<![CDATA[Low-cost voltage and current sensors such as the ZMPT101B and ACS712 are widely used in IoT-based energy monitoring due to their affordability and ease of integration. However, their outputs suffer from drift caused by thermal variation, material degradation, and electromagnetic interference, leading to cumulative errors that compromise load monitoring, forecasting, and anomaly detection. This work presents a drift-resilient framework that integrates lightweight filtering and regression-based calibration into a unified pipeline deployable on ESP32-class devices. Moving average and adaptive Kalman filters suppress noise and track drift trends, regression models align sensor outputs with reference standards, and spectrogram-based analysis detects transient drift events for adaptive correction. Experiments under realistic conditions show substantial improvements: voltage RMSE decreased by over 90% (3.45V to 0.30V), current RMSE by 92% (0.065A to 0.005A), and MAPE to below 0.5%. Signal-to-noise ratio improved by approximately 21dB, confirming significant restoration of measurement fidelity. Compared with data-intensive deep learning or AutoML frameworks, the proposed method offers a scalable, interpretable, and resource-efficient solution for long-term IoT energy monitoring. By bridging drift mitigation strategies with the practical constraints of low-cost sensors, this framework enhances the reliability of smart grid and IoT-based infrastructures.]]>
Copyrights © 2026
