Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

BAYESIAN-OPTIMIZED BIDIRECTIONAL LSTM REGRESSION MODEL FOR NON-INTRUSIVE LOAD MONITORING

Abstract: 

In this paper, a Bayesian-optimized bidirectional Long Short -Term Memory (LSTM) method for energy disaggregation, is introduced. Energy disaggregation, or Non-Intrusive Load Monitoring (NILM), is a process aiming to identify the individual contribution of appliances in the aggregate electricity load. The proposed model, Bayes-BiLSTM, is structured in a modular way to address multi-dimensionality issues that arise when the number of appliances increase. In addition, a non-causal model is introduced in order to tackle with inherent structure, characterizing the operation of multi-state appliances. Furthermore, a Bayesian-optimized framework is introduced to select the best configuration of the proposed regression model, thus increasing performance. Experimental results indicate the proposed method’s superiority, compared to the current state-of-the-art.

up
0 users have voted:

Paper Details

Authors:
Maria Kaselimi, Nikolaos Doulamis, Anastasios Doulamis, Athanasios Voulodimos, Eftychios Protopapadakis
Submitted On:
10 May 2019 - 4:49pm
Short Link:
Type:
Poster
Event:
Presenter's Name:
Maria Kaselimi
Paper Code:
IDSP-P1.11
Document Year:
2019
Cite

Document Files

Kaselimi_icassp_2019

(96)

Subscribe

[1] Maria Kaselimi, Nikolaos Doulamis, Anastasios Doulamis, Athanasios Voulodimos, Eftychios Protopapadakis, "BAYESIAN-OPTIMIZED BIDIRECTIONAL LSTM REGRESSION MODEL FOR NON-INTRUSIVE LOAD MONITORING", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4407. Accessed: Sep. 27, 2020.
@article{4407-19,
url = {http://sigport.org/4407},
author = {Maria Kaselimi; Nikolaos Doulamis; Anastasios Doulamis; Athanasios Voulodimos; Eftychios Protopapadakis },
publisher = {IEEE SigPort},
title = {BAYESIAN-OPTIMIZED BIDIRECTIONAL LSTM REGRESSION MODEL FOR NON-INTRUSIVE LOAD MONITORING},
year = {2019} }
TY - EJOUR
T1 - BAYESIAN-OPTIMIZED BIDIRECTIONAL LSTM REGRESSION MODEL FOR NON-INTRUSIVE LOAD MONITORING
AU - Maria Kaselimi; Nikolaos Doulamis; Anastasios Doulamis; Athanasios Voulodimos; Eftychios Protopapadakis
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4407
ER -
Maria Kaselimi, Nikolaos Doulamis, Anastasios Doulamis, Athanasios Voulodimos, Eftychios Protopapadakis. (2019). BAYESIAN-OPTIMIZED BIDIRECTIONAL LSTM REGRESSION MODEL FOR NON-INTRUSIVE LOAD MONITORING. IEEE SigPort. http://sigport.org/4407
Maria Kaselimi, Nikolaos Doulamis, Anastasios Doulamis, Athanasios Voulodimos, Eftychios Protopapadakis, 2019. BAYESIAN-OPTIMIZED BIDIRECTIONAL LSTM REGRESSION MODEL FOR NON-INTRUSIVE LOAD MONITORING. Available at: http://sigport.org/4407.
Maria Kaselimi, Nikolaos Doulamis, Anastasios Doulamis, Athanasios Voulodimos, Eftychios Protopapadakis. (2019). "BAYESIAN-OPTIMIZED BIDIRECTIONAL LSTM REGRESSION MODEL FOR NON-INTRUSIVE LOAD MONITORING." Web.
1. Maria Kaselimi, Nikolaos Doulamis, Anastasios Doulamis, Athanasios Voulodimos, Eftychios Protopapadakis. BAYESIAN-OPTIMIZED BIDIRECTIONAL LSTM REGRESSION MODEL FOR NON-INTRUSIVE LOAD MONITORING [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4407