Collaborative learning for classification and prediction of building energy flexibility

Anil Kumar, Elena Mocanu, Muhammad Babar, Phuong H. Nguyen

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

35 Downloads (Pure)

Abstract

In this paper we propose an simple digital learning platform for flexible energy detection using data with fine granularity. The platform is empowered with artificially intelligent methods aiming to quantify the uncertainty of building energy consumption at building level, as well as at the aggregated level. Two major learning tasks are perform in this context: prediction and classification. Firstly, the building energy prediction with various time steps resolution are perform using methods such as Fully Connected Neural Networks (FCNN), Long short-term memory (LSTM), and Decision Trees (DT). Secondly, a Support Vector Machine (SVM) method is used to unlock the building energy flexibility by performing classification assuming three different levels of flexibility. Further on, a collaborative task is integrate within the platform to improve the multi-class classification accuracy. Through the end, we argue that this approach can be considered a solid integrated and automated basic block able to incorporate future AI models in (near) real-time to explore the benefits at the synergy between built environment and emerging smart grid technologies and applications.
Original languageEnglish
Title of host publication9th IEEE PES Innovative Smart Grid Technology Conference Europe
PublisherIEEE
Number of pages5
Publication statusAccepted/In press - 2019
Event2019 IEEE PES Innovative Smart Grid Technologies Europe, ISGT Europe - University POLITEHNICA, Bucharest, Romania
Duration: 29 Sep 20192 Oct 2019
http://sites.ieee.org/isgt-europe-2019/

Conference

Conference2019 IEEE PES Innovative Smart Grid Technologies Europe, ISGT Europe
Abbreviated titleISGT 2019
CountryRomania
CityBucharest
Period29/09/192/10/19
Internet address

Fingerprint

Decision trees
Support vector machines
Energy utilization
Neural networks
Long short-term memory
Uncertainty

Cite this

Kumar, A., Mocanu, E., Babar, M., & Nguyen, P. H. (Accepted/In press). Collaborative learning for classification and prediction of building energy flexibility. In 9th IEEE PES Innovative Smart Grid Technology Conference Europe IEEE.
Kumar, Anil ; Mocanu, Elena ; Babar, Muhammad ; Nguyen, Phuong H. / Collaborative learning for classification and prediction of building energy flexibility. 9th IEEE PES Innovative Smart Grid Technology Conference Europe. IEEE, 2019.
@inproceedings{516139faeb7b44c5bbb50579d8b45a0b,
title = "Collaborative learning for classification and prediction of building energy flexibility",
abstract = "In this paper we propose an simple digital learning platform for flexible energy detection using data with fine granularity. The platform is empowered with artificially intelligent methods aiming to quantify the uncertainty of building energy consumption at building level, as well as at the aggregated level. Two major learning tasks are perform in this context: prediction and classification. Firstly, the building energy prediction with various time steps resolution are perform using methods such as Fully Connected Neural Networks (FCNN), Long short-term memory (LSTM), and Decision Trees (DT). Secondly, a Support Vector Machine (SVM) method is used to unlock the building energy flexibility by performing classification assuming three different levels of flexibility. Further on, a collaborative task is integrate within the platform to improve the multi-class classification accuracy. Through the end, we argue that this approach can be considered a solid integrated and automated basic block able to incorporate future AI models in (near) real-time to explore the benefits at the synergy between built environment and emerging smart grid technologies and applications.",
author = "Anil Kumar and Elena Mocanu and Muhammad Babar and Nguyen, {Phuong H.}",
year = "2019",
language = "English",
booktitle = "9th IEEE PES Innovative Smart Grid Technology Conference Europe",
publisher = "IEEE",
address = "United States",

}

Kumar, A, Mocanu, E, Babar, M & Nguyen, PH 2019, Collaborative learning for classification and prediction of building energy flexibility. in 9th IEEE PES Innovative Smart Grid Technology Conference Europe. IEEE, 2019 IEEE PES Innovative Smart Grid Technologies Europe, ISGT Europe, Bucharest, Romania, 29/09/19.

Collaborative learning for classification and prediction of building energy flexibility. / Kumar, Anil; Mocanu, Elena ; Babar, Muhammad; Nguyen, Phuong H.

9th IEEE PES Innovative Smart Grid Technology Conference Europe. IEEE, 2019.

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

TY - GEN

T1 - Collaborative learning for classification and prediction of building energy flexibility

AU - Kumar, Anil

AU - Mocanu, Elena

AU - Babar, Muhammad

AU - Nguyen, Phuong H.

PY - 2019

Y1 - 2019

N2 - In this paper we propose an simple digital learning platform for flexible energy detection using data with fine granularity. The platform is empowered with artificially intelligent methods aiming to quantify the uncertainty of building energy consumption at building level, as well as at the aggregated level. Two major learning tasks are perform in this context: prediction and classification. Firstly, the building energy prediction with various time steps resolution are perform using methods such as Fully Connected Neural Networks (FCNN), Long short-term memory (LSTM), and Decision Trees (DT). Secondly, a Support Vector Machine (SVM) method is used to unlock the building energy flexibility by performing classification assuming three different levels of flexibility. Further on, a collaborative task is integrate within the platform to improve the multi-class classification accuracy. Through the end, we argue that this approach can be considered a solid integrated and automated basic block able to incorporate future AI models in (near) real-time to explore the benefits at the synergy between built environment and emerging smart grid technologies and applications.

AB - In this paper we propose an simple digital learning platform for flexible energy detection using data with fine granularity. The platform is empowered with artificially intelligent methods aiming to quantify the uncertainty of building energy consumption at building level, as well as at the aggregated level. Two major learning tasks are perform in this context: prediction and classification. Firstly, the building energy prediction with various time steps resolution are perform using methods such as Fully Connected Neural Networks (FCNN), Long short-term memory (LSTM), and Decision Trees (DT). Secondly, a Support Vector Machine (SVM) method is used to unlock the building energy flexibility by performing classification assuming three different levels of flexibility. Further on, a collaborative task is integrate within the platform to improve the multi-class classification accuracy. Through the end, we argue that this approach can be considered a solid integrated and automated basic block able to incorporate future AI models in (near) real-time to explore the benefits at the synergy between built environment and emerging smart grid technologies and applications.

M3 - Conference contribution

BT - 9th IEEE PES Innovative Smart Grid Technology Conference Europe

PB - IEEE

ER -

Kumar A, Mocanu E, Babar M, Nguyen PH. Collaborative learning for classification and prediction of building energy flexibility. In 9th IEEE PES Innovative Smart Grid Technology Conference Europe. IEEE. 2019