Dynamic State Estimation of Power Systems Using Deep Learning and PMU Data
DOI:
https://doi.org/10.63282/3117-5481/AIJCST-V6I3P104Keywords:
Dynamic State Estimation, Power Systems, Phasor Measurement Units, Deep Learning, Kalman Filters, Smart Grids, ReviewAbstract
Dynamic State Estimation (DSE) is vital to the real-time and robust operation of the contemporary power systems especially during dynamic operating conditions due to the incorporation of renewable energy sources, variability of load, and network disruptions. The conventional methods of DSE, which are mainly founded on the Kalman filtering and observer-based methods, are highly dependent on proper mathematical models of the development of the system. These models are however, not always easy to get or sustain because of the system nonlinearities, lack of parameters, and changing topologies. Massive application of Phasor Measurement Units (PMUs) has made it possible to make high-resolution time-synchronized measurements, leading to a move away towards data-driven estimation methods. The recent years have witnessed deep learning (DL) as a potent alternative to dynamic state estimation, which provides good nonlinear modeling ability and resistance to uncertainties without explicit models of the system. The paper gives a detailed review of the dynamic state estimation of power systems with emphasis on the deep learning methods inferred on the PMU data. The development of the traditional Kalman filter-based approaches to the modern deep learning based systems is discussed in a systematic way. Different deep learning networks, such as recycling neural network, long short-term memory networks, convolutional neural networks, graph neural networks, and transformer based networks are discussed and compared. The essential issues concerning the PMU data quality, scalability, usability, and real-time implementation are addressed. Lastly, the actual research problems and future outlook are determined as an indicator of further developing deep learning-based dynamic state estimation.
References
[1] Upadhyay, D., & Sampalli, S. (2020). SCADA (Supervisory Control and Data Acquisition) systems: Vulnerability assessment and security recommendations. Computers & Security, 89, 101666.
[2] Pazderin, A., Zicmane, I., Senyuk, M., Gubin, P., Polyakov, I., Mukhlynin, N., ... & Kamalov, F. (2023). Directions of application of phasor measurement units for control and monitoring of modern power systems: A state-of-the-art review. Energies, 16(17), 6203.
[3] Yang, S., & Baum, M. (2017, March). Extended Kalman filter for extended object tracking. In 2017 IEEE international conference on acoustics, speech and signal processing (ICASSP) (pp. 4386-4390). IEEE.
[4] Shinde, B. T. (2020). Real-time stability surveillance in power systems: a deep learning approach. The George Washington University.
[5] Zhao, J., Gómez-Expósito, A., Netto, M., Mili, L., Abur, A., Terzija, V., ... & Meliopoulos, A. S. (2019). Power system dynamic state estimation: Motivations, definitions, methodologies, and future work. IEEE Transactions on Power Systems, 34(4), 3188-3198.
[6] Zhang, K., Zhang, L., & Xie, L. (2020). Discrete-time and discrete-space dynamical systems. Springer International Publishing.
[7] Zhou, N., Meng, D., Huang, Z., & Welch, G. (2014). Dynamic state estimation of a synchronous machine using PMU data: A comparative study. IEEE Transactions on Smart grid, 6(1), 450-460.
[8] Kumari, N., Kulkarni, R., Ahmed, M. R., & Kumar, N. (2021). Use of kalman filter and its variants in state estimation: A review. Artificial intelligence for a sustainable industry 4.0, 213-230.
[9] Sun, Y., Bao, W., Valk, K., Brauer, C. C., Sumihar, J., & Weerts, A. H. (2020). Improving forecast skill of lowland hydrological models using ensemble Kalman filter and unscented Kalman filter. Water Resources Research, 56(8), e2020WR027468.
[10] Zhao, J., Netto, M., & Mili, L. (2016). A robust iterated extended Kalman filter for power system dynamic state estimation. IEEE transactions on power systems, 32(4), 3205-3216.
[11] Shlezinger, N., Whang, J., Eldar, Y. C., & Dimakis, A. G. (2023). Model-based deep learning. Proceedings of the IEEE, 111(5), 465-499.
[12] Al-Sharman, M. K., Zweiri, Y., Jaradat, M. A. K., Al-Husari, R., Gan, D., & Seneviratne, L. D. (2019). Deep-learning-based neural network training for state estimation enhancement: Application to attitude estimation. IEEE Transactions on Instrumentation and Measurement, 69(1), 24-34.
[13] Suykens, J. A., Vandewalle, J. P., & De Moor, B. L. (2012). Artificial neural networks for modelling and control of non-linear systems. Springer Science & Business Media.
[14] Zhang, L., Cheng, L., Li, H., Gao, J., Yu, C., Domel, R., ... & Liu, W. K. (2021). Hierarchical deep-learning neural networks: finite elements and beyond. Computational Mechanics, 67(1), 207-230.
[15] Wang, S., Dehghanian, P., & Li, L. (2019). Power grid online surveillance through PMU-embedded convolutional neural networks. IEEE Transactions on Industry Applications, 56(2), 1146-1155.
[16] Shadi, M. R., Ameli, M. T., & Azad, S. (2022). A real-time hierarchical framework for fault detection, classification, and location in power systems using PMUs data and deep learning. International Journal of Electrical Power & Energy Systems, 134, 107399.
[17] Chandra, N., Ahuja, L., Khatri, S. K., & Monga, H. (2021). Utilizing gated recurrent units to retain long term dependencies with recurrent neural network in text classification.
[18] Zarzycki, K., & Ławryńczuk, M. (2021). LSTM and GRU neural networks as models of dynamical processes used in predictive control: A comparison of models developed for two chemical reactors. Sensors, 21(16), 5625.
[19] Liu, Y., Xie, H., Presekal, A., Stefanov, A., & Palensky, P. (2023). A GNN-based generative model for generating synthetic cyber-physical power system topology. IEEE Transactions on Smart Grid, 14(6), 4968-4971.
[20] L’Heureux, A., Grolinger, K., & Capretz, M. A. (2022). Transformer-based model for electrical load forecasting. Energies, 15(14), 4993.
[21] Yao, D., Zhi-li, Z., Xiao-feng, Z., Wei, C., Fang, H., Yao-ming, C., & Cai, W. W. (2023). Deep hybrid: multi-graph neural network collaboration for hyperspectral image classification. Defence Technology, 23, 164-176.
[22] Tu, C., He, X., Liu, X., & Li, P. (2018). Cyber-attacks in PMU-based power network and countermeasures. IEEE Access, 6, 65594-65603.
[23] K. Gandhi and P. Verma, “Wind and solar power generation forecasting using hybrid deep-learning models,” Amer. J. Comput. Eng., vol. 5, no. 2, pp. 50–69, 2022.
[24] P. Verma and K. Gandhi, “Anomaly detection in pipeline operations using unsupervised and semi-supervised learning,” Amer. J. Comput. Eng., vol. 6, no. 2, pp. 1–17, 2023.
