Privacy-Aware Edge Intelligence in Smart Meters for Personal Energy Management
Keywords:
Edge intelligence; Smart meters; NILM; Federated learning; Load forecasting; Privacy; HEMS.Abstract
Smart meters are becoming increasingly capable, transforming from passive meters into local decision nodes that can include demand forecasting, appliance-level inference, privacy-preserving learning, and demand-response support. This survey presents edge-intelligent smart meters for personal energy management, covering on-device inference, non-intrusive load monitoring (NILM), federated learning, privacy, local control, and meter–gateway–cloud coordination. The review is oriented toward meter-side deployment, and methods are evaluated based not only on prediction accuracy but also on memory footprint, inference latency, communication overhead, explainability, cybersecurity, adaptation, and user trust. The synthesis suggests that a layered architecture will be easiest to deploy in the near term, with trusted sensing and lightweight inference at the meter, heavier learning and user-friendly control at the gateway, and privacy-preserving aggregation and benchmarking in the cloud. Key open problems are continuous personalization under embedded constraints, secure federated NILM, and realistic meter-class benchmarking.
References
[1] Y. Wang, Q. Chen, T. Hong, and C. Kang, "Review of Smart Meter Data Analytics: Applications, Methodologies, and Challenges," IEEE Transactions on Smart Grid, vol. 10, no. 3, pp. 3125-3148, May 2019, doi: 10.1109/TSG.2018.2818167.
[2] B. Zhou, W. Li, K. W. Chan, Y. Cao, Y. Kuang, X. Liu, and X. Wang, "Smart Home Energy Management Systems: Concept, Configurations, and Scheduling Strategies," Renewable and Sustainable Energy Reviews, vol. 61, pp. 30-40, Aug. 2016, doi: 10.1016/j.rser.2016.03.047.
[3] W. Shi, J. Cao, Q. Zhang, Y. Li, and L. Xu, "Edge Computing: Vision and Challenges," IEEE Internet of Things Journal, vol. 3, no. 5, pp. 637-646, Oct. 2016, doi: 10.1109/JIOT.2016.2579198.
[4] H. B. Gooi, J. Zheng, S. Chen, B. Lu, and T. Zhang, "Edge Intelligence for Smart Grid: A Survey on Concepts, Architectures and Applications," CSEE Journal of Power and Energy Systems, 2022.
[5] Q. T. Minh, N. Nguyen, T. H. Nguyen, and E. N. Huh, "Edge Computing for Smart Grid: A Comprehensive Survey," Energies, vol. 15, no. 17, 6140, 2022.
[6] A. N. Akpolat, E. Dursun, and S. Kuzlu, "Edge Intelligence in Smart Grids: A Review of Architectures, Applications, and Challenges," Journal of Sensor and Actuator Networks, vol. 11, no. 3, 47, 2022.
[7] M. Rafiq, H. Zhang, H. Li, and M. K. Ochani, "A Comprehensive Review of Non-Intrusive Load Monitoring: Methods, Datasets, and Challenges," Energy and Buildings, vol. 305, 113890, 2024.
[8] M. Rafiq, G. Hafeez, I. Khan, F. A. Khan, and A. Shafiq, "Data Augmentation for Non-Intrusive Load Monitoring," IEEE Transactions on Smart Grid, vol. 12, no. 6, pp. 5142-5154, Nov. 2021.
[9] A. Manca, G. Graditi, M. G. Ippolito, and E. R. Sanseverino, "Non-Intrusive Load Monitoring at Low Sampling Rate: A Review," Computer Applications in Engineering Education, 2022.
[10] D. B. Avancini, J. J. P. C. Rodrigues, S. G. B. Martins, R. A. L. Rabêlo, J. Al-Muhtadi, and P. Solic, "Energy Meters Evolution in Smart Grids: A Review," Journal of Cleaner Production, vol. 217, pp. 702-715, Apr. 2019, doi: 10.1016/j.jclepro.2019.01.229.
[11] Z. Ghaffar, M. K. Hanif, and S. H. Ahmed, "Non-Intrusive Load Monitoring Using Spectral Clustering and Smart Meter Data," Sensors, vol. 22, no. 11, 4036, 2022.
[12] J. Yang, Y. Li, and H. Zhang, "Non-Intrusive Electric Vehicle Charging Detection Using Smart Meter Measurements," IEEE Transactions on Consumer Electronics, 2024.
[13] L. Nardello, M. Rossi, and D. Brunelli, "A Low-Cost Non-Intrusive Load Monitoring System for Smart Meters," in Proc. IEEE PES Innovative Smart Grid Technologies Europe, Torino, Italy, 2017.
[14] M. N. Fekri, K. Grolinger, and S. Mir, "Distributed Load Forecasting Using Smart Meter Data: Federated Learning with Recurrent Neural Networks," International Journal of Electrical Power & Energy Systems, vol. 137, 107669, May 2022, doi: 10.1016/j.ijepes.2021.107669.
[15] M. N. Fekri, K. Grolinger, and S. Mir, "An Online Adaptive Recurrent Neural Network for Load Forecasting of Individual Smart Meters," International Journal of Electrical Power & Energy Systems, vol. 152, 109285, Nov. 2023.
[16] Z. Cui, R. Ke, Z. Pu, and Y. Wang, "Personalized Federated Learning for Smart Meter Data-Based Load Forecasting," CSEE Journal of Power and Energy Systems, 2022.
[17] Y. Wang, N. Zhang, Q. Chen, D. S. Kirschen, P. Li, and Q. Xia, "Data-Driven Probabilistic Net Load Forecasting With High Penetration of Behind-the-Meter PV," IEEE Transactions on Power Systems, vol. 33, no. 3, pp. 3255-3264, May 2018, doi: 10.1109/TPWRS.2017.2762599.
[18] H. Qu, K. Li, and T. Zhang, "Heterogeneous Residential Load Forecasting Based on Clustering and Deep Learning," Big Data Mining and Analytics, vol. 5, no. 2, pp. 135-146, 2022.
[19] A. Taïk and S. Cherkaoui, "Electrical Load Forecasting Using Edge Computing and Federated Learning," in Proc. IEEE International Conference on Communications (ICC), Dublin, Ireland, 2020, pp. 1-6, doi: 10.1109/ICC40277.2020.9148937.
[20] N. Hudson, J. S. Liu, and A. R. Hota, "Federated Learning for Privacy-Preserving Short-Term Residential Load Forecasting," in Proc. International Conference on Computer Communications and Networks (ICCCN), Athens, Greece, 2021, pp. 1-9.
[21] Y. Su, T. T. Kim, and H. V. Poor, "Privacy-Preserving Federated Learning for Residential Short-Term Load Forecasting," IEEE Transactions on Industrial Informatics, vol. 18, no. 11, pp. 7629-7639, Nov. 2022.
[22] X. Wang, Y. Wang, and D. Shi, "A Privacy-Preserving Distributed Learning Scheme for Smart Meter Data Analytics," IEEE Transactions on Smart Grid, 2021.
[23] M. Husnoo, A. Anwar, Z. Tari, and A. Mahmood, "A Secure Federated Learning Framework for Smart Grid Load Forecasting," IEEE Transactions on Smart Grid, 2023.
[24] M. Raza, N. Javaid, A. Gumaei, and M. Al-Rakhami, "Business Intelligence for Smart Energy Management: A Review," IEEE Access, vol. 11, pp. 119316-119338, 2023.
[25] Z. Chen, A. M. Amani, X. Yu, and M. Jalili, "Control and Optimisation of Power Grids Using Smart Meter Data: A Review," Sensors, vol. 23, no. 4, 2118, 2023, doi: 10.3390/s23042118.
[26] M. U. Hassan, M. H. Rehmani, and J. Chen, "Privacy Preservation in Smart Grid: A Survey," Computer Science Review, vol. 43, 100424, Feb. 2022.
[27] S. M. Abu Adnan Abir, A. Anwar, J. Choi, and A. S. M. Kayes, "IoT-Enabled Smart Energy Grid: Applications and Challenges," IEEE Access, vol. 9, pp. 50961-50981, 2021, doi: 10.1109/ACCESS.2021.3067331.
[28] S. Kirmani, M. Jamil, I. Akhtar, and M. Rizwan, "IoT Applications in Smart Grid: A Survey," Sustainability, vol. 15, no. 1, 717, 2023.
[29] Y. Mehmood, N. Ahmad, and A. Alrajeh, "Edge Computing for Internet of Things Based Smart Grid: A Comprehensive Survey," Wireless Communications and Mobile Computing, vol. 2021, 5524025, 2021.
[30] M. Kolosov, P. Zancanaro, and T. Ahmed, "High-Frequency Smart Meter Data for Edge-Aware Energy Analytics," Sensors, vol. 25, no. 17, 5280, 2025.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Journal of Intelligent Engineering and Informatics
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
