Application of intelligent algorithms for residential building energy performance rating prediction

Usman Ali; Mohammad Haris Shamsi; Fawaz Alshehri; Eleni Mangina; James O'Donnell

Application of intelligent algorithms for residential building energy performance rating prediction

Usman Ali
, Mohammad Haris Shamsi
, Fawaz Alshehri
, Eleni Mangina
, James O'Donnell

School of Mechanical and Materials Engineering
University College Dublin

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

Abstract

Energy Performance Certificates (EPC) provide an indication of buildings' energy use. The creation of an EPC for individual building requires information surveys. Hence, these ratings are typically non-existent for entire building stock. This paper addresses these information gaps using machine-learning models. Developed models were evaluated with Irish EPC data that included approximately 650,000 residential buildings with 199 inputs variables. Results indicate that the deep learning algorithm produces results with highest accuracy level of 88% when only 82 input variables are available. This identified approach will allow stakeholders such as authorities, policymakers and urban-planners to determine the EPC rating for rest of the building stock using limited data.

Original language	English
Title of host publication	16th International Conference of the International Building Performance Simulation Association, Building Simulation 2019
Editors	Vincenzo Corrado, Enrico Fabrizio, Andrea Gasparella, Francesco Patuzzi
Publisher	International Building Performance Simulation Association
Pages	3177-3184
Number of pages	8
ISBN (Electronic)	9781713809418
Publication status	Published - 2019
Externally published	Yes
Event	16th International Conference of the International Building Performance Simulation Association, Building Simulation 2019 - Rome, Italy Duration: 2 Sep 2019 → 4 Sep 2019

Publication series

Name	Building Simulation Conference Proceedings
Volume	5
ISSN (Print)	2522-2708

Conference

Conference	16th International Conference of the International Building Performance Simulation Association, Building Simulation 2019
Country/Territory	Italy
City	Rome
Period	2/09/19 → 4/09/19

UN SDGs

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

SDG 7 Affordable and Clean Energy
SDG 12 Responsible Consumption and Production

Cite this

Ali, U., Shamsi, M. H., Alshehri, F., Mangina, E., & O'Donnell, J. (2019). Application of intelligent algorithms for residential building energy performance rating prediction. In V. Corrado, E. Fabrizio, A. Gasparella, & F. Patuzzi (Eds.), 16th International Conference of the International Building Performance Simulation Association, Building Simulation 2019 (pp. 3177-3184). (Building Simulation Conference Proceedings; Vol. 5). International Building Performance Simulation Association.

Ali, Usman ; Shamsi, Mohammad Haris ; Alshehri, Fawaz et al. / Application of intelligent algorithms for residential building energy performance rating prediction. 16th International Conference of the International Building Performance Simulation Association, Building Simulation 2019. editor / Vincenzo Corrado ; Enrico Fabrizio ; Andrea Gasparella ; Francesco Patuzzi. International Building Performance Simulation Association, 2019. pp. 3177-3184 (Building Simulation Conference Proceedings).

@inproceedings{eb4ec9b99d634d65ae14af43c7394d8b,

title = "Application of intelligent algorithms for residential building energy performance rating prediction",

abstract = "Energy Performance Certificates (EPC) provide an indication of buildings' energy use. The creation of an EPC for individual building requires information surveys. Hence, these ratings are typically non-existent for entire building stock. This paper addresses these information gaps using machine-learning models. Developed models were evaluated with Irish EPC data that included approximately 650,000 residential buildings with 199 inputs variables. Results indicate that the deep learning algorithm produces results with highest accuracy level of 88\% when only 82 input variables are available. This identified approach will allow stakeholders such as authorities, policymakers and urban-planners to determine the EPC rating for rest of the building stock using limited data.",

author = "Usman Ali and Shamsi, \{Mohammad Haris\} and Fawaz Alshehri and Eleni Mangina and James O'Donnell",

note = "Publisher Copyright: {\textcopyright} 2019 Building Simulation Conference Proceedings. All rights reserved.; 16th International Conference of the International Building Performance Simulation Association, Building Simulation 2019 ; Conference date: 02-09-2019 Through 04-09-2019",

year = "2019",

language = "English",

series = "Building Simulation Conference Proceedings",

publisher = "International Building Performance Simulation Association",

pages = "3177--3184",

editor = "Vincenzo Corrado and Enrico Fabrizio and Andrea Gasparella and Francesco Patuzzi",

booktitle = "16th International Conference of the International Building Performance Simulation Association, Building Simulation 2019",

}

Ali, U, Shamsi, MH, Alshehri, F, Mangina, E & O'Donnell, J 2019, Application of intelligent algorithms for residential building energy performance rating prediction. in V Corrado, E Fabrizio, A Gasparella & F Patuzzi (eds), 16th International Conference of the International Building Performance Simulation Association, Building Simulation 2019. Building Simulation Conference Proceedings, vol. 5, International Building Performance Simulation Association, pp. 3177-3184, 16th International Conference of the International Building Performance Simulation Association, Building Simulation 2019, Rome, Italy, 2/09/19.

Application of intelligent algorithms for residential building energy performance rating prediction. / Ali, Usman; Shamsi, Mohammad Haris; Alshehri, Fawaz et al.
16th International Conference of the International Building Performance Simulation Association, Building Simulation 2019. ed. / Vincenzo Corrado; Enrico Fabrizio; Andrea Gasparella; Francesco Patuzzi. International Building Performance Simulation Association, 2019. p. 3177-3184 (Building Simulation Conference Proceedings; Vol. 5).

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

TY - GEN

T1 - Application of intelligent algorithms for residential building energy performance rating prediction

AU - Ali, Usman

AU - Shamsi, Mohammad Haris

AU - Alshehri, Fawaz

AU - Mangina, Eleni

AU - O'Donnell, James

PY - 2019

Y1 - 2019

N2 - Energy Performance Certificates (EPC) provide an indication of buildings' energy use. The creation of an EPC for individual building requires information surveys. Hence, these ratings are typically non-existent for entire building stock. This paper addresses these information gaps using machine-learning models. Developed models were evaluated with Irish EPC data that included approximately 650,000 residential buildings with 199 inputs variables. Results indicate that the deep learning algorithm produces results with highest accuracy level of 88% when only 82 input variables are available. This identified approach will allow stakeholders such as authorities, policymakers and urban-planners to determine the EPC rating for rest of the building stock using limited data.

AB - Energy Performance Certificates (EPC) provide an indication of buildings' energy use. The creation of an EPC for individual building requires information surveys. Hence, these ratings are typically non-existent for entire building stock. This paper addresses these information gaps using machine-learning models. Developed models were evaluated with Irish EPC data that included approximately 650,000 residential buildings with 199 inputs variables. Results indicate that the deep learning algorithm produces results with highest accuracy level of 88% when only 82 input variables are available. This identified approach will allow stakeholders such as authorities, policymakers and urban-planners to determine the EPC rating for rest of the building stock using limited data.

UR - https://www.scopus.com/pages/publications/85107343641

M3 - Conference contribution

AN - SCOPUS:85107343641

T3 - Building Simulation Conference Proceedings

SP - 3177

EP - 3184

BT - 16th International Conference of the International Building Performance Simulation Association, Building Simulation 2019

A2 - Corrado, Vincenzo

A2 - Fabrizio, Enrico

A2 - Gasparella, Andrea

A2 - Patuzzi, Francesco

PB - International Building Performance Simulation Association

T2 - 16th International Conference of the International Building Performance Simulation Association, Building Simulation 2019

Y2 - 2 September 2019 through 4 September 2019

ER -

Ali U, Shamsi MH, Alshehri F, Mangina E, O'Donnell J. Application of intelligent algorithms for residential building energy performance rating prediction. In Corrado V, Fabrizio E, Gasparella A, Patuzzi F, editors, 16th International Conference of the International Building Performance Simulation Association, Building Simulation 2019. International Building Performance Simulation Association. 2019. p. 3177-3184. (Building Simulation Conference Proceedings).

Application of intelligent algorithms for residential building energy performance rating prediction

Abstract

Publication series

Conference

UN SDGs

Other files and links

Fingerprint

Cite this