Insights into Household Energy Consumption: Disaggregating Cooling and Heating Profiles using Principal Component Analysis

This paper develops a methodology based on Principal Component Analysis (PCA) to disaggregate distinct baseline electricity, heating and cooling components from the daily total electricity consumption data of 68 houses in Cyprus over the course of one year. The results show that the electricity data involves several principal components, with the two main ones accounting for 52.27% and 14.83% of the total variance, representing cooling and heating, respectively. The findings highlight the potential of using PCA for effective energy disaggregation, which could be extended to various building types and communities. By analyzing energy consumption patterns, targeted energy-saving and improved energy efficiency measures can be identified. Future research will compare PCA results with physics-driven building models, explore alternative disaggregation methods, and apply the methodology to broader datasets.