Research Article
A Feature and Classifier Study for Appliance Event Classification
@INPROCEEDINGS{10.1007/978-3-030-97027-7_7, author={Benjamin V\o{}lker and Philipp M. Scholl and Bernd Becker}, title={A Feature and Classifier Study for Appliance Event Classification}, proceedings={Sustainable Energy for Smart Cities. Third EAI International Conference, SESC 2021, Virtual Event, November 24--26, 2021, Proceedings}, proceedings_a={SESC}, year={2022}, month={3}, keywords={NILM Non-Intrusive Load Monitoring Feature evaluation Appliance classification}, doi={10.1007/978-3-030-97027-7_7} }- Benjamin Völker
Philipp M. Scholl
Bernd Becker
Year: 2022
A Feature and Classifier Study for Appliance Event Classification
SESC
Springer
DOI: 10.1007/978-3-030-97027-7_7
Abstract
The shift towards advanced electricity metering infrastructure gained traction because of several smart meter roll-outs during the last decade. This increased the interest in Non-Intrusive Load Monitoring. Nevertheless, adoption is low, not least because the algorithms cannot simply be integrated into the existing smart meters due to the resource constraints of the embedded systems. We evaluated 27. features and four classifiers regarding their suitability for event-based NILM in a standalone and combined feature analysis. Active power was found to be the best scalar and WaveForm Approximation the best multidimensional feature. We propose the feature set(\left[ P,\textit{cos}\,\varPhi ,TRI,WFA\right] )in combination with a Random Forest classifier. Together, these lead to(F_1)-scores of up to 0.98 on average across four publicly available datasets. Still, feature extraction and classification remains computationally lightweight and allows processing on resource constrained embedded systems.
