Crowd-sourced BMS point matching and metadata maintenance with Babel

Cyber-physical applications, deployed on top of Building Management Systems (BMS), promise energy saving and comfort improvement in non-residential buildings. Such applications are so far mainly deployed as research prototypes. The main roadblock to widespread adoption is the low quality of BMS metadata. There is indeed a mismatch between (i) the anecdotal nature of metadata for legacy BMS - they are usually initialized when the BMS is commissioned and later neglected-, and (ii) the imperious need for consistent and up-to-date metadata for supporting building analytics or personalized control systems. Such applications access sensors and actuators through BMS metadata in form of point labels. The naming of labels is however often inconsistent and incomplete. To tackle this problem, we introduce Babel, a crowd-sourced approach to the creation and maintenance of BMS metadata. In our system, occupants provide physical and digital input in form of actuations (e.g., the turning on/off a light) and readings (e.g., reading room temperature of a thermostat) to Babel. Babel then matches this input to digital points in the BMS based on value equality. We have implemented a prototype of our system in a non-residential building. While our approach can not solve all metadata problems, we show that it is able to match end-user relevant points in a fast and precise manner.