A Quantum Machine Learning Methodology for Precise Appliance Identification in Smart Grids

Classification of power consumption data to a set of electric appliances is of paramount importance for tasks pertaining to the efficient and stable operation of smart grids given that it is strongly related to energy management, demand response, load monitoring and electricity theft. In recent years, the field of quantum machine learning has emerged as a promising field with the potential to revolutionize various aspects of data analysis and classification. By utilizing quantum computing concepts like superposition, entanglement, and quantum interference to process and analyze data in a fundamentally different way from conventional techniques and standard machine learning algorithms, quantum classifiers offer a novel solution to classification problems. This research investigates the influence of a robust Convolutional Neural Network (CNN) and a cutting-edge Variational Quantum Classifier (VQC) on the classification accuracy of consumption patterns to seven domestic electrical appliances obtained from 65 different locations in Pittsburgh, Pennsylvania. The findings of this study indicate that the proposed VQC is more effective and precise in handling challenging classification tasks, as it outperforms the simple CNN and provides higher classification accuracy.