Applying Deep Learning and Databases for Energy-efficient Architectural Design Abstract

Manav Mahan Singh; Patricia Schneider-Marin; Hannes Harter; Werner Lang; Philipp Florian Geyer

Details

Original language	English
Title of host publication	Anthropologic
Subtitle of host publication	Architecture and Fabrication in the cognitive age
Editors	Liss C. Werner, Dietmar Koering
Place of Publication	Berlin
Pages	79-87
Number of pages	9
Publication status	Published - 2020
Externally published	Yes
Event	38th Conference on Education and Research in Computer Aided Architectural Design in Europe, eCAADe 2020 - Berlin, Germany Duration: 16 Sept 2020 → 17 Sept 2020

Publication series

Name	Proceedings of the International Conference on Education and Research in Computer Aided Architectural Design in Europe
Volume	2
ISSN (Print)	2684-1843

Abstract

The reduction of energy consumption of buildings requires consideration in early design phases. However, modelling and computation time required for dynamic energy simulations makes them inappropriate in the early phases. This paper presents a performance prediction approach for these phases that is embedded in a multi-level-of-development modelling approach. First, parametric pre-trained modular deep learning components are embedded in the building elements. The energy performance is predicted by composing these components. Second, embodied energy assessment is performed by extracting the information from a database. A calculation module queries the database and calculates the embodied energy. Both, embodied and operational, energy are assembled to predict lifecycle energy demand. The method has been implemented prototypically in a digital modelling environment Revit. A case study serves to demonstrate the application process, the user interaction and the information flows. It shows energy prediction in early design phases to enhance the environmental performance of the building.

Keywords

BIM, Early Design Phases, Embodied Energy, Life-cycle Energy Demand, Operational Energy

ASJC Scopus subject areas

Computer Science(all)
Computer Graphics and Computer-Aided Design
Social Sciences(all)
Education
Engineering(all)
Architecture

Sustainable Development Goals

SDG 7 - Affordable and Clean Energy

Cite this

Applying Deep Learning and Databases for Energy-efficient Architectural Design Abstract. / Singh, Manav Mahan; Schneider-Marin, Patricia; Harter, Hannes et al.
Anthropologic: Architecture and Fabrication in the cognitive age. ed. / Liss C. Werner; Dietmar Koering. Berlin, 2020. p. 79-87 (Proceedings of the International Conference on Education and Research in Computer Aided Architectural Design in Europe; Vol. 2).

Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review

Singh, MM, Schneider-Marin, P, Harter, H, Lang, W & Geyer, PF 2020, Applying Deep Learning and Databases for Energy-efficient Architectural Design Abstract. in LC Werner & D Koering (eds), Anthropologic: Architecture and Fabrication in the cognitive age. Proceedings of the International Conference on Education and Research in Computer Aided Architectural Design in Europe, vol. 2, Berlin, pp. 79-87, 38th Conference on Education and Research in Computer Aided Architectural Design in Europe, eCAADe 2020, Berlin, Germany, 16 Sept 2020.

Singh, M. M., Schneider-Marin, P., Harter, H., Lang, W., & Geyer, P. F. (2020). Applying Deep Learning and Databases for Energy-efficient Architectural Design Abstract. In L. C. Werner, & D. Koering (Eds.), Anthropologic: Architecture and Fabrication in the cognitive age (pp. 79-87). (Proceedings of the International Conference on Education and Research in Computer Aided Architectural Design in Europe; Vol. 2)..

Singh MM, Schneider-Marin P, Harter H, Lang W, Geyer PF. Applying Deep Learning and Databases for Energy-efficient Architectural Design Abstract. In Werner LC, Koering D, editors, Anthropologic: Architecture and Fabrication in the cognitive age. Berlin. 2020. p. 79-87. (Proceedings of the International Conference on Education and Research in Computer Aided Architectural Design in Europe).

Singh, Manav Mahan ; Schneider-Marin, Patricia ; Harter, Hannes et al. / Applying Deep Learning and Databases for Energy-efficient Architectural Design Abstract. Anthropologic: Architecture and Fabrication in the cognitive age. editor / Liss C. Werner ; Dietmar Koering. Berlin, 2020. pp. 79-87 (Proceedings of the International Conference on Education and Research in Computer Aided Architectural Design in Europe).

Download

@inproceedings{5445898c3f6a4791abd2f6660a99e848,

title = "Applying Deep Learning and Databases for Energy-efficient Architectural Design Abstract",

abstract = "The reduction of energy consumption of buildings requires consideration in early design phases. However, modelling and computation time required for dynamic energy simulations makes them inappropriate in the early phases. This paper presents a performance prediction approach for these phases that is embedded in a multi-level-of-development modelling approach. First, parametric pre-trained modular deep learning components are embedded in the building elements. The energy performance is predicted by composing these components. Second, embodied energy assessment is performed by extracting the information from a database. A calculation module queries the database and calculates the embodied energy. Both, embodied and operational, energy are assembled to predict lifecycle energy demand. The method has been implemented prototypically in a digital modelling environment Revit. A case study serves to demonstrate the application process, the user interaction and the information flows. It shows energy prediction in early design phases to enhance the environmental performance of the building.",

keywords = "BIM, Early Design Phases, Embodied Energy, Life-cycle Energy Demand, Operational Energy",

author = "Singh, {Manav Mahan} and Patricia Schneider-Marin and Hannes Harter and Werner Lang and Geyer, {Philipp Florian}",

note = "Publisher Copyright: {\textcopyright} 2020, Education and research in Computer Aided Architectural Design in Europe. All rights reserved.; 38th Conference on Education and Research in Computer Aided Architectural Design in Europe, eCAADe 2020 ; Conference date: 16-09-2020 Through 17-09-2020",

year = "2020",

language = "English",

isbn = "9789491207211",

series = "Proceedings of the International Conference on Education and Research in Computer Aided Architectural Design in Europe",

pages = "79--87",

editor = "Werner, {Liss C.} and Dietmar Koering",

booktitle = "Anthropologic",

}

Download

TY - GEN

T1 - Applying Deep Learning and Databases for Energy-efficient Architectural Design Abstract

AU - Singh, Manav Mahan

AU - Schneider-Marin, Patricia

AU - Harter, Hannes

AU - Lang, Werner

AU - Geyer, Philipp Florian

PY - 2020

Y1 - 2020

N2 - The reduction of energy consumption of buildings requires consideration in early design phases. However, modelling and computation time required for dynamic energy simulations makes them inappropriate in the early phases. This paper presents a performance prediction approach for these phases that is embedded in a multi-level-of-development modelling approach. First, parametric pre-trained modular deep learning components are embedded in the building elements. The energy performance is predicted by composing these components. Second, embodied energy assessment is performed by extracting the information from a database. A calculation module queries the database and calculates the embodied energy. Both, embodied and operational, energy are assembled to predict lifecycle energy demand. The method has been implemented prototypically in a digital modelling environment Revit. A case study serves to demonstrate the application process, the user interaction and the information flows. It shows energy prediction in early design phases to enhance the environmental performance of the building.

AB - The reduction of energy consumption of buildings requires consideration in early design phases. However, modelling and computation time required for dynamic energy simulations makes them inappropriate in the early phases. This paper presents a performance prediction approach for these phases that is embedded in a multi-level-of-development modelling approach. First, parametric pre-trained modular deep learning components are embedded in the building elements. The energy performance is predicted by composing these components. Second, embodied energy assessment is performed by extracting the information from a database. A calculation module queries the database and calculates the embodied energy. Both, embodied and operational, energy are assembled to predict lifecycle energy demand. The method has been implemented prototypically in a digital modelling environment Revit. A case study serves to demonstrate the application process, the user interaction and the information flows. It shows energy prediction in early design phases to enhance the environmental performance of the building.

KW - BIM

KW - Early Design Phases

KW - Embodied Energy

KW - Life-cycle Energy Demand

KW - Operational Energy

UR - http://www.scopus.com/inward/record.url?scp=85123839031&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85123839031

SN - 9789491207211

T3 - Proceedings of the International Conference on Education and Research in Computer Aided Architectural Design in Europe

SP - 79

EP - 87

BT - Anthropologic

A2 - Werner, Liss C.

A2 - Koering, Dietmar

CY - Berlin

T2 - 38th Conference on Education and Research in Computer Aided Architectural Design in Europe, eCAADe 2020

Y2 - 16 September 2020 through 17 September 2020

ER -

Research@Leibniz University