Oliver Parson

TL;DR: This work is the first research to compare multiple disaggregation approaches across multiple publicly available data sets, and demonstrates the range of reproducible analyses made possible by the toolkit.

TL;DR: This paper proposes an approach by which individual appliances can be iteratively separated from an aggregate load, and evaluates the accuracy of the approach using the REDD data set, and shows the disaggregation performance when using the training approach is comparable to when sub-metered training data is used.

TL;DR: Empirical evaluation demonstrates that general appliance models can be constructed using data from only a small number of appliances, and furthermore that 28–99% of the remaining behaviour which is specific to a single household can be learned using only aggregate data from existing smart meters.

TL;DR: A subset of the Dataport database in NILMTK format is released, containing one month of electricity data from 669 households, posing a challenge to the signal processing community to produce energy disaggregation algorithms which are both accurate and scalable.

TL;DR: A rewrite of the disaggregation API and a new experiment API are described which lower the barrier to entry for algorithm developers and simplify the definition of algorithm comparison experiments, and the release of NILMTK-contrib is described; a new repository containing NIL MTK-compatible implementations of 3 benchmarks and 9 recent disaggregation algorithms.