A novel feature extraction and classification algorithm based on power components using single-point monitoring for NILM

This paper presents a classification approach based on the power components and applied to the Non-Intrusive Load Monitoring (NILM). The active, reactive and apparent power levels are recorded and are fed to a Decision Tree (DT) classifier to develop the appropriate classification model. The results have shown that using the change in the power components level instead of using the actual power components recorded can result in significant improvement in the classification accuracy.