858
Views
72
Downloads
0
Crossref
N/A
WoS
0
Scopus
N/A
CSCD
Federated-learning-based active fault management (AFM) is devised to achieve real-time safety assurance for microgrids and the main grid during faults. AFM was originally formulated as a distributed optimization problem. Here, federated learning is used to train each microgrid’s network with training data achieved from distributed optimization. The main contribution of this work is to replace the optimization-based AFM control algorithm with a learning-based AFM control algorithm. The replacement transfers computation from online to offline. With this replacement, the control algorithm can meet real-time requirements for a system with dozens of microgrids. By contrast, distributed-optimization-based fault management can output reference values fast enough for a system with several microgrids. More microgrids, however, lead to more computation time with optimization-based method. Distributed-optimization-based fault management would fail real-time requirements for a system with dozens of microgrids. Controller hardware-in-the-loop real-time simulations demonstrate that learning-based AFM can output reference values within 10 ms irrespective of the number of microgrids.
Federated-learning-based active fault management (AFM) is devised to achieve real-time safety assurance for microgrids and the main grid during faults. AFM was originally formulated as a distributed optimization problem. Here, federated learning is used to train each microgrid’s network with training data achieved from distributed optimization. The main contribution of this work is to replace the optimization-based AFM control algorithm with a learning-based AFM control algorithm. The replacement transfers computation from online to offline. With this replacement, the control algorithm can meet real-time requirements for a system with dozens of microgrids. By contrast, distributed-optimization-based fault management can output reference values fast enough for a system with several microgrids. More microgrids, however, lead to more computation time with optimization-based method. Distributed-optimization-based fault management would fail real-time requirements for a system with dozens of microgrids. Controller hardware-in-the-loop real-time simulations demonstrate that learning-based AFM can output reference values within 10 ms irrespective of the number of microgrids.
Wang, L. Z., Qin, Y. Y., Tang, Z. F., Zhang, P. (2020). Software-defined microgrid control: The genesis of decoupled cyber-physical microgrids. IEEE Open Access Journal of Power and Energy, 7: 173–182.
Hooshyar, A., El-Saadany, E. F., Sanaye-Pasand, M. (2016). Fault type classification in microgrids including photovoltaic DGs. IEEE Transactions on Smart Grid, 7: 2218–2229.
Zhou, Y. F., Zhang, P., Yue, M. (2021). Reachable dynamics of networked microgrids with large disturbances. IEEE Transactions on Power Systems, 36: 2416–2427.
Hansen, A. D., Michalke, G. (2007). Fault ride-through capability of DFIG wind turbines. Renewable Energy, 32: 1594–1610.
Giachetti, R. E., Peterson, C. J., van Bossuyt, D. L., Parker, G. W. (2020). Systems engineering issues in microgrids for military installations. INCOSE International Symposium, 30: 731–746.
Ortiz, L., González, J. W., Gutierrez, L. B., Llanes-Santiago, O. (2020). A review on control and fault-tolerant control systems of AC/DC microgrids. Heliyon, 6: e04799.
Buraimoh, E., Davidson, I. E., Martinez-Rodrigo, F. (2019). Fault ride-through enhancement of grid supporting inverter-based microgrid using delayed signal cancellation algorithm secondary control. Energies, 12: 3994.
Rosas-Caro, J. C., García-Vite, P. M., Rodríguez, A., Mendoza, A., Alejo-Reyes, A., Cuevas, E., Beltran-Carbajal, F. (2021). Differential evolution based algorithm for optimal current ripple cancelation in an unequal interleaved power converter. Mathematics, 9: 2755.
Wan, W. F., Bragin, M. A., Yan, B., Qin, Y. Y., Philhower, J., Zhang, P., Luh, P. B. (2020). Distributed and asynchronous active fault management for networked microgrids. IEEE Transactions on Power Systems, 35: 3857–3868.
Wan, W. F., Zhang, P., Bragin, M. A., Luh, P. B. (2022). Cooperative fault management for resilient integration of renewable energy. Electric Power Systems Research, 211: 108147.
Li, T., Sahu, A. K., Talwalkar, A., Smith, V. (2020). Federated learning: Challenges, methods, and future directions. IEEE Signal Processing Magazine, 37: 50–60.
Yang, Q., Liu, Y., Chen, T. J., Tong, Y. X. (2019). Federated machine learning. ACM Transactions on Intelligent Systems and Technology, 10: 1–19.
Bragin, M. A., Yan, B., Luh, P. B. (2020). Distributed and asynchronous coordination of a mixed-integer linear system via surrogate lagrangian relaxation. IEEE Transactions on Automation Science and Engineering, 18: 1191–1205.
Bragin, M. A., Luh, P. B., Yan, J. H., Yu, N. P., Stern, G. A. (2015). Convergence of the surrogate Lagrangian relaxation method. Journal of Optimization Theory and Applications, 164: 173–201.
Nikmehr, N., Bragin, M. A., Zhang, P., Luh, P. B. (2022). Computationally distributed and asynchronous operational optimization of droop-controlled networked microgrids. IEEE Open Access Journal of Power and Energy, 9: 265–277.
Nguyen, H. T., Sehwag, V., Hosseinalipour, S., Brinton, C. G., Chiang, M., Vincent Poor, H. (2021). Fast-convergent federated learning. IEEE Journal on Selected Areas in Communications, 39: 201–218.
Chen, M. Z., Poor, H. V., Saad, W., Cui, S. G. (2021). Convergence time optimization for federated learning over wireless networks. IEEE Transactions on Wireless Communications, 20: 2457–2471.
Peterson, C. J., van Bossuyt, D. L., Giachetti, R. E., Oriti, G. (2021). Analyzing mission impact of military installations microgrid for resilience. Systems, 9: 69.
Giachetti, R. E., Bossuyt, D. L. V., Anderson, W. W., Oriti, G. (2022). Resilience and cost trade space for microgrids on Islands. IEEE Systems Journal, 16: 3939–3949.
This work was supported in part by the National Science Foundation under Grants No. OIA-2134840 and ECCS-1810108, and in part by Department of Energy under Grant No. DE-EE0009341. This work relates to Department of Navy award N00014-20-1-2858 issued by the Office of Naval Research. The United States Government has a royalty-free license throughout the world in all copyrightable material contained herein.
Copyright: by the author(s). The articles published in this open access journal are distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/).