Load control in smart grids: a review of NILM-, machine learn-, and reflectometry-based approaches

Authors

DOI:

https://doi.org/10.21712/lajer.2025.v12.n3.p145-153

Keywords:

Machine learning; Load control; NILM; Reflectometry; Smart grids.

Abstract

Load control is essential for the efficient management of energy systems, especially in smart grids with distributed generation. This management relies on data collection through sensors, which are later processed by machine learning algorithms. This study aims to analyze the main load classification methods, the algorithms employed, and their various applications in real-world contexts. The adopted methodology consists of a comparative review of three approaches: (i) non-intrusive load monitoring (NILM), (ii) methods using sensors based on reflectometry, and (iii) independent techniques that utilize machine learning and the Internet of Things (IoT). The results indicate that, although NILM is widely used for load monitoring and independent methods offer diverse strategies for real-time tracking, approaches based on reflectometry sensors demonstrate greater potential in improving accuracy and enhancing load control. This study also highlights accessible and sustainable solutions for the energy sector and emphasizes the untapped potential of reflectometry in smart electrical grids, a recent and promising topic.

Downloads

Download data is not yet available.

Author Biographies

  • João José de Sousa Junior, Federal University of Espírito Santo

    Master's student in Energy at the Federal University of Espírito Santo (2025- ). Holds a degree in Industrial Mathematics from the Federal University of Espírito Santo (2023). During his studies, he was a CNPq scholarship recipient for scientific initiation between 2020 and 2021, a UFES scholarship recipient for scientific initiation between 2021 and 2022, and a CNPq scholarship recipient for scientific initiation between 2022 and 2023. His research interests lie in the areas of Energy Efficiency, Artificial Intelligence, and Computational Mathematics.

  • Ana Paula Meneguelo, Federal University of Espírito Santo

    Graduated in Chemical Engineering from the Faculty of Chemical Engineering of Lorena (1998), an inland campus of the University of São Paulo. Master's degree in Chemical Engineering from the State University of Campinas in 2001 and doctorate in Chemical Engineering from the Federal University of Santa Catarina in 2007. Completed postdoctoral studies at the Federal University of Santa Catarina focusing on the development of intensified processes. Currently, she is an associate professor and teaches courses in the Petroleum Engineering program. Her research focuses on geological CO2 storage processes, inorganic fouling in porous media, and oil and natural gas processing. She is a professor in the Energy Graduate Program at the Federal University of Espírito Santo (UFES/ES) in the research area of ​​Oil, Gas and Renewable Energies. She has experience in the area of ​​modeling and simulation of intensified processes. She participates in the ANP's human resources training program - PRH53.1 - by supervising undergraduate research and final course projects, and is also a member of the program's management committee.

  • Daniel José Custódio Coura, Federal University of Espírito Santo

    Currently, he is an Adjunct Professor at the Federal University of Espírito Santo in the Department of Computer Science and Electronics (DCEL) at the North-Central Campus of Espírito Santo (CEUNES). Since 2011, he has taught undergraduate courses in Computer Engineering and Computer Science. He has been a collaborating member of the Postgraduate Program in Energy (PPGEN) since 2017. He participates in research in the areas of telecommunications and energy efficiency, mainly on the following topics: passive optical networks, optical access networks, and smart grids.

  • Wanderley Cardoso Celeste, Federal University of Espírito Santo

    Holds a PhD (2009), Master's degree (2005), and Bachelor's degree (2002) in Electrical Engineering from the Federal University of Espírito Santo (UFES). Since 2009, he has been a tenured professor in the Department of Computer Science and Electronics (DCE) at the North University Center of Espírito Santo (CEUNES/UFES). He teaches undergraduate courses in Computer Engineering (since 2009) and Computer Science (since 2015). He is a permanent member of the Postgraduate Program in Energy (PPGEN/CEUNES/UFES), where he teaches and supervises Master's (since 2011) and Doctoral (since 2024) students.

References

Ahammed, MT, Hasan, MM, Arefin, MS, Islam, MR, Rahman, MA, Hossain, E and Hasan, MT (2021) ‘Real-time non-intrusive electrical load classification over IoT using machine learning’. IEEE Access, v. 9, pp.115053–115067. https://doi.org/10.1109/ACCESS.2021.3104263

Awwad, E, Dorize, C, Guerrier, S and Renaudier, J (2020), ‘Detection-localization-identification of vibrations over long distance SSMF with coherent-OTDR'. Journal of Lightwave Technology, v. 38, n.12, pp.3089–3095.

Bucci, G, Ciancetta, F, Fiorucci, E, Mari, S and Fioravanti, A (2021), ‘Measurements for non-intrusive load monitoring through machine learning approaches’. Acta IMEKO, v.10, n.4, pp.90–96. https://doi.org/10.21014/acta_imeko.v10i4.1184

Cazzulani, G, Silva, A and Pennacchi, P (2021) ‘Optimization of continuous sensor placement for modal analysis: Application to an optical backscatter reflectometry strain sensor’. Mechanical Systems and Signal Processing, v.150, p.107242. https://doi.org/10.1016/j.ymssp.2020.107242

Empresa de Pesquisa Energética (EPE) (2024) ‘Balanço energético nacional 2024: Relatório síntese – ano base 2023’. EPE. https://www.epe.gov.br/pt/publicacoes-dados-abertos/publicacoes/balanco-energetico-nacional-ben

Ensslin, L, Ensslin, SR, Lacerda, RTO and Tasca, JE (2010) ‘ProKnow-C: Knowledge development process – constructivist’ [Unpublished Brazilian patent application]. Instituto Nacional da Propriedade Industrial.

Furse, CM, Kafal, M, Razzaghi, R and Shin, YJ (2020) 'Fault diagnosis for electrical systems and power networks: A review’. IEEE Sensors Journal, v. 21, n. 2, pp. 888–906. https://doi.org/10.1109/JSEN.2020.2987321

Ghosh, S and Chatterjee, D (2021) ‘Artificial bee colony optimization based non-intrusive appliances load monitoring technique in a smart home’. IEEE Transactions on Consumer Electronics, v. 67, n.1, pp.77–86. https://doi.org/10.1109/TCE.2021.3051164

Ghosh, S, Manna, D, Chatterjee, A and Chatterjee, D (2020) ‘Remote appliance load monitoring and identification in a modern residential system with smart meter data’. IEEE Sensors Journal, v. 21, n. 4, pp. 5082–5090. https://doi.org/10.1109/JSEN.2020.3035057

Hu, YC, Lin, YH and Lin, CH (2020) ‘Artificial intelligence, accelerated in parallel computing and applied to nonintrusive appliance load monitoring for residential demand-side management in a smart grid: A comparative study’. Applied Sciences, v. 10, n.22, p. 8114. https://doi.org/10.3390/app10228114

Li, TX, Zhang, FD, Lin, J, Bai, XY and Liu, HZ (2023a) ‘Fading noise suppression method of Φ-OTDR system based on GA-VMD algorithm’. IEEE Sensors Journal, v. 23, n.19, pp. 22608–22619. https://doi.org/10.1109/JSEN.2023.3306199

Li, X, Chen, J, Sun, L, Li, J and Zhao, X (2023b) ‘Research on sparse decomposition processing of ultrasonic signals of heat exchanger fouling’. IEEE Sensors Journal, v. 23, n.14, pp. 15795–15802. https://doi.org/10.1109/JSEN.2023.3279413

Ma, Y, Maqsood, A, Oslebo, D and Corzine, K (2021) ‘Wavelet transform data-driven machine learning-based real-time fault detection for naval DC pulsating loads’. IEEE Transactions on Transportation Electrification, v. 8, n.2, pp.1956–1965. https://doi.org/10.1109/TTE.2021.3130044

Ministério de Minas e Energia (MME) (2021) ‘Relatório Smart Grid: Grupo de Trabalho de Redes Elétricas Inteligentes’. Ministério de Minas e Energia. https://www.gov.br/mme/pt-br/assuntos/secretarias/secretaria-nacional-energia-eletrica/relatorio-smart-grid-1/documentos

Park, HP, Kwon, GY, Lee, CK and Chang, SJ (2024) ‘AI-enhanced time–frequency domain reflectometry for robust series arc fault detection in DC grids’. Measurement, v. 238, p. 115188. https://doi.org/10.1016/j.measurement.2024.115188

Peng, Z, Wen, H, Jian, J, Gribok, A, Wang, M, Huang, S and Chen, KP (2020a). ‘Identifications and classifications of human locomotion using Rayleigh-enhanced distributed fiber acoustic sensors with deep neurais networks’. Scientifc Reports, v.10, i n.1, p. 21014. https://doi.org/10.1038/s41598-020-77147-2

Peng, Z, Jian, J, Wen, H, Gribok, A, Wang, M, Liu, H, Huang, S, Mao, ZH and Chen, p (2020b) ‘Distributed fiber sensor and machine learning data analytics for pipeline protection against extrinsic intrusions and intrinsic corrosions’. Optics Express, v. 22, n. 16, p. 27277-27292. https://doi.org/10.1364/OE.397509

Rao, Y, Wang, Z, Wu, H, Ran, Z and Han, B (2021) ‘Recent advances in phase-sensitive optical time domain reflectometry (Φ-OTDR)’. Photonic Sensors, v. 11, pp. 1–30. https://doi.org/10.1007/s13320-021-0619-4

Rosa, C, Coimbra, M, Barbosa, P, Chantre, C and Rosental, R. (2022) ‘Microrredes: Benefícios e desafios para o setor elétrico brasileiro’. GESEL/UFRJ. https://www.gesel.ie.ufrj.br/app/webroot/files/publications/10_Rosa_2022_02_02.pdf

Tangudu, R. and Sahu, PK (2021) ‘Rayleigh Φ-OTDR based DIS system design using hybrid features and machine learning algorithms’. Optical Fiber Technology, v. 61, p. 102405. https://doi.org/10.1016/j.yofte.2020.102405

Yang, G, Luan, B, Sun, J, Niu, J, Lin, H. and Wang, L (2024) ‘Sparrow search mechanism-based effective feature mining algorithm for the broken wire signal detection of prestressed concrete cylinder pipe’. Mechanical Systems and Signal Processing, v. 212, p. 111270. https://doi.org/10.1016/j.ymssp.2024.111270

Yin, G, Zhu, Z, Liu, M, Wang, Y, Liu, K, Yu, K. and Zhu, T, (2023) ‘Optical frequency domain reflectometry based on multilayer perceptron’. Sensors, v. 23, n.6, p. 3165.

Zhao, L, Zhang, J, You, R. and Li, HN (2025) ‘Automatic detection of crack depth and width combining inverse finite-element and PSO-optimized SVR method with OFDR fiber-optic sensors’. Structural Health Monitoring, pp. 1–17. https://doi.org/10.1177/14759217251327728

Zhou, Z, Xiang, Y, Xu, H, Wang, Y, Shi, D and Wang, Z (2021) ‘Self-organizing probability neural network-based intelligent non-intrusive load monitoring with applications to low-cost residential measuring devices’. Transactions of the Institute of Measurement and Control, v. 43, n.3, pp. 635–645. https://doi.org/10.1177/0142331220950865

Downloads

Published

11/29/2025

Issue

Vol. 12 No. 3 (2025): 1 Encontro Interdisciplinar em Energia

Section

Eficiência Energética

License

Copyright (c) 2025 Latin American Journal of Energy Research

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

O autor, no ato da submissão do artigo, transfere o direito autoral ao periódico.

How to Cite

Load control in smart grids: a review of NILM-, machine learn-, and reflectometry-based approaches. (2025). Latin American Journal of Energy Research, 12(3), 145-153. https://doi.org/10.21712/lajer.2025.v12.n3.p145-153

Similar Articles

1-10 of 171

You may also start an advanced similarity search for this article.