AMPds: A public dataset for load disaggregation and eco-feedback research

By S. Makonin, Fred Popowich, L. Bartram, Bob Gill, I. Bajić. 2013 IEEE Electrical Power & Energy Conference, 2013

336 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Exploiting HMM Sparsity to Perform Online Real-Time Nonintrusive Load Monitoring (2016, background): “To support our contribution claims in Section I-A, we chose two low-frequency datasets: AMPds [12] and REDD [18].”
Short-Term Residential Load Forecasting Based on Resident Behaviour Learning (2018, methodology): “In this study, AMPds is used for the proof of concept [6].”
NILMTK: an open source toolkit for non-intrusive load monitoring (2014, methodology): “The Almanac of Minutely Power dataset (AMPds) [15] was also released that year containing both”
The ECO data set and the performance of non-intrusive load monitoring algorithms (2014, methodology): “Since then, other data sets have been published such as the Smart* data set [4], GREEND [26], BLUED [1], AMPds [24], UK-Dale [18], iAWE [5], and the Pecan Street [15] data set.”
Matrix Profile I: All Pairs Similarity Joins for Time Series: A Unifying View That Includes Motifs, Discords and Shapelets (2016, methodology): “We demonstrate the utility of these ideas on the AMPds dataset [11].”