Optimizing Energy Usage through Real-Time Vacancy Detection

Buildings contribute significantly to energy consumption, accounting for nearly 40% of total energy use in the United States. Prior research indicates that up to 50% of this energy is consumed during periods of complete vacancy. This study investigates cost-effective methods for detecting realtime vacancy using existing data sources, such as CO2 levels, WiFi connections, and electricity demand. Logistic regression and artificial neural network models were developed to predict vacancy and demonstrate their effectiveness in reducing energy wastage. To contextualize the significance of this approach, ethical implications, model predictions, and broader societal impacts are discussed.