Big IoT data mining for real-time energy disaggregation in buildings (extended abstract)

Decebal Constantin Mocanu; Elena Mocanu; Phuong H. Nguyen; M. Gibescu; Antonio Liotta

Big IoT data mining for real-time energy disaggregation in buildings (extended abstract)

Decebal Constantin Mocanu, Elena Mocanu, Phuong H. Nguyen, M. Gibescu, Antonio Liotta

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

12 Downloads (Pure)

Abstract

In the smart grid context, the identification and prediction of building energy flexibility is a challenging open question. In this paper, we propose a hybrid approach to address this problem. It combines sparse smart meters with deep learning methods, e.g. Factored Four-Way Conditional Restricted Boltzmann Machines (FFW-CRBMs), 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.

Original language	English
Title of host publication	Benelearn 2017
Subtitle of host publication	Proceedings of the Twenty-Sixth Benelux Conference on Machine Learning
Editors	Wouter Duivesteijn, Mykola Pechenizkiy, George Fletcher, Vlado Menkovski, Eric Postma, Joaquin Vanschoren, Pete van der Putten
Place of Publication	Eindhoven
Publisher	TU/e
Publication status	Published - 10 Jun 2017
Event	26th Benelux Conference on Machine Learning, Benelearn 2017 - Eindhoven University of Technology, Eindhoven, Netherlands Duration: 9 Jun 2017 → 10 Jun 2017 Conference number: 26

Conference

Conference	26th Benelux Conference on Machine Learning, Benelearn 2017
Abbreviated title	Benelearn
Country/Territory	Netherlands
City	Eindhoven
Period	9/06/17 → 10/06/17

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

Mocanu2017bigFinal published version, 115 KB

Cite this

Mocanu, D. C., Mocanu, E., Nguyen, P. H., Gibescu, M., & Liotta, A. (2017). Big IoT data mining for real-time energy disaggregation in buildings (extended abstract). In W. Duivesteijn, M. Pechenizkiy, G. Fletcher, V. Menkovski, E. Postma, J. Vanschoren, & P. van der Putten (Eds.), Benelearn 2017: Proceedings of the Twenty-Sixth Benelux Conference on Machine Learning TU/e.

Mocanu, Decebal Constantin ; Mocanu, Elena ; Nguyen, Phuong H. et al. / Big IoT data mining for real-time energy disaggregation in buildings (extended abstract). Benelearn 2017: Proceedings of the Twenty-Sixth Benelux Conference on Machine Learning. editor / Wouter Duivesteijn ; Mykola Pechenizkiy ; George Fletcher ; Vlado Menkovski ; Eric Postma ; Joaquin Vanschoren ; Pete van der Putten. Eindhoven : TU/e, 2017.

@inproceedings{a202b8764ef9495e8c0903065dc7220d,

title = "Big IoT data mining for real-time energy disaggregation in buildings (extended abstract)",

abstract = "In the smart grid context, the identification and prediction of building energy flexibility is a challenging open question. In this paper, we propose a hybrid approach to address this problem. It combines sparse smart meters with deep learning methods, e.g. Factored Four-Way Conditional Restricted Boltzmann Machines (FFW-CRBMs), 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.",

author = "Mocanu, {Decebal Constantin} and Elena Mocanu and Nguyen, {Phuong H.} and M. Gibescu and Antonio Liotta",

year = "2017",

month = jun,

day = "10",

language = "English",

editor = "Wouter Duivesteijn and Mykola Pechenizkiy and George Fletcher and Vlado Menkovski and Eric Postma and Joaquin Vanschoren and {van der Putten}, Pete",

booktitle = "Benelearn 2017",

publisher = "TU/e",

note = "26th Benelux Conference on Machine Learning, Benelearn 2017, Benelearn ; Conference date: 09-06-2017 Through 10-06-2017",

}

Mocanu, DC, Mocanu, E, Nguyen, PH, Gibescu, M & Liotta, A 2017, Big IoT data mining for real-time energy disaggregation in buildings (extended abstract). in W Duivesteijn, M Pechenizkiy, G Fletcher, V Menkovski, E Postma, J Vanschoren & P van der Putten (eds), Benelearn 2017: Proceedings of the Twenty-Sixth Benelux Conference on Machine Learning. TU/e, Eindhoven, 26th Benelux Conference on Machine Learning, Benelearn 2017, Eindhoven, Netherlands, 9/06/17.

Big IoT data mining for real-time energy disaggregation in buildings (extended abstract). / Mocanu, Decebal Constantin; Mocanu, Elena; Nguyen, Phuong H. et al.
Benelearn 2017: Proceedings of the Twenty-Sixth Benelux Conference on Machine Learning. ed. / Wouter Duivesteijn; Mykola Pechenizkiy; George Fletcher; Vlado Menkovski; Eric Postma; Joaquin Vanschoren; Pete van der Putten. Eindhoven: TU/e, 2017.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Big IoT data mining for real-time energy disaggregation in buildings (extended abstract)

AU - Mocanu, Decebal Constantin

AU - Mocanu, Elena

AU - Nguyen, Phuong H.

AU - Gibescu, M.

AU - Liotta, Antonio

N1 - Conference code: 26

PY - 2017/6/10

Y1 - 2017/6/10

N2 - In the smart grid context, the identification and prediction of building energy flexibility is a challenging open question. In this paper, we propose a hybrid approach to address this problem. It combines sparse smart meters with deep learning methods, e.g. Factored Four-Way Conditional Restricted Boltzmann Machines (FFW-CRBMs), 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.

AB - In the smart grid context, the identification and prediction of building energy flexibility is a challenging open question. In this paper, we propose a hybrid approach to address this problem. It combines sparse smart meters with deep learning methods, e.g. Factored Four-Way Conditional Restricted Boltzmann Machines (FFW-CRBMs), 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.

UR - https://research.tue.nl/en/publications/big-iot-data-mining-for-real-time-energy-disaggregation-in-buildi-2

M3 - Conference contribution

BT - Benelearn 2017

A2 - Duivesteijn, Wouter

A2 - Pechenizkiy, Mykola

A2 - Fletcher, George

A2 - Menkovski, Vlado

A2 - Postma, Eric

A2 - Vanschoren, Joaquin

A2 - van der Putten, Pete

PB - TU/e

CY - Eindhoven

T2 - 26th Benelux Conference on Machine Learning, Benelearn 2017

Y2 - 9 June 2017 through 10 June 2017

ER -

Big IoT data mining for real-time energy disaggregation in buildings (extended abstract)

Abstract

Conference

UN SDGs

Access to Document

Other files and links

Cite this