Name
Abstract | ||
|---|---|---|
Energy-saving becomes an increasingly important point since the demand for energy increases, and the resources for production are limited. One way to help consumers to save is by providing them with more transparency on how they are consuming. Energy disaggregation seeks to distinguish the electrical energy consumption of distinct devices connected to a single channel, in a non-intrusive way from a single measuring point. Deep learning is very promising in this field since they present better results when compared to previous models such as the Factorial Hidden Markov Model and Graph Signal Processing. In this work, we propose a deep learning approach for energy disaggregation, focusing on its performance for embedded devices. Thus, we evaluate the scalability of our proposal for disaggregating multiple appliances considering an embedded device. The results show that our proposal is well-suited for this application and better than previous works. |
Year | DOI | Venue |
|---|---|---|
2019 | 10.1109/SBESC49506.2019.9046095 | 2019 IX Brazilian Symposium on Computing Systems Engineering (SBESC) |
Keywords | DocType | ISSN |
Energy disaggregation,NILM,embedded systems,deep learning | Conference | 2324-7886 |
ISBN | Citations | PageRank |
978-1-7281-6319-2 | 0 | 0.34 |
References | Authors | |
12 | 3 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Eduardo G. Santos | 1 | 0 | 0.34 |
| Cristopher G. S. Freitas | 2 | 0 | 0.34 |
| André L. L. Aquino | 3 | 0 | 0.34 |