Occupancy-driven facility management and building performance analysis

Abstract

Accurate and automated real-time building monitoring is a challenging task due to the large number of different parameters that are involved. This paper presents several aspects of a building monitoring and control system that has been developed. The system is based on a multi-sensorial network which is able to capture sustainability-related metrics due to the use of heterogeneous sensors such as occupancy detection sensors, environmental sensors, power consumption sensors and actuators. The availability of occupancy information at room or zone level which is achieved via the occupancy sensors, offers the opportunity to extract valuable information about the way the building is utilized. Furthermore, as the occupancy patterns considerably affect the building's indoor environmental condition and the consumed energy, occupancy estimation turns into a useful tool for the facility manager to analyze and then improve the building's energy performance and enhance the indoor environmental quality by applying control actions through the actuators. The building information is visualized in the spatio-temporal domain to both the facility manager and the occupants via two different components. The system has been evaluated in real-life conditions at a building which is comprised of different types of spaces. Results showed that useful conclusions are drawn when occupancy information is combined with the other monitored parameters.

Measuring Indoor Occupancy through Environmental Sensors: A Systematic Review on Sensor Deployment

“…The most widely used algorithm is the conditional random field (CRF) (two publications), which is a relatively new type of discriminative probabilistic graphical model for labeling sequence data. Each feature is a real value and is associated with a numerical weight [ 16 , 77 ].…”

“…People. Accuracy 42.7–64.3% [ 83 ] 7 Y Detection, Levels NO YES 1 min CO concentration and computer electricity consumption indicators of occupancy leves Error 0.25–73.71% [ 77 ] 1 Y Detection, Num. People NO YES 5 seg CRF Detection Accuracy 84–98%, Num.…”

Smart Campus Tools

“…Furthermore, a significant number of papers make use of multiple sensing methods. In applications that optimise building services, researchers make use of sensors that measure aspects of the indoor environment, such as temperature, CO 2 , luminance, humidity, acoustics (Ekwevugbe, Brown, Pakka, & Fan, 2017;Ioannidis et al, 2017;Saralegui, Anton, Arbelaitz, & Muguerza, 2019;Schwee et al, 2019). In two recent studies, these are combined with the collection of user feedback (Dave et al, 2018;Romero Herrera et al, 2018).…”

Towards a smart campus: supporting campus decisions with Internet of Things applications

“…Furthermore, a significant number of papers make use of multiple sensing methods. In applications that optimize building services, researchers make use of sensors that measure aspects of the indoor environment, such as temperature, CO 2 , luminance, humidity, acoustics (Ekwevugbe et al, 2017;Ioannidis et al, 2017;Saralegui et al, 2019;Schwee et al, 2019). In two recent studies, these are combined with the collection of user feedback (Dave et al, 2018;Romero Herrera et al, 2018).…”