Joosang Lee’s research while affiliated with Yonsei University and other places

There is growing concern that airtight and well-insulated buildings designed to limit heat loss in temperate and cold climates could unintentionally elevate the risk of overheating in summers. Existing literature primarily uses dynamic simulation to investigate this problem due to the difficulty of obtaining large-scale in-performance data. To address this gap, we undertake a meta-analysis of large-scale indoor air temperature data for 195 UK dwellings, as a study of performance in a temperate climate. Of these, 113 are baseline (i.e., typical existing dwellings) and the rest designed to the high-performance Passivhaus standard. Using both Passivhaus and the well-known CIBSE TM59 overheating standards, this study found that there were few overheated cases for any building type. However, the average summer nighttime temperature of Passivhaus bedrooms was 1.6 °C higher than baseline, with 20 out of 31 measured bedrooms exceeding the overheating criterion, and the average overheating hours constituting approximately 19% of the total summertime observation period. These findings suggest that bedrooms in highly insulated dwellings may pose an overheating risk although whole-dwelling overheating risk is low.

Incorporating Internet of Things (IoT) technology into the operation of buildings is expected to generate immense synergy, thereby saving energy and improving occupant comfort by overcoming the limitations of the existing system. Preventing operations in the absence of occupants can save energy, and the occupants’ preferred operating temperature should be used as the control set-point rather than the nominal temperature. In this study, IoT technology and image sensors are used to rapidly detect indoor environment changes, and a method is proposed to utilize air quality and thermal comfort as the control set-points. A real-time ventilation control algorithm is proposed based on the CO2 concentration calculated according to the number of occupants. To check the thermal comfort level, the real-time operating temperature estimated from the surface temperature data of the infrared array sensor is reflected in the comfort zone defined by the American Society of Heating, Refrigerating, and Air-Conditioning Engineers (ASHRAE). The deficiencies in indoor environment conditions caused by the temporal and spatial lag of sensors in the old system are minimized using IoT technology, which also facilitates wireless communications. The image sensors can be used for multiple purposes based on various interpretations of the image information obtained.

Humans spend approximately 90% of the daytime in buildings, and greenhouse gases (GHGs) emitted by buildings account for approximately 20% of total GHG emissions. As the energy consumed during building operation from a building life-cycle perspective amounts to approximately 70–90% of the total energy, it is essential to accurately predict the energy consumption of buildings for their efficient operation. This study aims to optimize a model for predicting the thermal energy consumption of buildings by (i) first extracting major variables through feature selection and deriving significant variables in addition to the collected data and (ii) predicting the thermal energy consumption using a machine learning model. Feature selection using random forest was performed, and 11 out of 17 available data were selected. The accuracy of the prediction model was significantly improved when the hour of day variable was added. The prediction model was constructed using an artificial neural network (ANN), and the improvement in the prediction accuracy was analyzed by comparing different cases of variable combinations. The ANN prediction accuracy was improved by 15% using the feature selection process compared to when all data were used as input data, and 25% coefficient of variation of the root mean square error (CVRMSE) accuracy was achieved.