Abstract:
Increasing energy consumption of commercial buildings has motivated numerous energy tracking
and monitoring systems in the recent years. A particular area that is less explored in this domain
is that of energy apportionment whereby total energy usage of a shared space such as a building
is disaggregated to attribute it to an individual occupant. This particular scenario of individual
apportionment is important for increased transparency in the actual energy consumption of
shared living spaces in commercial buildings e.g. hotels, student dormitories and hospitals
amongst others. Accurate energy accounting is a di cult problem to solve using only a single
smart meter. In this paper, we present a novel, scalable and a low cost energy apportionment
system called WattShare that builds upon our EnergyLens architecture, where data from a
common electricity meter and smartphones (carried by the occupants) is fused, and then used
for detailed energy disaggregation. This information is then used to measure the room-level
energy consumption. We evaluate WattShare using a week long deployment conducted in a
student dormitory in a campus in India. We show that WattShare is able to disaggregate the
total energy usage from a single smart meter to individual rooms with an average precision
of 96.42% and average recall of 94.96%. WattShare achieves 86.42% energy apportionment
accuracy which increases to 94.57% when an outlier room is removed.
