A limited-data model of building energy consumption
Andrew Rice, Simon Hay and Dan Ryder-Cook. A limited-data model of building energy consumption. In Proceedings of the 2nd ACM Workshop On Embedded Sensing Systems For Energy-Efficiency In Buildings (BuildSys 2010, in conjunction with ACM SenSys 2010).
We present a model targeted at practical, wide-scale deployment which produces an ongoing breakdown of building energy consumption. We argue that wide-scale deployment is practical due to its reliance only on commonly available sensor information and crowd-sourced inventory data. The results for our own building over the previous 10 months show many of the trends seen in the building's true, metered energy consumption and we find our model predicts long term averages within 10% of the true value in some scenarios. We further use our model to estimate the potential impact of some energy saving scenarios.