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 proceedingConference contributionAcademicpeer-review

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 languageEnglish
Title of host publicationBenelearn 2017
Subtitle of host publicationProceedings of the Twenty-Sixth Benelux Conference on Machine Learning
EditorsWouter Duivesteijn, Mykola Pechenizkiy, George Fletcher, Vlado Menkovski, Eric Postma, Joaquin Vanschoren, Pete van der Putten
Place of PublicationEindhoven
PublisherTU/e
Publication statusPublished - 10 Jun 2017
Event26th Benelux Conference on Machine Learning, Benelearn 2017 - Eindhoven University of Technology, Eindhoven, Netherlands
Duration: 9 Jun 201710 Jun 2017
Conference number: 26

Conference

Conference26th Benelux Conference on Machine Learning, Benelearn 2017
Abbreviated titleBenelearn
CountryNetherlands
CityEindhoven
Period9/06/1710/06/17

Fingerprint Dive into the research topics of 'Big IoT data mining for real-time energy disaggregation in buildings (extended abstract)'. Together they form a unique fingerprint.

Cite this