Human-in-the-loop BMS Point Matching and Metadata Labeling with Babel
In this project, we work on solving the problem of inconsistent Building Management Systems (BMS) metadata in non-residential buildings through crowd-sourcing the building occupants. Inconsistent BMS metadata hinders the deployment of novel cyber-physical applications.
The reasons that make non-residential buildings a prime candidate for cyber-physical applications are numerous: These buildings account for a major share in energy use in Western countries, while the average person spends a long time inside them. At the same time, many non-residential buildings contain already a BMS. A BMS controls building functions like HVAC and lightening through sensors and actuators and is controlled by a building manager. Recent work has developed cyber-physical applications on top of such a BMS infrastructure that show great potential in terms of energy reduction and comfort improvements. The means of which these applications access the sensors and actuators of a BMS is by their metadata in form of point labels.
So why are these applications not deployed beyond single research experiments? Deploying such applications on many buildings requires portable applications. Currently, this portability can not be achieved because BMS metadata is very building specific, incomplete and inconsistent—no universal namespace is used. Solving this portability problem is what we are working on with Babel.
Babel is a continuous, human-in-the-loop and crowdsourced approach to the creation and maintenance of BMS metadata. Occupants provide physical and digital input in form of actuations (e.g., the switching of a light) and readings (e.g., the reading of the room temperature of a thermostat) to Babel. Babel then matches this input to digital points in the BMS based on value equality. We have already implemented a prototype of our system in a non-residential building over the BACnet protocol. While our approach can not solve all metadata problems, initial experiments show that it is able to match many points in a fast and precise manner.