Big IoT data mining for real-time energy disaggregation in buildings

D.C. Mocanu, E. Mocanu, H.P. Nguyen, M. Gibescu, A. Liotta

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

8 Citations (Scopus)
677 Downloads (Pure)

Abstract

In the smart grid context, the identification and prediction of building energy flexibility is a challenging open question, thus paving the way for new optimized behaviors from the demand side. At the same time, the latest smart meters developments allow us to monitor in real-time the power consumption level of the home appliances, aiming at a very accurate energy disaggregation. However, due to practical constraints is infeasible in the near future to attach smart meter devices on all home appliances, which is the problem addressed herein. We propose a hybrid approach, which combines sparse smart meters with machine learning methods. Using a subset of buildings equipped with subset of smart meters we can create a database on which we train two deep learning models, i.e. Factored Four-Way Conditional Restricted Boltzmann Machines (FFW-CRBMs) and Disjunctive FFW-CRBM. We show how our method may be used to accurately predict and identify the energy flexibility of buildings unequipped with smart meters, starting from their aggregated energy values. The proposed approach was validated on a real database, namely the Reference Energy Disaggregation Dataset. The results show that for the flexibility prediction problem solved here, Disjunctive FFW-CRBM outperforms the FFW-CRBMs approach, where for classification task their capabilities are comparable.
Original languageEnglish
Title of host publicationProceedings of the IEEE International Conference on Systems, Man, and Cybernetics (SMC 2016), 9-12 October 2016, Budapest, Hungary
Place of PublicationPiscataway
PublisherInstitute of Electrical and Electronics Engineers
Pages003765-003769
ISBN (Electronic)978-1-5090-1897-0
ISBN (Print)978-1-5090-1898-7
DOIs
Publication statusPublished - 9 Feb 2017

Fingerprint

Smart meters
Data mining
Domestic appliances
Learning systems
Electric power utilization
Internet of things

Cite this

Mocanu, D. C., Mocanu, E., Nguyen, H. P., Gibescu, M., & Liotta, A. (2017). Big IoT data mining for real-time energy disaggregation in buildings. In Proceedings of the IEEE International Conference on Systems, Man, and Cybernetics (SMC 2016), 9-12 October 2016, Budapest, Hungary (pp. 003765-003769). Piscataway: Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/SMC.2016.7844820
Mocanu, D.C. ; Mocanu, E. ; Nguyen, H.P. ; Gibescu, M. ; Liotta, A. / Big IoT data mining for real-time energy disaggregation in buildings. Proceedings of the IEEE International Conference on Systems, Man, and Cybernetics (SMC 2016), 9-12 October 2016, Budapest, Hungary. Piscataway : Institute of Electrical and Electronics Engineers, 2017. pp. 003765-003769
@inproceedings{f4582d0fdb7343c0be941782c9bc2a69,
title = "Big IoT data mining for real-time energy disaggregation in buildings",
abstract = "In the smart grid context, the identification and prediction of building energy flexibility is a challenging open question, thus paving the way for new optimized behaviors from the demand side. At the same time, the latest smart meters developments allow us to monitor in real-time the power consumption level of the home appliances, aiming at a very accurate energy disaggregation. However, due to practical constraints is infeasible in the near future to attach smart meter devices on all home appliances, which is the problem addressed herein. We propose a hybrid approach, which combines sparse smart meters with machine learning methods. Using a subset of buildings equipped with subset of smart meters we can create a database on which we train two deep learning models, i.e. Factored Four-Way Conditional Restricted Boltzmann Machines (FFW-CRBMs) and Disjunctive FFW-CRBM. We show how our method may be used to accurately predict and identify the energy flexibility of buildings unequipped with smart meters, starting from their aggregated energy values. The proposed approach was validated on a real database, namely the Reference Energy Disaggregation Dataset. The results show that for the flexibility prediction problem solved here, Disjunctive FFW-CRBM outperforms the FFW-CRBMs approach, where for classification task their capabilities are comparable.",
author = "D.C. Mocanu and E. Mocanu and H.P. Nguyen and M. Gibescu and A. Liotta",
year = "2017",
month = "2",
day = "9",
doi = "10.1109/SMC.2016.7844820",
language = "English",
isbn = "978-1-5090-1898-7",
pages = "003765--003769",
booktitle = "Proceedings of the IEEE International Conference on Systems, Man, and Cybernetics (SMC 2016), 9-12 October 2016, Budapest, Hungary",
publisher = "Institute of Electrical and Electronics Engineers",
address = "United States",

}

Mocanu, DC, Mocanu, E, Nguyen, HP, Gibescu, M & Liotta, A 2017, Big IoT data mining for real-time energy disaggregation in buildings. in Proceedings of the IEEE International Conference on Systems, Man, and Cybernetics (SMC 2016), 9-12 October 2016, Budapest, Hungary. Institute of Electrical and Electronics Engineers, Piscataway, pp. 003765-003769. https://doi.org/10.1109/SMC.2016.7844820

Big IoT data mining for real-time energy disaggregation in buildings. / Mocanu, D.C.; Mocanu, E.; Nguyen, H.P.; Gibescu, M.; Liotta, A.

Proceedings of the IEEE International Conference on Systems, Man, and Cybernetics (SMC 2016), 9-12 October 2016, Budapest, Hungary. Piscataway : Institute of Electrical and Electronics Engineers, 2017. p. 003765-003769.

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

TY - GEN

T1 - Big IoT data mining for real-time energy disaggregation in buildings

AU - Mocanu, D.C.

AU - Mocanu, E.

AU - Nguyen, H.P.

AU - Gibescu, M.

AU - Liotta, A.

PY - 2017/2/9

Y1 - 2017/2/9

N2 - In the smart grid context, the identification and prediction of building energy flexibility is a challenging open question, thus paving the way for new optimized behaviors from the demand side. At the same time, the latest smart meters developments allow us to monitor in real-time the power consumption level of the home appliances, aiming at a very accurate energy disaggregation. However, due to practical constraints is infeasible in the near future to attach smart meter devices on all home appliances, which is the problem addressed herein. We propose a hybrid approach, which combines sparse smart meters with machine learning methods. Using a subset of buildings equipped with subset of smart meters we can create a database on which we train two deep learning models, i.e. Factored Four-Way Conditional Restricted Boltzmann Machines (FFW-CRBMs) and Disjunctive FFW-CRBM. We show how our method may be used to accurately predict and identify the energy flexibility of buildings unequipped with smart meters, starting from their aggregated energy values. The proposed approach was validated on a real database, namely the Reference Energy Disaggregation Dataset. The results show that for the flexibility prediction problem solved here, Disjunctive FFW-CRBM outperforms the FFW-CRBMs approach, where for classification task their capabilities are comparable.

AB - In the smart grid context, the identification and prediction of building energy flexibility is a challenging open question, thus paving the way for new optimized behaviors from the demand side. At the same time, the latest smart meters developments allow us to monitor in real-time the power consumption level of the home appliances, aiming at a very accurate energy disaggregation. However, due to practical constraints is infeasible in the near future to attach smart meter devices on all home appliances, which is the problem addressed herein. We propose a hybrid approach, which combines sparse smart meters with machine learning methods. Using a subset of buildings equipped with subset of smart meters we can create a database on which we train two deep learning models, i.e. Factored Four-Way Conditional Restricted Boltzmann Machines (FFW-CRBMs) and Disjunctive FFW-CRBM. We show how our method may be used to accurately predict and identify the energy flexibility of buildings unequipped with smart meters, starting from their aggregated energy values. The proposed approach was validated on a real database, namely the Reference Energy Disaggregation Dataset. The results show that for the flexibility prediction problem solved here, Disjunctive FFW-CRBM outperforms the FFW-CRBMs approach, where for classification task their capabilities are comparable.

U2 - 10.1109/SMC.2016.7844820

DO - 10.1109/SMC.2016.7844820

M3 - Conference contribution

SN - 978-1-5090-1898-7

SP - 3765

EP - 3769

BT - Proceedings of the IEEE International Conference on Systems, Man, and Cybernetics (SMC 2016), 9-12 October 2016, Budapest, Hungary

PB - Institute of Electrical and Electronics Engineers

CY - Piscataway

ER -

Mocanu DC, Mocanu E, Nguyen HP, Gibescu M, Liotta A. Big IoT data mining for real-time energy disaggregation in buildings. In Proceedings of the IEEE International Conference on Systems, Man, and Cybernetics (SMC 2016), 9-12 October 2016, Budapest, Hungary. Piscataway: Institute of Electrical and Electronics Engineers. 2017. p. 003765-003769 https://doi.org/10.1109/SMC.2016.7844820