Energy Disaggregation via Discriminative Sparse Coding

By J. Kolter, Siddharth Batra, Andrew Y. Ng. Neural Information Processing Systems, 2010

381 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/ae73bcd83e32cb1b52b51166a477e0612a66eb52

How researchers see this paper

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

Citations in the corpus

Non-Intrusive Load Monitoring Approaches for Disaggregated Energy Sensing: A Survey (2012, methodology): “In order to ease the data annotation process, sub-metering approach has also been utilized [13,25,26] that requires installation of one energy meter per appliance to record appliance-specific consumption patterns.”
Big IoT data mining for real-time energy disaggregation in buildings (2016, background): “sensors to identify the operational state of the appliances [12], motion sensors, the frequency of the appliance used [13], as well as time and appliance usage duration [13], [14].”
Approximate Inference in Additive Factorial HMMs with Application to Energy Disaggregation (2012, background): “Recent work has begun to look at more complex inference procedures for the actual disaggregation task, including FHMMs (with block Gibbs sampling) (Kim et al., 2011) and sparse coding methods (Kolter et al., 2010).”
AMPds: A public dataset for load disaggregation and eco-feedback research (2013, methodology): “The Plugwise dataset was used by [4] but is only available upon the submission of a request to the company.”
REDD : A Public Data Set for Energy Disaggregation Research (2011, background): “In our own past work [8] we have considered this challenge of generalizing across multiple homes, but the data used in that work was only available at an extremely low resolution (one hour), and was not permitted to be made publicly available, greatly limiting the ability of researchers to directly…”
Big data analytics in smart grids: a review (2018, methodology): “A deep learning approach with multiple layers of dictionaries trained for each device as “ deep sparse coding ” is utilized in (Singh & Majumdar, 2017; Zico Kolter et al., 2010).”
Exploiting HMM Sparsity to Perform Online Real-Time Nonintrusive Load Monitoring (2016, result): “We were surprised our disaggregator scor d as well as it did after reading Kolte ’s [21] published results for hourly disaggregation.”
Non-Intrusive Load Monitoring Using Prior Models of General Appliance Types (2012, methodology): “The first uses supervised methods which assume that sub-metered (ground truth) data is available for training prior to performing disaggregation (Kolter, Batra, and Ng 2010; Kolter and Johnson 2011).”
Tackling Climate Change with Machine Learning (2019, background): “l for targeting efﬁciency measures, and can motivate behavioral changes. Promising ML approaches to this problem include hidden Markov models [278], sparse coding algorithms for structured prediction [279], harmonic analysis that picks out the “signatures” of individual appliances [280], and deep ne”