Applying Deep Learning and Databases for Energy- efficient Architectural Design

Manav Mahan Singh1, Patricia Schneider-Marin2, Hannes Harter3, Werner Lang4, Philipp Geyer5 1KU Leuven 2,3,4TU Munich 5TU Berlin, KU Leuven 1manavmahan.singh@kuleuven.be 2,3,4{patricia.schneider|hannes.harter|w. lang}@tum.de 5geyer@tu-berlin.de 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.

[1]  Philipp Geyer,et al.  Consistent management and evaluation of building models in the early design stages , 2020, J. Inf. Technol. Constr..

[2]  Hannes Harter,et al.  Uncertainty Analysis of Embedded Energy and Greenhouse Gas Emissions Using BIM in Early Design Stages , 2020, Sustainability.

[3]  Philipp Geyer,et al.  Information requirements for multi-level-of-development BIM using sensitivity analysis for energy performance , 2020, Adv. Eng. Informatics.

[4]  Philipp Geyer,et al.  Component-based machine learning for performance prediction in building design , 2018, Applied Energy.

[5]  Pieter de Wilde,et al.  A review of uncertainty analysis in building energy assessment , 2018, Renewable and Sustainable Energy Reviews.

[6]  Philipp Geyer,et al.  Component-Based Machine Learning for Energy Performance Prediction by MultiLOD Models in the Early Phases of Building Design , 2018, EG-ICE.

[7]  Philipp Geyer,et al.  Statistical Decision Assistance for Determining Energy-Efficient Options In Building Design Under Uncertainty , 2018, EG-ICE.

[8]  Manish K. Dixit,et al.  Life cycle embodied energy analysis of residential buildings: A review of literature to investigate embodied energy parameters , 2017 .

[9]  Timothy L. Hemsath,et al.  Sensitivity analysis evaluating basic building geometry's effect on energy use , 2015 .

[10]  Staf Roels,et al.  Probabilistic design and analysis of building performances: methodology and application example , 2014 .

[11]  Young Jin Kim,et al.  BIM interface for full vs. semi-automated building energy simulation , 2014 .

[12]  Gregory W. Corder,et al.  Nonparametric Statistics for Non-Statisticians: A Step-by-Step Approach , 2009 .