Linking Building Energy-Load Variations with Occupants' Energy-Use Behaviors in Commercial Buildings: Non-Intrusive Occupant Load Monitoring (NIOLM)

Abstract

Studies indicate that occupancy-related energy-use behaviors have a significant influence on overall energy consumption in commercial buildings. In this context, understanding and improving occupants' energy-consuming behaviors shows promise as a cost-effective approach to decreasing commercial buildings' energy demands. Current behavior-modification pursuits rely on the data availability of occupant-specific energy consumption, but it is still quite challenging to track occupant-specific energy-consuming behaviors in commercial buildings. On the other hand, individual occupants have unique energy-consumption patterns at their entry and departure events and will typically follow such patterns consistently over time. Thus, analyzing occupants' energy-use patterns at the time of their entry and departure events plays a critical role in understanding individual occupants' energy-use behaviors. To this end, this paper aims to develop a non-intrusive occupant load monitoring (NIOLM) approach that profiles individual occupants' energy-use behaviors at their entry and departure events. The NIOLM approach correlates occupancy-sensing data captured from existing Wi-Fi networks with aggregated building energy-monitoring data in order to disaggregate building energy loads to the level of individual occupants. Results from a 3-month long period of tracking individual occupants validate the feasibility of the NIOLM approach by comparing the framework's outcomes with the individual metering data captured from plug-load sensors. By utilizing existing devices and Wi-Fi network infrastructure, NIOLM provides a new opportunity for current industry and research efforts to track individual occupants' energy-use behaviors at a minimal cost.