Intelligent voltage sag management in smat grids: A review of machine learing predicion and cooperative control techniques
Wanting Xu
Faculty of Information Technology, City University Malaysia/Faculty of Automotive and Aviation, Wuhu Vocational Technical University
Amirrudin Kamsin
Faculty of Information Technology, City University Malaysia/ Department of Computer System &Technology, Faculty of Computer Science and Information Technology, Universiti Malaya
DOI: https://doi.org/10.59429/esta.v12i4.12670
Keywords: voltage sag management; smart grids; machine learning; multi-agent reinforcement learning (MARL); CTDE paradigm; deep learning
Abstract
Voltage sags are critical power quality disturbances in modern smart grids, worsened by renewable energy integration and distributed generation. Traditional physics-based methods fail to handle high-dimensional data and non-linear dynamics, prompting the adoption of machine learning (ML) for prediction and multi-agent reinforcement learning (MARL) for cooperative control. This review synthesizes key advances in ML (traditional techniques and deep learning) for sag detection/classification, and MARL (via the CTDE paradigm) for distributed voltage regulation. Critical gaps—Rigid architectures, deployment barriers, lack of benchmarks—are identified, with pathways to unify prediction and control. It provides a foundation for advancing intelligent sag management in smart grids.
References
[1] D.W. Chakeres, F.D. Vocht, Static magnetic field effects on human subjects related to magnetic resonance imaging systems, Prog. Biophys. Mol. Biol. 87 (2–3) (2005) 255–265.
[2] J. Liu, Y. Pan, M. Li, Z. Chen, L. Tang, C. Lu, J. Wang, Applications of deep learning to MRI images: asurvey, Big Data Min. Anal. 1 (1) (2018) 1–18, doi: 10.26599/BDMA.2018.9020 0 01.
[3] M. Lustig, D. Donoho, J.M. Pauly, Sparse MRI: the application of compressed sensing for rapid MR imaging, Magn. Reson. Med. 58 (6) (2007) 1182–1195.
[4] X. Zhang, D. Guo, Y. Huang, Y. Chen, L. Wang, F. Huang, Q. Xu, X. Qu, Image reconstruction with lowrankness and self-consistency of k -space data in parallel MRI, Med. Image Anal. 63 (2020) 101687, doi: 10.1016/j.media.2020.101687.
[5] D.L. Donoho, Compressed sensing, IEEE Trans. Inf. Theory 52 (4) (2006) 1289–1306.
[6] M. Lustig, D.L. Donoho, J.M. Santos, J.M. Pauly, Compressed sensing MRI, IEEE Signal Process. Mag. 25 (2) (2008) 72–82.
[7] Y. Chen, C.-B. Schonlieb, P. Lio, T. Leiner, P.L. Dragotti, G. Wang, D. Rueckert,D. Firmin, G. Yang, AI-based reconstruction for fast MRI–A systematic review and meta-analysis, Proc. IEEE 110 (2) (2022) 224–245, doi: 10.1109/JPROC.2022.3141367.
[8] Y. Yang, J. Sun, H. Li, Z. Xu, Deep ADMM-net for compressive sensing MRI, in: D.D. Lee, M. Sugiyama, U. von Luxburg, I. Guyon, R. Garnett (Eds.), Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, December 5–10, 2016, Barcelona, Spain, 2016, pp. 10–18.
[9] S.U.H. Dar, M. Yurt, M. Shahdloo, M.E. Ildiz, B. Tinaz, T. Cukur, Prior-guided image reconstruction for accelerated multi-contrast MRI via generative adversarial networks, IEEE J. Sel. Top. Signal Process. 14 (6) (2020) 1072–1087, doi: 10.1109/JSTSP.2020.3001737.
[10] J. Shi, Q. Liu, C. Wang, Q. Zhang, S. Ying, H. Xu, Super-resolution reconstruction of MR image with a novel residual learning network algorithm, Phys. Med. Biol. 63 (8) (2018) 085011, doi: 10.1088/1361-6560/aab9e9.