Convolutional Sequence to Sequence Non-intrusive Load Monitoring
Machine Learning
2018-06-07 v1 Machine Learning
Applications
Abstract
A convolutional sequence to sequence non-intrusive load monitoring model is proposed in this paper. 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. We apply the proposed model to the REDD 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.
Cite
@article{arxiv.1806.02078,
title = {Convolutional Sequence to Sequence Non-intrusive Load Monitoring},
author = {Kunjin Chen and Qin Wang and Ziyu He and Kunlong Chen and Jun Hu and Jinliang He},
journal= {arXiv preprint arXiv:1806.02078},
year = {2018}
}
Comments
This paper is submitted to IET-The Journal of Engineering