Management of Pervasive Devices in Smart Buildings
ACTLab Activities
Office buildings take up to a year to be fully commissioned, and usually, only a subset of the installed capacities are deployed. The main goal of the project is to aid in the commissioning and management of smart office building with a high density of pervasive devices. We design algorithms and data analysis frameworks which tap into the building’s natural data flow between sensors and actuators. We use the natural behaviour of occupants to infer groups and hierarchies of context variables, sensors’ relative position, and changes in the patterns of building use.
Sensing technologies, comfort and energy saving:
The natural behaviour of building’s occupants is measured by detecting activities and context variables. We studied the limitations of widely used technologies like self-powered motion detectors, ultrasound sensors, and emerging technologies like low-cost thermopile array sensors. We analysed the effect of high-density sensor installation on energy-saving, and the effect of user feedback in order to improve activity detection performance. We also studied the different types of activities that could be measured using thermopile array sensors.
Example of object extraction from an image of the thermopile array sensor used in the kitchen area. Blue squares represent areas of interest and green squares represent pixels which passed the temperature threshold. After processing, three persons are detected (dark blue, green, red), and we can estimate that one of them is using the coffee pot in the lower right corner.
Presence detection installation using ultrasound sensors, installed in the white boxes visible on either side of the screen. The dual sensor installation allows determining which area of the desk people are using. Ceiling lights and desk lamps levels can be controlled accordingly. A self-powered switch gives users the ability to overwrite system settings.
Energy savings achieved in a 12 desk open office. Our approach (GB-BMS) controlled each ceiling lamp individually based on presence in the lamp’s area of coverage. The results were achieved by comparing GB-BMS against using one presence sensor in the room (BMS-01) or two (BMS-02).
Publication List
[publication-list ids=”MDBQNFW5,ERWSQCW5,NRQZFNBP,V6AN4DHV” sort=date ]
Contact
Dr. Luis I. Lopera G.
- Job title: Researcher
- Phone number: +49 9131 85-23605
- Email: luis.i.lopera@fau.de