Non-Intrusive Load Monitoring Based on Novel Transient Signal in Household Appliances with Low Sampling Rate

Thi-Thu-Huong Le and Howon Kim
Additional contact information
Thi-Thu-Huong Le: School of Computer Science and Engineering, Pusan National University, Busan 609-735, Korea
Howon Kim: School of Computer Science and Engineering, Pusan National University, Busan 609-735, Korea

Energies, 2018, vol. 11, issue 12, 1-35

Abstract: Nowadays climate change problems have been more and more concerns and urgent in the real world. Especially, the energy power consumption monitoring is a considerate trend having positive effects in decreasing affecting climate change. Non-Intrusive Load Monitoring (NILM) is the best economic solution to solve the electrical consumption monitoring issue. NILM captures the electrical signals from the aggregate energy consumption, feature extraction from these signals and then learning and predicting the switch ON/OFF of appliances used these feature extracted. This paper proposed a NILM framework including data acquisition, data feature extraction, and classification model. The main contribution is to develop a new transient signal in a different aspect. The proposed transient signal is extracted from the active power signal in the low-frequency sampling rate. This transient signal is used to detect the event of household appliances. In household appliances event detection, we applied to Decision Tree and Long Short-Time Memory (LSTM) models. The average accuracies of these models achieved 92.64% and 96.85%, respectively. The computational and result experiments present the solution effectiveness for the accurate transient signal extraction in the electrical input signals.

Keywords: NILM; energy disaggregation; MCP39F511; Jetson TX2; transient signature; decision tree; LSTM (search for similar items in EconPapers)
JEL-codes: Q Q0 Q4 Q40 Q41 Q42 Q43 Q47 Q48 Q49 (search for similar items in EconPapers)
Date: 2018
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (10)

Downloads: (external link)
https://www.mdpi.com/1996-1073/11/12/3409/pdf (application/pdf)
https://www.mdpi.com/1996-1073/11/12/3409/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jeners:v:11:y:2018:i:12:p:3409-:d:188176

Access Statistics for this article

Energies is currently edited by Ms. Agatha Cao

More articles in Energies from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().