On the performance of meta-models in building design optimization

Prada, Alessandro; Gasparella, Andrea; Baggio, Paolo

doi:10.1016/j.apenergy.2018.04.129

Cited by 59 publications

(22 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A review and comparison of model types are found in [16] and [15] . Prada et al [72] looked at the suitability of different types of surrogate models for evolutionary building design optimisation. A comprehensive review of the use of data for building design may be found in [5] .…”

Section: Previous Reviewsmentioning

confidence: 99%

Surrogate modelling for sustainable building design – A review

Westermann

Evins

2019

Energy and Buildings

196

View full text Add to dashboard Cite

Building design processes are dynamic and complex. The context of a building project is manifold and depends on the cultural context, climatic conditions and personal design preferences. Many stakeholders may be involved in deciding between a large space of possible designs defined by a set of influential design parameters. Building performance simulation is the state-of-the-art way to provide estimates of the energy and environmental performance of various design alternatives. However, setting up a simulation model can be labour intensive and evaluating it can be computationally costly. As a consequence, building simulations often occur towards the end of the design process instead of being an active component in design processes. This observation and the growing availability of machine learning algorithms as an aid to exploring analytical problems has lead to the development of surrogate models. The idea of surrogate models is to learn from a high-fidelity counterpart, here a building simulation model, by emulating the simulation outputs given the simulation inputs. The key advantage is their computational efficiency. They can produce performance estimates for hundreds of thousands of building designs within seconds. This has great potential to innovate the field. Instead of only being able to assess a few specific designs, entire regions of the design space can be explored, or instantaneous feedback on the sustainability of building can be given to architects during design sessions. I would like to express my thank to my supervisor, Dr. Ralph Evins, for giving me the opportunity to join him and the young Energy and Cities group in beautiful Victoria, for his guidance, and for his support to accommodate any of my plans. A special thanks goes to the rapidly growing team, which always had an open ear for my research ideas and brought in valuable input for my work. Especially I would like to thank Gaby Baasch, David Rulff, Matthias Welzel, David Fritzsche, Kevin Cant, Theo Christiaanse, and Gaëlle Faure. I also owe many thanks to Professor Arno Schlüter and the A/S research group at the Institute for Technology in Architecture, ETH Zurich, for hosting me during my visits in Zurich. Finally, I would like to express great gratitude to limitless support off-campus. Thanks to Chris Wood, Miguel Alvarez, Toby Cotton, Aurélien Liné, Claire Remington, the UVIC Field Hockey team and all the others. Thanks to my sisters and parents. Thank you, Fredi.

show abstract

Section: Previous Reviewsmentioning

confidence: 99%

Surrogate modelling for sustainable building design – A review

Westermann

Evins

2019

Energy and Buildings

196

View full text Add to dashboard Cite

show abstract

“…The optimization method based on meta-models has been widely used in related academic research [38]. With the help of machine learning algorithms, alternative models of simulation software for each performance can be separately constructed, and participate in optimization as the fitness function of the optimization algorithm [39].…”

Section: Multi-objective Optimization Methodsmentioning

confidence: 99%

Impact of adjustment strategies on building design process in different climates oriented by multiple performance

Wang

Feng

2020

Applied Energy

View full text Add to dashboard Cite

The effect of the adjustment strategy on the building design process is analyzed. • Uncertainty analysis, sensitivity analysis, performance optimization are involved. • Shading, window ventilation, and dimming are considered in the adjustment strategy. • Energy, thermal and visual comfort are included in building performance. • Various climate zones in China are compared given the impact of climate.

show abstract

“…Regarding the design parameters used as inputs, variables of building geometry, windows, and material properties are mainly used [122]. The consumed time is significantly reduced using the surrogate model in comparison to the simulation-based method [127]. For instance, in [128], a surrogate based optimisation method was developed combining ANN and genetic algorithm to help retrofit existing buildings.…”

Section: • Offline Simulationmentioning

confidence: 99%

Gaps and requirements for automatic generation of space layouts with optimised energy performance

Turrin

Jansen

et al. 2020

Automation in Construction

View full text Add to dashboard Cite

Due to the critical need for reducing carbon emissions, the demand for energy-efficient building design is urgent. Studies have shown that space layouts affect energy performance considerably. Energy performance optimisation is able to improve energy performance significantly. However, in order to apply energy performance optimisation to space layouts (EPO), abundant layout alternatives are needed. With the development of computational methods, automatic generation of space layouts (GSL) helps to generate abundant layouts quickly. Therefore, combining GSL with EPO is expected to be greatly helpful for energy-efficient design. This paper investigates 10 relevant studies combining GSL and EPO and analyses their gaps. Furtherly, we extend the analysis to the research on GSL and EPO. 7 GSL methods are categorised and evaluated based on 66 studies, and the requirements for the combination with optimisation are inspected. Regarding EPO, the requirements for energy performance assessment and optimisation are analysed.

show abstract

On the performance of meta-models in building design optimization

Cited by 59 publications

References 54 publications

Surrogate modelling for sustainable building design – A review

Surrogate modelling for sustainable building design – A review

Impact of adjustment strategies on building design process in different climates oriented by multiple performance

Gaps and requirements for automatic generation of space layouts with optimised energy performance

Contact Info

Product

Resources

About