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.

Coupled and distributed simulation helps in understanding the complexity arising from the combined effects of interdependent systems, by connecting and exchanging information across several software programs. In the building energy analysis domain, several tools have been created in the past to facilitate such analyses. However, the existing coupling frameworks such as Building Control Virtual Test Bed (BCVTB), MLE+, High-Level Architecture (HLA), and Functional Mockup Unit are characterized by their inherent complexity, making it a challenge for the building practitioners to widely deploy them in everyday decision-making. In addition, several of these frameworks embody tight coupling, which means they lack the flexibility to incorporate models and components of decision-makers’ choice. This study addresses these gaps by proposing a Lightweight and Adaptive Building Simulation (LABS) framework that capitalizes on Lightweight Communications and Marshalling (LCM), an inter-process communication framework widely used by the robotics community. As a case study demonstrating this new framework, a building energy simulation model is coupled with an agent-based occupant behavior model to understand the energy effects of occupants’ thermal comfort related actions (e.g., adjusting the thermostat set point). These behavioral patterns are also influenced by various interventions (e.g., peer pressure, energy-based education) that may occur in the building. Measuring these effects in a real building for a lengthy period is impractical and resource-intensive and the LABS framework can be used for understanding this system better. The results also highlight opportunities for achieving energy savings by influencing the occupants’ comfort related behavior.