Data-driven simulation for energy consumption estimation in a smart home

Stephen Adams (), Steven Greenspan (), Maria Velez-Rojas (), Serge Mankovski () and Peter A. Beling ()
Additional contact information
Stephen Adams: University of Virginia
Steven Greenspan: CA Technologies
Maria Velez-Rojas: CA Technologies
Serge Mankovski: CA Technologies
Peter A. Beling: University of Virginia

Environment Systems and Decisions, 2019, vol. 39, issue 3, 281-294

Abstract: Abstract Simulation and data-driven models are both tools that can play an important role in reducing the energy consumption of buildings and homes. However, sophisticated control schemes and models are only as good as the data collected by sensors and provided to them. Low-quality or faulty sensor that provide inaccurate data can lead to inefficient buildings. In this paper, we investigate the relationship between sensor quality and the prediction of energy consumption. We first construct a simulation of appliance energy consumption in a smart home and then assess the predictive ability of several data-driven models while varying the quality and function of the simulated sensors. The simulation was constructed using a smart home data set collected by other researchers. We find that the predictive ability is only decreased when noise is added to the appliance energy random variable. We conclude that low-quality sensors that do not monitor the environment as accurately as the devices used in the original study could be used for humidity and temperature without significantly reducing the predictive ability of the data-driven models. The method and findings have implications for how to conduct cost-benefit analyses of IoT device requirements.

Keywords: Data-driven models; Energy estimation; Simulation (search for similar items in EconPapers)
Date: 2019
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (4)

Downloads: (external link)
http://link.springer.com/10.1007/s10669-019-09727-1 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:envsyd:v:39:y:2019:i:3:d:10.1007_s10669-019-09727-1

Ordering information: This journal article can be ordered from
https://www.springer.com/journal/10669

DOI: 10.1007/s10669-019-09727-1

Access Statistics for this article

More articles in Environment Systems and Decisions from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().