Volume 15 , Issue 2 , PP: 91-103, 2025 | Cite this article as | XML | Html | PDF | Full Length Article
Huda W. Ahmed 1 * , Asma Khazaal Abdulsahib 2 , Massila Kamalrudin 3 , Mustafa Musa 4
Doi: https://doi.org/10.54216/JISIoT.150207
Accurate energy metering is essential for reliable power system operation, fair billing, and effective monitoring of electricity consumption. However, detecting faults in electric energy meters remains challenging because conventional inspection practices, including manual testing, operational sampling, and user-reported verification, are time-consuming, labor-intensive, and often limited in dynamic field conditions. This study proposes a deep learning-assisted prediction model (DLPM) for identifying abnormal metering behavior and improving the assessment of energy meter faults in electric power systems. The proposed model learns the relationship between expected and observed meter trajectories, enabling it to detect significant deviations that may indicate measurement errors or operational faults. By automating the analysis of metering discrepancies, the DLPM provides a more consistent and data-driven alternative to traditional fault diagnosis methods. The model supports accurate deviation estimation, improves abnormality recognition, and assists in identifying potential causes of smart meter malfunction. Simulation results demonstrate that the proposed DLPM achieves strong predictive performance, with 99.2% accuracy, 97.8% overall performance, and 98.9% efficiency. In addition, the model records an average consumption deviation of 10.3% and a root mean square error of 11.2%, indicating its effectiveness in supporting intelligent meter fault assessment. These findings suggest that deep learning can enhance the reliability, automation, and diagnostic capability of smart metering systems in modern electric power networks.
Artificial intelligence , Electric energy metering device error , Deep learning methods
[1] M. K. Hasan, M. M. Ahmed, A. H. A. Hashim, A. Razzaque, S. Islam, and B. Pandey, “A novel artificial intelligence-based timing synchronization scheme for smart grid applications,” Wireless Pers. Commun., vol. 114, no. 2, pp. 1067–1084, 2020.
[2] S. Al-Azzawi and A. M. Hasan, “A New 4D Hidden Hyperchaotic System with Higher Largest Lyapunov Exponent and Its Synchronization,” Int. J. Math. Stat. Comput. Sci., vol. 2, pp. 63–74, 2023, doi: 10.59543/ijmscs.v2i.8469.
[3] H. R. Rocha, I. H. Honorato, R. Fiorotti, W. C. Celeste, L. J. Silvestre, and J. A. Silva, “An Artificial Intelligence based scheduling algorithm for demand-side energy management in Smart Homes,” Appl. Energy, vol. 282, p. 116145, 2021.
[4] G. Amudha, “Dilated Transaction Access and Retrieval: Improving the Information Retrieval of Blockchain-Assimilated Internet of Things Transactions,” Wireless Pers. Commun., pp. 1–21, 2021.
[5] S. Baskar, S. Periyanayagi, P. M. Shakeel, and V. S. Dhulipala, “An energy persistent range-dependent regulated transmission communication model for vehicular network applications,” Comput. Netw., vol. 152, pp. 144–153, 2019.
[6] P. Stefanidou-Voziki, N. Sapountzoglou, B. Raison, and J. L. Dominguez-Garcia, “A review of fault location and classification methods in distribution grids,” Electr. Power Syst. Res., vol. 209, p. 108031, 2022.
[7] N. T. Nguyen, B. H. Liu, V. T. Pham, and Y. S. Luo, “On maximizing the lifetime for data aggregation in wireless sensor networks using virtual data aggregation trees,” Comput. Netw., vol. 105, pp. 99–110, 2016.
[8] Y. Yao, X. Li, Y. Cui, J. Wang, and C. Wang, “Energy-Efficient Routing Protocol Based on Multi-Threshold Segmentation in Wireless Sensor Networks for Precision Agriculture,” arXiv preprint arXiv: 2307.00697, 2023.
[9] J. Gao, H. Wang, and H. Shen, “Task failure prediction in cloud data centers using deep learning,” IEEE Trans. Serv. Comput., 2020.
[10] T. Sirojan, “Artificial Intelligence based Sensor Data Analytics Framework for Remote Electricity Network Condition Monitoring,” arXiv preprint arXiv: 2102.03356, 2021.
[11] J. Gao, H. Wang, and H. Shen, “Smartly handling renewable energy instability in supporting a cloud datacenter,” in Proc. IEEE Int. Parallel Distrib. Process. Symp. (IPDPS), 2020, pp. 769–778.
[12] B. C. Erdener, C. Feng, K. Doubleday, A. Florita, and B. M. Hodge, “A review of behind-the-meter solar forecasting,” Renew. Sustain. Energy Rev., vol. 160, p. 112224, 2022.
[13] N. de Marcellis-Warin, F. Marty, E. Thelisson, and T. Warin, “Artificial intelligence and consumer manipulations: from consumer's counter algorithms to firm's self-regulation tools,” AI Ethics, vol. 2, no. 2, pp. 259–268, 2022.
[14] I. Diahovchenko et al., “Effect of harmonic distortion on electric energy meters of different metrological principles,” Front. Energy, vol. 13, no. 2, pp. 377–385, 2019.
[15] M. Kaur, D. Singh, V. Kumar, B. B. Gupta, and A. A. Abd El-Latif, “Secure and energy-efficient based E-health care framework for green Internet of Things,” IEEE Trans. Green Commun. Netw., 2021.
[16] R. Saha et al., “The Blockchain solution for the security of Internet of Energy and Electric Vehicle Interface,” IEEE Trans. Veh. Technol., 2021.
[17] R. Zhang and R. D. Jackson Samuel, “Fuzzy efficient energy smart home management system for renewable energy resources,” Sustainability, vol. 12, no. 8, p. 3115, 2020.
[18] C. Chen, Y. Hu, K. Marimuthu, and P. M. Kumar, “Artificial intelligence on economic evaluation of energy efficiency and renewable energy technologies,” Sustain. Energy Technol. Assess., vol. 47, p. 101358, 2021.
[19] R. Sundarasekar et al., “Adaptive energy-aware quality of service for reliable data transfer in underwater acoustic sensor networks,” IEEE Access, vol. 7, pp. 80093–80103, 2019.
[20] S. R. Das et al., “Artificial intelligence-based grid connected inverters for power quality improvement in smart grid applications,” Comput. Electr. Eng., vol. 93, p. 107208, 2021.
[21] A. J. Balaji, D. S. H. Ram, and B. B. Nair, “A deep learning approach to electric energy consumption modeling,” J. Intell. Fuzzy Syst., vol. 36, no. 5SI, pp. 4049–4055, 2019.
[22] Ž. Nakutis, S. Rinaldi, P. Kuzas, and R. Lukočius, “A method for non-invasive remote monitoring of energy meter error using power consumption profile,” IEEE Trans. Instrum. Meas., vol. 69, no. 9, pp. 6677–6685, 2020.
[23] S. Wang, H. Chen, L. Wu, and J. Wang, “A novel smart meter data compression method via stacked convolutional sparse auto-encoder,” Int. J. Electr. Power Energy Syst., vol. 118, p. 105761, 2020.
[24] S. Muralidhara, N. Hegde, and P. M. Rekha, “An Internet of Things-based smart energy meter for monitoring device-level consumption of energy,” Comput. Electr. Eng., vol. 87, p. 106772, 2020.
[25] X. Kong, Y. Ma, X. Zhao, Y. Li, and Y. Teng, “A recursive least squares method with double-parameter for online estimation of electric meter errors,” Energies, vol. 12, no. 5, p. 805, 2019.
[26] T. Čegovnik, A. Dobrovoljc, J. Povh, M. Rogar, and P. Tomšič, “Electricity consumption prediction using artificial intelligence,” Cent. Eur. J. Oper. Res., pp. 1–19, 2023.
[27] H. A. Sayed, A. William, and A. M. Said, “Smart electricity meter load prediction in Dubai using MLR, ANN, RF, and ARIMA,” Electronics, vol. 12, no. 2, p. 389, 2023.
[28] M. Nutakki and S. Mandava, “Review on optimization techniques and role of artificial intelligence in home energy management systems,” Eng. Appl. Artif. Intell, vol. 119, p. 105721, 2023.
[29] L. Richter et al., “Artificial intelligence for electricity supply chain automation,” Renew. Sustain. Energy Rev., vol. 163, p. 112459, 2022.
[30] S. Zhang, N. Qu, T. Zheng, and C. Hu, “Series arc fault detection based on wavelet compression reconstruction data enhancement and deep residual network,” IEEE Trans. Instrum. Meas., vol. 71, pp. 1–9, 2022.
