Small logo of ETH main building ETH Zurich : Computer Science : Pervasive Computing : Distributed Systems : Research : ECO data set

ECO data set (Electricity Consumption & Occupancy)

A Research Project of the Distributed Systems Group

Summary

Update: We developed an interactive dashboard application that visualizes the ECO data set. The application allows you to browse through the data, get an overview of the data set, and download chunks of it for your analysis (please get in touch with Wilhelm Kleiminger for the credentials).

This website provides access to the ECO data set (Electricity Consumption and Occupancy). The ECO data set is a comprehensive data set for non-intrusive load monitoring and occupancy detection research. It was collected in 6 Swiss households over a period of 8 months. For each of the households, the ECO data set provides:
  • 1 Hz aggregate consumption data. Each measurement contains data on current, voltage, and phase shift for each of the three phases in the household.
  • 1 Hz plug-level data measured from selected appliances.
  • Occupancy information measured through a tablet computer (manual labeling) and a passive infrared sensor (in some of the households).
We make the ECO data set available to the research community. You may directly access the data set, but we always like to receive a short description on what you plan to do with the data via e-mail to Wilhelm Kleiminger.

Project context

The data was collected in the context of the project Smart Meter Services. The project is related to the open source framework NILM-Eval, in which we utilize the ECO data set to evaluate a set of non-intrusive load monitoring algorithms and our work on opportunistic occupancy sensing. We have also published the OpenWrt package Pylon, which allows for obtaining measurements from SML-based smart electricity meters.

Downloads

The data set may be obtained from http://data-archive.ethz.ch/delivery/DeliveryManagerServlet?dps_pid=IE594964 or via its own DOI.

Publications

The following publications contain more detailed information on the data set and the measurement infrastructure deployed into the six household to collect the data. Please cite one or both of these papers when using the data set.

The following projects contributed to the ECO data set or made use of it in their analysis:

  • Zeno Koller
    ECOviz: A Web-based Time Series Dashboard
    Bachelor's thesis, ETH Zurich, 2015.

  • Romano Cicchetti
    NILM-Eval: Disaggregation of Real-World Electricity Consumption Data.
    Master's thesis, ETH Zurich, 2014.

  • Andreas Dröscher and Sara Kilcher
    Web of Energy
    Distributed Systems Laboratory Project, ETH Zurich, 2013.

  • Daniel Pauli
    Open Metering.
    Master's thesis, ETH Zurich, 2012.

Acknowledgements

We thank our project partner Energie Thun and the participating households for their support. We also want to thank our students (Zeno Koller, Andreas Dröscher, Christian Stücklberger, Daniel Pauli, Dominique im Obersteg, Manuel Kläy, Michael Spiegel, Romano Cicchetti, Sarah Kilcher, Steven van Damme, and Thomas Selber) for their valuable support in collecting, analyzing, and visualizing the data.

See also the following related items:

ETH ZurichDistributed Systems Group
Last updated January 1 1970 01:00:00 AM MET ko