Clustering and prediction of space cooling and heating energy consumption in high-rise residential buildings with the influence of occupant behaviour: Evidence from a survey in Changsha, China

Abstract

Residential building space cooling and heating energy consumption account for approximately 15% of the total social energy consumption. Occupant behaviour is the primary factor influencing energy consumption for cooling and heating in residential buildings. This study used extensive face-to-face questionnaire surveys and actual measurements for typical households to study the cooling and heating energy consumption of high-rise residential buildings in Changsha. Statistical analysis was conducted on the influencing factors of participant information, architecture, occupant behaviour, and energy conservation awareness in the questionnaire survey. The household energy bills for cooling and heating were clustered, and PCA models were proposed between the influencing factors and the energy consumption, and were verified by measured data of typical households. The results demonstrated that the household energy bills could be divided into five categories. The PCA models show the mode of ventilation during the cooling period and the mode of air conditioner (AC) turning on/off during the heating period are the most important component, accounting for 46.7% and 35.9%, respectively. The statistical parameters provided a reference for the energy consumption simulation software, and the PCA models achieved energy consumption prediction through data of principal components, which are significant for building energy efficiency and carbon reduction.