Real-Time Power Quality Classification Using a Raspberry Pi 3B+

Power quality monitoring is essential for maintaining the stability and efficiency of modern electrical systems worldwide. Traditional methods of monitoring power quality often require complex and expensive equipment, which is not always accessible or feasible in resource-limited areas. Although the development of efficient machine learning models is crucial, their true value lies in demonstrating their practical implementation on devices with limited resources. Building upon our previous work, this paper presents a novel approach for real-time power quality classification using the Large-EPQC model, deployed on a Raspberry Pi 3B+ edge device. By optimizing computational performance, the model accurately classifies power disturbances, offering a scalable and cost-efficient solution for real-world applications.