Prior Flow Variational Autoencoder: A density estimation model for Non-Intrusive Load Monitoring. Henriques, L. F. M. O., Morgan, E., Colcher, S., & Milidiú, R. L. 2020.
Prior Flow Variational Autoencoder: A density estimation model for Non-Intrusive Load Monitoring [link]Paper  Prior Flow Variational Autoencoder: A density estimation model for Non-Intrusive Load Monitoring [link]Year  abstract   bibtex   11 downloads  
Non-Intrusive Load Monitoring (NILM) is a computational technique to estimate the power loads' appliance-by-appliance from the whole consumption measured by a single meter. In this paper, we propose a conditional density estimation model, based on deep neural networks, that joins a Conditional Variational Autoencoder with a Conditional Invertible Normalizing Flow model to estimate the individual appliance's power demand. The resulting model is called Prior Flow Variational Autoencoder or, for simplicity PFVAE. Thus, instead of having one model per appliance, the resulting model is responsible for estimating the power demand, appliance-by-appliance, at once. We train and evaluate our proposed model in a publicly available dataset composed of power demand measures from a poultry feed factory located in Brazil. The proposed model's quality is evaluated by comparing the obtained normalized disaggregation error (NDE) and signal aggregated error (SAE) with the previous work values on the same dataset. Our proposal achieves highly competitive results, and for six of the eight machines belonging to the dataset, we observe consistent improvements that go from 28% up to 81% in NDE and from 27% up to 86% in SAE.
@article{henriques_prior_2020,
	title = {Prior Flow Variational Autoencoder: A density estimation model for Non-Intrusive Load Monitoring},
	url = {http://arxiv.org/abs/2011.14870},
	shorttitle = {Prior Flow Variational Autoencoder},
	abstract = {Non-Intrusive Load Monitoring ({NILM}) is a computational technique to estimate the power loads' appliance-by-appliance from the whole consumption measured by a single meter. In this paper, we propose a conditional density estimation model, based on deep neural networks, that joins a Conditional Variational Autoencoder with a Conditional Invertible Normalizing Flow model to estimate the individual appliance's power demand. The resulting model is called Prior Flow Variational Autoencoder or, for simplicity {PFVAE}. Thus, instead of having one model per appliance, the resulting model is responsible for estimating the power demand, appliance-by-appliance, at once. We train and evaluate our proposed model in a publicly available dataset composed of power demand measures from a poultry feed factory located in Brazil. The proposed model's quality is evaluated by comparing the obtained normalized disaggregation error ({NDE}) and signal aggregated error ({SAE}) with the previous work values on the same dataset. Our proposal achieves highly competitive results, and for six of the eight machines belonging to the dataset, we observe consistent improvements that go from 28\% up to 81\% in {NDE} and from 27\% up to 86\% in {SAE}.},
	journaltitle = {{arXiv}:2011.14870 [cs]},
	author = {Henriques, Luis Felipe M. O. and Morgan, Eduardo and Colcher, Sergio and Milidiú, Ruy Luiz},
	urlyear = {2021},
	year = {2020},
	eprinttype = {arxiv},
	eprint = {2011.14870},
	keywords = {Computer Science - Artificial Intelligence, Computer Science - Computer Vision and Pattern Recognition, Computer Science - Machine Learning},
}
Downloads: 11
About
Documentation
Keywords
Search
Users
Terms and Conditions of Use
Privacy Policy
Sitemap
© BibBase.org 2021