Explicit data-driven prediction model of annual energy consumed by elevators in residential buildings

• Published in: Journal of Building Engineering Vol. 31; p. 101278
• Main Authors: Zubair, Muhammad Umer, Zhang, Xueqing
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.09.2020
• Subjects: Elevator; Energy efficiency; Forecast; Motor drive; Multiple linear regression; Simulation; Motor drive; Energy efficiency; Multiple linear regression; Simulation; Elevator; Forecast
• ISSN: 2352-7102; 2352-7102
• DOI: 10.1016/j.jobe.2020.101278

This research has proposed an explicit data-driven multiple linear regression model for predicting the annual energy consumption of elevators installed in residential buildings. This model consists of elevator and building parameters of average rated capacity, motor rating, number of elevators, number of domestic units in the building, and type of motor drive. The model was formulated after analyzing the historical elevator energy consumption data of 196 residential buildings in Hong Kong and validated using statistical measures and through its application to 25 additional residential buildings. The model enables the comparison of the energy efficiency of elevators using ACVVVF (AC motor with variable voltage variable frequency) drive and those using non-ACVVVF drive such as AC 2 speed motor drive, DC motor drive with solid-state controller, and AC motor drive with variable speed controller. Compared to previous models, this model has a big advantage, that is, it does not require traffic data as an input, which is rarely available in practice. It is concluded that saving of up to 50% of annual energy consumption could be achieved if non-ACVVVF drives are replaced with ACVVVF drives. Furthermore, the sensitivity analysis of the regression model through Monte Carlo Simulation reveals that considerable reduction of annual energy consumption can be achieved by optimizing the average rated capacity of elevators. •Developed an explicit data-driven model for predicting the energy consumption of elevators.•Prediction model not require rigorous operational and traffic data.•Compared the energy efficiency of elevators using different types of motor drives.•Significant energy saving by optimizing the average rated capacity of elevators.