Digital ID framework for human-centric monitoring and control of smart buildings

Smart offices can help employers attract and retain talented people and can positively impact well-being and productivity. Thanks to emerging technologies and increased computational power, smart buildings with a specific focus on personal experience are gaining attraction. Real-time monitoring and estimation of the human states are key to achieving individual satisfaction. Although some studies have incorporated real-time data into the buildings to predict occupants' indoor experience (e.g., thermal comfort and work engagement), a detailed framework to integrate personal prediction models with building systems has not been well studied. Therefore, this paper proposes a framework to predict and track the real-time states of each individual and assist with decision-making (e.g., room assignment and indoor environment control). The core idea of the framework is to distinguish individuals by a new concept of Digital ID (DID), which is then integrated with recognition, prediction, recommendation, visualization, and feedback systems. The establishment of the DID database is discussed and a systematic prediction methodology to determine occupants' indoor comfort is developed. Based on the prediction results, the Comfort Score Index (CSI) is proposed to give recommendations regarding the best-fit rooms for each individual. In addition, a visualization platform is developed for real-time monitoring of the indoor environment. To demonstrate the framework, a case study is presented. The thermal sensation is considered the reference for the room allocation, and two groups of people are used to demonstrate the framework in different scenarios. For one group of people, it is assumed that they are existing occupants with personal DID databases. People in another group are considered the new occupants without any personal database, and the public database is used to give initial guesses about their thermal sensations. The results show that the recommended rooms can provide better thermal environments for the occupants compared to the randomly assigned rooms. Furthermore, the recommendations regarding the indoor setpoints (temperature and lighting level) are illustrated using a work engagement prediction model. However, although specific indoor metrics are used in the case study to demonstrate the framework, it is scalable and can be integrated with any other algorithms and techniques, which can serve as a fundamental framework for future smart buildings.