Decision-making model for energy efficient technologies in green buildings

Abstract

Employee satisfaction is paramount as it directly impacts their productivity and health, particularly in the office environment, where thermal comfort plays a crucial role. Existing quantitative methods for evaluating thermal comfort satisfaction solely focus on building structural elements. To bridge this gap, a study was conducted, surveying 1091 staff members across 14 green office buildings to assess their satisfaction with indoor environmental quality (IEQ) comfort. The analysis introduced a proposed network of IEQ comfort features to aid in designing the questionnaire and measuring the environment. To address the issue of an imbalanced dataset, the study implemented various resampling methods along with feature selection techniques that integrated statistical analysis methods and machine learning algorithms. Developing predictive models using the Random Forest algorithm allowed for a comparison with Decision Tree, Lasso Regression and Support Vector Regression models. Three predictive models were created to assess thermal comfort, visual comfort and indoor air quality comfort separately, and one predictive model was created to assess the overall IEQ comfort. The study identified significant factors influencing IEQ comfort satisfaction, the share of the area served by AC, total window area, the thickness of the wall insulation, area served by lighting, and smart controlling. The predictive models achieved more than 75% accuracy, and interpretability supports their practical application in office design. By utilising this predictive model, building designers and managers can make informed decisions, uncovering situations where green building certifications may not meet employees' expected level of thermal comfort. Ultimately, optimising employee thermal comfort can lead to enhanced productivity.