Research

Designing sensor sets for capturing energy events in buildings


Reference:

Lovett, T. R., Gabe-Thomas, E., Natarajan, S., Brown, M. and Padget, J. A., 2014. Designing sensor sets for capturing energy events in buildings. Working Paper.

Related documents:

[img]
Preview
PDF (working paper) - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
Download (1717kB) | Preview

    Abstract

    We study the problem of designing sensor sets for capturing energy events in buildings. In addition to direct energy sens- ing methods, e.g. electricity and gas, it is often desirable to monitor energy use and occupant activity through other sensors such as temperature and motion. However, practical constraints such as cost and deployment requirements can limit the choice, quantity and quality of sensors that can be distributed within each building, especially for large-scale deployments. In this paper, we present an approach to select a set of sensors for capturing energy events, using a measure of each candidate sensor’s ability to predict energy events within a building. We use constrained optimisation – specif- ically, a bounded knapsack problem (BKP) – to choose the best sensors for the set given each sensor’s predictive value and specified cost constraints. Our approach arises from a field study of 4 UK homes with temperature, light, motion, humidity, sound and CO2 sensors. By using random forests to generate a measure of each sensor’s predictive value, and financial cost as a measure of each sensor’s cost, the results show that these environmental sensors are useful predictors of energy use, though the optimal sets vary substantially with the constraint parameters. Furthermore, valuable yet expen- sive sensors such as CO2 are often not chosen in the opti- mal set, and a proportion of both CO2 and light level can be predicted from the other environmental sensors used in the study.

    Details

    Item Type Reports/Papers (Working Paper)
    CreatorsLovett, T. R., Gabe-Thomas, E., Natarajan, S., Brown, M. and Padget, J. A.
    Uncontrolled Keywordsenergy sensing,machine learning,environmental sensing,occupancy sensing
    DepartmentsFaculty of Engineering & Design > Architecture & Civil Engineering
    Faculty of Humanities & Social Sciences > Psychology
    Faculty of Science > Computer Science
    Research CentresMedia Technology Research Centre
    ?? WIRC ??
    StatusUnpublished
    ID Code39150

    Export

    Actions (login required)

    View Item

    Document Downloads

    More statistics for this item...