Experimental Study on Impact of Appliance ID-Based Normalization on SimDataset for Anomalous Power Consumption Classification

Abstract

In terms of annual worldwide energy consumption, buildings use more energy than any other sector. Enhancing buildings' energy efficiency and ensuring security of the appliances requires iden-tifying abnormal power usage. Identifying anomalous power usage is essential for energy conservation. This study suggests an experimental analysis of SimDataset used for detecting micro-moment-based abnormal power usage. Five machine learning-based classifiers-Random Forest (RF), Support Vector Ma-chine (SVM), K Nearest Neighbors (KNN), Naive Bayes (NB), and Decision Tree (DT)-are used to detect unusual consumption of electricity. The Sim-Dataset has undergone binary and multi-class classi-fication. Effect on the performance of the classifiers after the inclusion of new features is examined. Computational complexity of the classifiers is also analyzed. Experimental results showed, the binary and multi-class classification using the RF model with the original dataset, with Min-Max Normalized Power feature and Appliance Id-based Normalized Power feature, produced identical and maximum accuracy, precision, recall, and F1-Score. © 2024 IEEE.