New Dataset for Event-Based Electricity Disaggregation Research
We just received the news that our paper for the 2012 KDD Workshop on Data Mining Applications in Sustainability (SustKDD) has been accepted. In this paper we describe how we collected and processed a week-long dataset of voltage and current measurements for a whole house, at 12 kHz, and labeled each of the appliance state transitions (e.g., a TV turning off, a toaster turngin on, etc.) that occurred during that period.
The dataset can be found here:
The paper in question will be published later this year, but here is the reference:
K. Anderson, A. Ocneanu, D. Benitez, D. Carlson, A. Rowe, and M. Berges, “BLUED: A Fully Labeled Public Dataset for Event-Based Non-Intrusive Load Monitoring Research,” in Proceedings of the 2nd KDD Workshop on Data Mining Applications in Sustainability (SustKDD), Beijing, China, 2012.