
Open access
Datum
2018-11-29Typ
- Journal Article
ETH Bibliographie
yes
Altmetrics
Abstract
A convolutional sequence to sequence non-intrusive load monitoring model is proposed in this study. Gated linear unit convolutional layers are used to extract information from the sequences of aggregate electricity consumption. Residual blocks are also introduced to refine the output of the neural network. The partially overlapped output sequences of the network are averaged to produce the final output of the model. The authors apply the proposed model to the reference energy disaggregation data set dataset and compare it with the convolutional sequence to point model in the literature. Results show that the proposed model is able to give satisfactory disaggregation performance for appliances with varied characteristics. Mehr anzeigen
Persistenter Link
https://doi.org/10.3929/ethz-b-000320506Publikationsstatus
publishedExterne Links
Zeitschrift / Serie
The Journal of EngineeringBand
Seiten / Artikelnummer
Verlag
Institution of Engineering and TechnologyOrganisationseinheit
09642 - Fink, Olga (ehemalig) / Fink, Olga (former)
ETH Bibliographie
yes
Altmetrics