Volume 11: Sustainable Energy Solutions for Changing the World: Part III

Investigation of the Impact of Illumination on Deep Learning-based Equipment Load Detection for Energy Demand Estimation Shuangyu Wei, Paige Tien, Yupeng Wu, John Calautit



The main aim of this paper is to investigate the impact of lighting conditions on the detection accuracy of the vision-based equipment load detection approach. The work will be using artificial intelligence cameras to detect equipment information in different lighting levels, employing deep learning method to analyze and generate real-time equipment usage profiles for offices which can be inputted to the demand-based building controls to increase the efficiency of heating, ventilation, and air-conditioning systems. The performance of the developed approach in various illumination conditions was compared by using a building energy simulation tool. The results showed that as compared with the conventionally-scheduled heating, ventilation, and air-conditioning systems, the system with the use of equipment usage profiles conducted by the proposed approach can achieve up to 15% reduction in energy consumption depending on the setup of the camera in terms of indoor lighting levels. The finding indicates that adequate illumination level contributes to the decrease of building energy demand by achieving an effective deep learning approach.

Keywords Artificial Intelligence; Deep Learning; Equipment Detection; Building Energy; Built Environment

Copyright ©
Energy Proceedings