Deep learning methods for on-line flexibility prediction and optimal resource allocation in smart buildings

E. Mocanu, H.P. Nguyen, M. Gibescu, J.G. Slootweg

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

143 Downloads (Pure)

Abstract

Unprecedented high volume of data is available with the upward growth of the advanced metering infrastructure. Because the built environment is the largest user of electricity, a deeper look at building energy consumption holds promise for helping to achieve overall optimization of the energy system. Yet, a knowledge transfer from the fusion of extensive data is under development. To overcome this limitation, in the big data era, more and more machine learning methods appear to be suitable to automatically extract, predict and optimized building electrical patterns by performing successive transformation of the data. More recently, there has been a revival of interest in deep learning methods as the most advance on-line solutions for large-scale and real databases. Enabling real-time applications from the high level of aggregation in the smart grid will put end-users in position to change their consumption patterns, offering useful benefits for the system as a whole.
Original languageEnglish
Title of host publicationProceedings of 2017 IEEE Power and Energy Society General Meeting , 16-20 July 2017, Chicago, Illinois
Place of PublicationPiscataway
PublisherInstitute of Electrical and Electronics Engineers
Publication statusPublished - Jul 2017
Event2017 IEEE Power and Energy Society General Meeting, PESGM 2017 - Chicago, IL USA, Chicago, United States
Duration: 16 Jul 201720 Jul 2017
http://www.pes-gm.org/2017
http://www.pes-gm.org/2017/

Conference

Conference2017 IEEE Power and Energy Society General Meeting, PESGM 2017
Abbreviated titlePESGM 2017
CountryUnited States
CityChicago
Period16/07/1720/07/17
Internet address

Fingerprint

Advanced metering infrastructures
Intelligent buildings
Resource allocation
Learning systems
Fusion reactions
Energy utilization
Agglomeration
Electricity
Deep learning
Big data

Bibliographical note

Sheet presentation

Cite this

Mocanu, E., Nguyen, H. P., Gibescu, M., & Slootweg, J. G. (2017). Deep learning methods for on-line flexibility prediction and optimal resource allocation in smart buildings. In Proceedings of 2017 IEEE Power and Energy Society General Meeting , 16-20 July 2017, Chicago, Illinois Piscataway: Institute of Electrical and Electronics Engineers.
Mocanu, E. ; Nguyen, H.P. ; Gibescu, M. ; Slootweg, J.G. / Deep learning methods for on-line flexibility prediction and optimal resource allocation in smart buildings. Proceedings of 2017 IEEE Power and Energy Society General Meeting , 16-20 July 2017, Chicago, Illinois. Piscataway : Institute of Electrical and Electronics Engineers, 2017.
@inproceedings{a611a64e48c6407dab62b2d39dd12b80,
title = "Deep learning methods for on-line flexibility prediction and optimal resource allocation in smart buildings",
abstract = "Unprecedented high volume of data is available with the upward growth of the advanced metering infrastructure. Because the built environment is the largest user of electricity, a deeper look at building energy consumption holds promise for helping to achieve overall optimization of the energy system. Yet, a knowledge transfer from the fusion of extensive data is under development. To overcome this limitation, in the big data era, more and more machine learning methods appear to be suitable to automatically extract, predict and optimized building electrical patterns by performing successive transformation of the data. More recently, there has been a revival of interest in deep learning methods as the most advance on-line solutions for large-scale and real databases. Enabling real-time applications from the high level of aggregation in the smart grid will put end-users in position to change their consumption patterns, offering useful benefits for the system as a whole.",
author = "E. Mocanu and H.P. Nguyen and M. Gibescu and J.G. Slootweg",
note = "Sheet presentation",
year = "2017",
month = "7",
language = "English",
booktitle = "Proceedings of 2017 IEEE Power and Energy Society General Meeting , 16-20 July 2017, Chicago, Illinois",
publisher = "Institute of Electrical and Electronics Engineers",
address = "United States",

}

Mocanu, E, Nguyen, HP, Gibescu, M & Slootweg, JG 2017, Deep learning methods for on-line flexibility prediction and optimal resource allocation in smart buildings. in Proceedings of 2017 IEEE Power and Energy Society General Meeting , 16-20 July 2017, Chicago, Illinois. Institute of Electrical and Electronics Engineers, Piscataway, 2017 IEEE Power and Energy Society General Meeting, PESGM 2017, Chicago, United States, 16/07/17.

Deep learning methods for on-line flexibility prediction and optimal resource allocation in smart buildings. / Mocanu, E.; Nguyen, H.P.; Gibescu, M.; Slootweg, J.G.

Proceedings of 2017 IEEE Power and Energy Society General Meeting , 16-20 July 2017, Chicago, Illinois. Piscataway : Institute of Electrical and Electronics Engineers, 2017.

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

TY - GEN

T1 - Deep learning methods for on-line flexibility prediction and optimal resource allocation in smart buildings

AU - Mocanu, E.

AU - Nguyen, H.P.

AU - Gibescu, M.

AU - Slootweg, J.G.

N1 - Sheet presentation

PY - 2017/7

Y1 - 2017/7

N2 - Unprecedented high volume of data is available with the upward growth of the advanced metering infrastructure. Because the built environment is the largest user of electricity, a deeper look at building energy consumption holds promise for helping to achieve overall optimization of the energy system. Yet, a knowledge transfer from the fusion of extensive data is under development. To overcome this limitation, in the big data era, more and more machine learning methods appear to be suitable to automatically extract, predict and optimized building electrical patterns by performing successive transformation of the data. More recently, there has been a revival of interest in deep learning methods as the most advance on-line solutions for large-scale and real databases. Enabling real-time applications from the high level of aggregation in the smart grid will put end-users in position to change their consumption patterns, offering useful benefits for the system as a whole.

AB - Unprecedented high volume of data is available with the upward growth of the advanced metering infrastructure. Because the built environment is the largest user of electricity, a deeper look at building energy consumption holds promise for helping to achieve overall optimization of the energy system. Yet, a knowledge transfer from the fusion of extensive data is under development. To overcome this limitation, in the big data era, more and more machine learning methods appear to be suitable to automatically extract, predict and optimized building electrical patterns by performing successive transformation of the data. More recently, there has been a revival of interest in deep learning methods as the most advance on-line solutions for large-scale and real databases. Enabling real-time applications from the high level of aggregation in the smart grid will put end-users in position to change their consumption patterns, offering useful benefits for the system as a whole.

M3 - Conference contribution

BT - Proceedings of 2017 IEEE Power and Energy Society General Meeting , 16-20 July 2017, Chicago, Illinois

PB - Institute of Electrical and Electronics Engineers

CY - Piscataway

ER -

Mocanu E, Nguyen HP, Gibescu M, Slootweg JG. Deep learning methods for on-line flexibility prediction and optimal resource allocation in smart buildings. In Proceedings of 2017 IEEE Power and Energy Society General Meeting , 16-20 July 2017, Chicago, Illinois. Piscataway: Institute of Electrical and Electronics Engineers. 2017