Zhang, W., & Cai, Z. (2023). UGIF-Net: An efficient, fully guided information flow network for underwater image enhancement. IEEE Transactions on Geoscience and Remote Sensing, 61, 1-17. https://doi.org/10.1109/TGRS.2023.3293912 DOI: https://doi.org/10.1109/TGRS.2023.3293912

[11] Xue, T., Lyu, J., Wang, H., & Cai, X. (2021). A complete impedance model of a PMSG-based wind energy conversion system and its effect on the stability analysis of MMC-HVDC connected offshore wind farms. IEEE Transactions on Energy Conversion, 36(4), 3449-3461. https://doi.org/10.1109/TEC.2021.3079225 DOI: https://doi.org/10.1109/TEC.2021.3074798

[12] Chen, X., Huo, L., & Sun, C. (2025). Deep-learning-based short-term voltage stability assessment with topology-adaptive voltage dynamic feature and domain transfer. Journal of Modern Power Systems and Clean Energy. https://doi.org/10.1007/s40500-025-00548-w

[13] Miraftabzadeh, S. M., Di Martino, A., Longo, M., & Zaninelli, D. (2024). Deep learning in power systems: A bibliometric analysis and future trends. IEEE Access. https://doi.org/10.1109/ACCESS.2024.3125183 DOI: https://doi.org/10.1109/ACCESS.2024.3491914

[14] Chen, Y., Jacob, R. A., Gel, Y. R., Zhang, J., & Poor, H. V. (2023). Learning power grid outages with higher-order topological neural networks. IEEE Transactions on Power Systems, 39(1), 720-732. https://doi.org/10.1109/TPWRS.2023.3145839 DOI: https://doi.org/10.1109/TPWRS.2023.3266956

[15] Nelson, S., Yallamelli, A. R. G., Alkhayyat, A., & Saranya, N. N. (2024, July). Hybrid autoregressive integrated moving average and bi-directional gated recurrent unit for time series forecasting. In 2024 International Conference on Data Science and Network Security (ICDSNS) (pp. 1-4). IEEE. DOI: https://doi.org/10.1109/ICDSNS62112.2024.10690898

[16] Yang, L., & Teh, J. (2023). Review of Vulnerability Analysis of Power Distribution Networks. Electric Power Systems Research, 224, 109741. https://doi.org/10.1016/j.epsr.2023.109741 DOI: https://doi.org/10.1016/j.epsr.2023.109741

[17] Zhu, Y., Zhou, Y., Sun, Y., & Li, W. (2024). Fast resilience assessment for power systems under typhoons based on spatial-temporal graphs. IEEE Systems Journal. https://doi.org/10.1109/JSYST.2024.3147665 DOI: https://doi.org/10.1109/JSYST.2024.3496754

[18] Dyavani, N. R., Ubagaram, C., Garikipati, V., Jayaprakasam, B. S., Mandala, R. R., & Thanjaivadivel, M. Adaptive Access Control in SHACS: Leveraging Markov Models and Topological Data Analysis for Enhanced Cloud Security.

[19] Zhang, C., Shan, G., & Roh, B. H. (2024). Communication-efficient federated multi-domain learning for network anomaly detection. Digital Communications and Networks. https://doi.org/10.1016/j.dcan.2024.01.002 DOI: https://doi.org/10.1016/j.dcan.2024.11.014

[20] Hijazi, M., Dehghanian, P., & Wang, S. (2023). Transfer learning for transient stability predictions in modern power systems under enduring topological changes. IEEE Transactions on Automation Science and Engineering. https://doi.org/10.1109/TASE.2023.3174289 DOI: https://doi.org/10.1109/TASE.2023.3277536

[21] Xu, Y., Lv, J., Wang, J., Ye, F., Ye, S., & Ji, J. (2024). Identifying topology of distribution substation in power Internet of Things using dynamic voltage load fluctuation flow analysis. PeerJ Computer Science, 10, e1688. https://doi.org/10.7717/peerj-cs.1688 DOI: https://doi.org/10.7717/peerj-cs.1688

[22] Han, Y., Jia, R., Luan, W., Zhao, B., Cai, H., & Liu, B. (2024, April). Data-driven mid-term load forecasting based on topological data analysis. In 2024 9th Asia Conference on Power and Electrical Engineering (ACPEE) (pp. 338-344). IEEE. https://doi.org/10.1109/ACPEE50219.2024.00081 DOI: https://doi.org/10.1109/ACPEE60788.2024.10532533

[23] Gattupalli, K., Gollavilli, V. S. B. H., Nagarajan, H., Alagarsundaram, P., Sitaraman, S. R., & Jayanthi. (2025). Applying deep belief networks and cloud technology for early detection of stroke in medical environments. International Journal of Engineering, Management and Humanities (IJEMH), 6(2), 107–113.