Low-cost IoT-based smart meter for real-time power quality monitoring and disturbance detection using embedded 1D CNN

Year 2025, Volume: 9 Issue: 4, 365 - 379, 30.12.2025

Bouchra Feriel Khaldi , Fatma Zohra Dekhandji , Abdelmadjid Recioui

https://doi.org/10.30521/jes.1718242

Abstract

Power quality disturbances (PQDs) such as voltage sags, swells, interruptions, and harmonics significantly impact the performance and stability of electrical distribution networks. With the growing demand for intelligent, embedded monitoring systems in smart grids, edge computing offers a practical approach to real-time disturbance detection. This paper presents a compact and efficient PQD classification system based on a quantized 1D Convolutional Neural Network (CNN), deployed on an ESP32 microcontroller. The model, developed using Edge Impulse, was compressed to approximately 2 KB, allowing deployment on low-power hardware. Key signal features such as root mean square voltage (VRMS) and total harmonic distortion (THD) were extracted to aid in classification. Real-time validation was performed using both live signals and real-world data obtained from the National Company for Electricity and Gas distribution areas, covering various single and combined PQD events. The ESP32 was connected to the Blynk IoT platform for live monitoring, where detected disturbances triggered mobile alerts, virtual LED indicators, and sound notifications. Results confirm the system’s high classification accuracy and responsiveness, demonstrating the potential of lightweight neural models for edge-based PQ monitoring.

Keywords

1D CNN , ESP32 , IoT monitoring , Power quality , Smart Grid , Smart meter

Supporting Institution

Algerian National Company for Electricity and Gas

Thanks

The authors would like to express their sincere gratitude to the Algerian National Company for Electricity and Gas for providing the necessary power quality disturbance measurements from distribution areas, which were essential for this work. Their support was instrumental in validating the proposed system and demonstrating its effectiveness in real-world conditions.

References

• [1] Zhan H, Strawderman AD, Hovakimyan CE. Autonomous wildland fire monitoring via integrated path planning and sensor fusion. IEEE Trans Autom Sci Eng. 2024; early access. doi:10.1109/TASE.2024.3456789.
• [2] Bar-Shalom Y, Tse E, Weiss A. A localization upper bound with uncertain transmitter positions. IEEE Trans Signal Process. 2023;71:234–247. doi:10.1109/TSP.2023.3321458.
• [3] Rezaei M, Weiss A, Wang L. Robust position estimation under transmitter location uncertainty using sensitivity maps. IEEE Trans Veh Technol. 2024 May;73(5):6154–6167. doi:10.1109/TVT.2024.3367890.
• [4] Rahmani R, Abbas N, Ahmad M. Performance comparison of H∞ control and feedback linearization on a rotary inverted pendulum system. IEEE Access. 2024;12:87156–87168. doi:10.1109/ACCESS.2024.3459087.
• [5] Khaldi BF, Dekhandji FZ, Recioui A. Power quality disturbances: A review of detection, classification, optimization, and mitigation techniques. Alger J Signal Syst. 2024;9:261–275.
• [6] Ravi T, Kumar KS, Kumar KS. Analysis, monitoring, and mitigation of power quality disturbances in a distributed generation system. Front Energy Res. 2022;10:989474.
• [7] Channa IA, Li D, Dahri FH, Abro GEM, Zahid F. A novel deep learning model for classifying power quality problems in PV-integrated microgrids using CNN-LSTM. In: Proc. 1st Int Conf Innovative Engineering Sciences and Technological Research (ICIESTR); 2024; Muscat, Oman. p. 1–5. doi:10.1109/ICIESTR60916.2024.10798309.
• [8] Cen S, Kim DO, Lim CG. A fused CNN-LSTM model using FFT with application to real-time power quality disturbances recognition. Energy Sci Eng. 2023;11:2267–2280.
• [9] Dekhandji FZ, Recioui A, Ladada A, Moulay Brahim TS. Detection and classification of power quality disturbances using LSTM. In: Proc. 2nd Int Conf Computer Engineering and Information Systems (ICCEIS); 2022. p. 1–6.
• [10] Hassan KA, Agboola MK, Oladiran TA, Olorunmaye II. Microcontroller based smart energy meter with data logger system. J Adv Ind Technol Appl. 2023;4:94–103.
• [11] Gowda VHR, NBV, Sathish K, Gowda CKP, Sulthana S. Smart electricity meter monitoring and prediction using I-socket. Int J Adv Res Sci Commun Technol. 2024;4:160.
• [12] Maheshkumar KS, Jagadeesan PR. IoT-integrated smart energy meter for industrial energy monitoring. Int J Sci Res Eng Manag. 2025;9:1.
• [13] Khan A, Sohail A, Zahoora U, Qureshi AS. A survey of the recent architectures of deep convolutional neural networks. Artif Intell Rev. 2020;53:1–18.
• [14] Purwono P, Ma’arif A, Rahmaniar W, Fathurrahman HIK, Kusuma Frisky AZ, Haq QM. Understanding of convolutional neural network (CNN): A review. Int J Robot Control Syst. 2022;2:739–748.
• [15] Patil P, Muley K, Agrawal R. Identification of power quality disturbance using neural network. In: Proc. 3rd Int Conf Electronics, Communication and Aerospace Technology (ICECA); 2019; Coimbatore, India. p. 990–996. doi:10.1109/ICECA.2019.8822214.
• [16] Liu J, Wang T, Skidmore A, Sun Y, Jia P, Zhang K. Integrated 1D, 2D, and 3D CNNs enable robust and efficient land cover classification from hyperspectral imagery. Remote Sens. 2020;12:3643.
• [17] LeCun Y, Bottou L, Bengio Y, Haffner P. Gradient-based learning applied to document recognition. Proc IEEE. 1998 Nov;86(11):2278–2324. doi:10.1109/5.726791.
• [18] Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, et al. Going deeper with convolutions. arXiv preprint. 2014; arXiv:1409.4842. doi:10.48550/arXiv.1409.4842.
• [19] Pavlitskaya S, Oswald J, Zöllner JM. Measuring overfitting in convolutional neural networks using adversarial perturbations and label noise. In: Proc. IEEE Symp Series Computational Intelligence (SSCI); 2022. p. 1551–1559.
• [20] Al-Hyari AY, Abu-Faraj M. Hyperparameters optimization of convolutional neural networks using evolutionary algorithms. In: Proc. Int Conf Emerging Trends in Computing and Engineering Applications (ETCEA); 2022. p. 1–6.
• [21] Uribe-Pérez N, Hernández L, de la Vega D, Angulo I. State of the art and trends review of smart metering in electricity grids. Appl Sci. 2023;13:4680.
• [22] Ezhilarasi P, Ramesh L, Sanjeevikumar P, Khan B. A cost-effective smart metering approach towards affordable deployment strategy. Sci Rep. 2023;13:10832.
• [23] Shi W, Cao J, Zhang Q, Li Y, Xu L. Edge computing: Vision and challenges. IEEE Internet Things J. 2016;3(5):637–646.
• [24] Zhao K, Ge L, Qiu J. Cybersecurity and privacy-preserving in smart grids. IEEE Wirel Commun. 2020;27(2):122–129.
• [25] Patil SR, Patil PM. Power quality monitoring in smart grid using advanced sensing technologies: A review. J Electr Syst Inf Technol. 2018;5(3):456–467.
• [26] Tabassum S, Vijay Babu AR, Kumar Dheer D. Real-time power quality enhancement in smart grids through IoT and adaptive neuro-fuzzy systems. Sci Technol Energy Transition. 2024;79:89.
• [27] Chen Z, Amani AM, Yu X, Jalili M. Control and optimisation of power grids using smart meter data: A review. Sensors. 2023;23(4):2118. doi:10.3390/s23042118.