Commercial buildings are increasingly equipped with building automation systems (BAS), advanced metering infrastructure (AMI), and sensors. The data collected by these systems provides opportunities for enhanced automation, fault detection and diagnostics (FDD), as well as performance tracking and benchmarking through advanced data analytics.
This project uses advanced data analytics and inverse modeling technique to integrate sensor and meter data with physics-based models to evaluate and improve building energy efficiency as well as demand flexibility (DF). One activity area is the development of occupant-centric Key Performance Indicators (KPIs) for thermal comfort, visual comfort and indoor air quality that can be calculated from sensor and meter data. These KPIs provide a basis for evaluating occupant services when DF is activated. They will be added as a new reporting feature in EnergyPlus, allowing EnergyPlus to evalute DF strategies that are informed by these KPIs.
A second activity area is the continued development of data-driven and inverse modeling methods to infer difficult-to-obtain but important building energy model parameters from sensor and meter data streams. Previous work has shown that zone temperature time series data can be used to derive zone-infiltration rates and internal thermal mass.