Logo PUC-Rio Logo Maxwell
ETDs @PUC-Rio
Estatística
Título: LOAD DISAGGREGATION IN A BRAZILIAN INDUSTRIAL DATASET USING INVERTIBLE NETWORKS AND VARIATIONAL AUTOENCODERS
Autor: EDUARDO SANTORO MORGAN
Colaborador(es): SERGIO COLCHER - Orientador
Catalogação: 05/AGO/2021 Língua(s): ENGLISH - UNITED STATES
Tipo: TEXT Subtipo: THESIS
Notas: [pt] Todos os dados constantes dos documentos são de inteira responsabilidade de seus autores. Os dados utilizados nas descrições dos documentos estão em conformidade com os sistemas da administração da PUC-Rio.
[en] All data contained in the documents are the sole responsibility of the authors. The data used in the descriptions of the documents are in conformity with the systems of the administration of PUC-Rio.
Referência(s): [pt] https://www.maxwell.vrac.puc-rio.br/projetosEspeciais/ETDs/consultas/conteudo.php?strSecao=resultado&nrSeq=54082&idi=1
[en] https://www.maxwell.vrac.puc-rio.br/projetosEspeciais/ETDs/consultas/conteudo.php?strSecao=resultado&nrSeq=54082&idi=2
DOI: https://doi.org/10.17771/PUCRio.acad.54082
Resumo:
Load Disaggregation is the task of estimating appliance-level consumption from a single aggregate consumption metering point. This work explores machine learning techniques applied to an industrial load disaggregation dataset from a poultry feed factory in Brazil. It proposes a model that combines variational autoencoders with invertible normalizing flows models. The results obtained are, in general, better than the current best reported results for this dataset, outperforming them by up to 86 percent in the Signal Aggregate Error and by up to 81 percent in the Normalized Disaggregation Error.
Descrição: Arquivo:   
COMPLETE PDF