Design of a Low-Cost Embedded Measurement System for Power Quality Event Detection and Classification

Abstract

Power quality (PQ) monitoring plays a crucial role in the operating conditions of electrical distribution networks and ensuring compliance with power quality standards. The increasing need for pervasive and distributed monitoring motivates the development of low-cost measurement instrumentation capable of operating directly at the network edge. With these aims, this paper proposes the design of a compact and distributed instrumentation device suitable for deployment in low-voltage networks and resource-constrained measurement scenarios implemented on an ESP32 microcontroller platform. The power signal is acquired through a cost-effective sensing front-end and processed using a multisinusoidal decomposition technique, which provides the feature extraction for the detection and classification of PQ events such as harmonics, voltage sags and swells, and transients. For the classification, the extracted features are used as inputs to a machine learning algorithm. In order to select the most suitable one, a further contribution of this paper is to test several supervised machine learning algorithms, which are systematically compared in terms of classification accuracy, robustness to measurement noise, and computational complexity. Particular emphasis is placed on algorithm suitability for real-time execution on embedded measurement hardware with limited memory and processing resources, such as the ESP32. Experimental results are obtained using emulated PQ signals. The results confirm that the integration of multisinusoidal signal analysis with lightweight machine learning techniques represents an effective solution for cost-effective and scalable PQ instrumentation.