Search

Most engineers predict future building energy consumption via simulation programs in the pre-design phase. In this process, many simulation steps have to be repeated to predict building energy consumption. The authors in this article proposed another way to select optimal building materials for saving commercial building energy in the U.S. using soft computing methods. To achieve the research goal, reliable public data that is provided by the U.S. Energy Information Administration was used. The data contain numerous energyrelated characteristics of buildings including gas, electricity, types of materials, and climate conditions of 6,700 commercial buildings located in the U.S. This study utilized two methods to find out optimal building materials for saving energy. First, the Principle Component Analysis was used to determine which building characteristics among over 400 characteristics have the greatest impact on gas and electricity consumption. Second, Association Rule Mining was used to extract combinations of optimal building materials. Since a building consists of a combination of various materials, energy simulation should predict for multiple factors rather than a single factor. The use of these methods would greatly reduce resources, such as limited budget and time, during the simulation process.

Thermal comfort is a critical issue in achieving an acceptable indoor environment and managing building energy use. However, it is difficult to precisely recognize thermal comfort because its determination varies depending on the characteristics of humans and indoor spaces. Moreover, accumulating datasets of indoor environmental and individual features is challenging in terms of both collection time and cost, and is sometimes unrealistic. This study established a prediction model for individual thermal comfort to mitigate this challenge. This model is based on ensemble transfer learning (TL) to transfer knowledge from datasets of someone in different indoor spaces and thermal environments, even if the physiological and environmental data of the target subject are insufficient. First, the physiological data of each subject and the indoor environmental data were collected from wearable wristbands and sensors. Then, a pre-trained model was developed with the datasets by combining deep learning and machine learning algorithms. Based on the pre-trained model, the ensemble TL method was applied to overcome the weak generalization performance that occurred when the dataset of each target subject was insufficient. The results revealed that the ensemble TL more accurately predicted the thermal comfort of two target subjects using the pre-trained model from a source. The accuracy and F1-score were both 95% for the first subject. For the second subject, they were calculated as 85% and 83%, respectively. It was also found that the ensemble TL was suitable for application when using fewer and imbalanced datasets in the target domains.