Application of a smart electricity meter to improve electricity consumption analysis

Resumen

This research presents the development and evaluation of a smart electrical meter designed to measure, analyze, and remotely monitor key power-quality parameters using low-cost sensors and an ESP32 microcontroller. The system captures voltage and current through SCT-013-100 and ZMPT101B sensors, processes the data locally, and transmits it via Wi-Fi to a cloud platform, where users can visualize measurements in real time through a mobile application. Machine-learning techniques, including Empirical Mode Decomposition (EMD), Kernel PCA, and Support Vector Machines (SVM), were implemented to extract features and classify electrical consumption patterns. Experimental validation showed high accuracy in voltage readings, with errors near ±1.10% for low loads and around 0.5% compared to a professional CW500 meter. Current measurements remained acceptable, despite occasional deviations linked to synchronization differences. The system also accurately registered frequency stability at 60 Hz and enabled harmonic-distortion and active-power analysis. Overall, the smart meter demonstrated reliable performance for real-time monitoring and represents a scalable, low-cost solution for energy-quality assessment