Embedding intelligence to control adaptive building envelopes

Favoino, Fabio; Baracani, Manuela; Giovannini, Luigi; Gennaro, Giovanni; Goia, Francesco

doi:10.1016/b978-0-12-822477-9.00007-3

“…For example, optimizing the light environment and improving indoor energy consumption simultaneously (Shi et al, 2020), minimizing cooling load, and maximizing daylighting performance in summer (Kim & Clayton, 2020). The operation of DF for multi-objective optimization requires a comprehensive calculation of environmental parameters to achieve an optimal solution for a certain period, creating an intelligent control system to cope with the complexity is an essential research direction (Böke et al, 2019;Favoino et al, 2022). Current researches on DF mainly use the Rhino/Grasshopper platform to build a parametric model (González & Fiorito, 2015), which could be combined with modules such as Ladybug and Honeybee to simulate, evaluate, and optimize the performance of the façade (Roudsari & Pak, 2013).…”

Section: Energy and Lighting Simulationmentioning

confidence: 99%

Optimising the Control Strategies for Performance-Driven Dynamic Building Facades Using Machine Learning

Li¹,

Huang²,

Yao³

2023

CAADRIA Proceedings

0

View full text Add to dashboard Cite

The balance between energy consumption and indoor environmental comfort is a continuing research topic in building energy efficiency. The dynamic façades (DF) are considered a practical approach to separate the sun and create more shadows for buildings with curtain walls, reducing the HVAC system's energy consumption. However, the design complexity of the DF leads to a time-consuming simulation process, making it difficult to modify the design parameters in the early design stage efficiently. This paper provides optimized control strategies for four dynamic façade prototypes. We use explainable machine learning to explore the relationship between design parameters of DF and indoor performance, including Energy Use Intensity (EUI) and Daylight Glare Probability (DGP). We deployed the trained model in optimizing the rotation angle of DF per hour on a typical day to minimize the EUI and DGP of the target room. The results show that the rotation angle of DF significantly affects the DGP, whereas the room size affects EUI performance more than rotation angles. Optimized control strategies of DF bring a maxim 13.5% EUI decrease and 51.7% reduction of DGP. Our work provides a generalizable design flow for performance-driven dynamic skin design.

show abstract

“…The operation of DF for multi-objective optimization requires a comprehensive calculation of environmental parameters to achieve an optimal solution for a certain period, creating an intelligent control system to cope with the complexity is an essential research direction (Böke et al, 2019;Favoino et al, 2022). Current researches on DF mainly use the Rhino/Grasshopper platform to build a parametric model (González & Fiorito, 2015), which could be combined with modules such as Ladybug and Honeybee to simulate, evaluate, and optimize the performance of the façade (Roudsari & Pak, 2013).…”

Section: Energy and Lighting Simulationmentioning

confidence: 99%

Proceedings of the 28th Conference on Computer Aided Architectural Design Research in Asia (CAADRIA) [Volume 1]

2023

CAADRIA Proceedings

0

View full text Add to dashboard Cite

The papers are also available online at the open access cumulative database CumInCAD (http://papers.cumincad.org).The proceedings are the outcome of an extensive collaborative and voluntary effort between the International Reviewing Committee and Paper Selection Committee, with the former consisting of 140 reviewers from over 30 different countries working across the globe. It marks another year of growing quality and strength in the history of CAADRIA. The papers in this publication have been selected through a two-stage double-blind peer review process. Calls for papers in July of 2022 resulted in the submission of 450 abstracts from 37 countries, of which 292 were invited for further development as full paper submission. At least 3 to 4 international reviewers were assigned to conduct a double-blind review of each of the submitted papers. Following the reviewers' recommendation and the Paper Selection Committee's evaluation, 139 papers were finally accepted in February of 2023 for their inclusion in the publication and presentation at the conference.We congratulate the authors for their accomplishment. Our sincere thanks go out to our international reviewers, who volunteered their valuable time and effort. We also thank the organising team in CEPT University for developing the 2023 CAADRIA Conference as a strong collaborative effort between academic institutions, industry and practice. We thank Gabriel Wurzer for his relentless support with customizing the submission and review system to the needs of CAADRIA from the abstract submission all the way to production. Finally, I sincerely thank the CAADRIA community for offering me the opportunity and honour to serve as the chair of the Paper Selection Committee during the past 1 year of preparation.

show abstract

“…The operation of DF for multi-objective optimization requires a comprehensive calculation of environmental parameters to achieve an optimal solution for a certain period, creating an intelligent control system to cope with the complexity is an essential research direction (Böke et al, 2019;Favoino et al, 2022). Current researches on DF mainly use the Rhino/Grasshopper platform to build a parametric model (González & Fiorito, 2015), which could be combined with modules such as Ladybug and Honeybee to simulate, evaluate, and optimize the performance of the façade (Roudsari & Pak, 2013).…”

Section: Energy and Lighting Simulationmentioning

confidence: 99%

CAADRIA 2023: HUMAN-CENTRIC - Volume 1

Koh,

Reinhardt,

Makki

et al. 2023

CAADRIA Proceedings

0

View full text Add to dashboard Cite

The papers are also available online at the open access cumulative database CumInCAD (http://papers.cumincad.org).The proceedings are the outcome of an extensive collaborative and voluntary effort between the International Reviewing Committee and Paper Selection Committee, with the former consisting of 140 reviewers from over 30 different countries working across the globe. It marks another year of growing quality and strength in the history of CAADRIA. The papers in this publication have been selected through a two-stage double-blind peer review process. Calls for papers in July of 2022 resulted in the submission of 450 abstracts from 37 countries, of which 292 were invited for further development as full paper submission. At least 3 to 4 international reviewers were assigned to conduct a double-blind review of each of the submitted papers. Following the reviewers' recommendation and the Paper Selection Committee's evaluation, 139 papers were finally accepted in February of 2023 for their inclusion in the publication and presentation at the conference.We congratulate the authors for their accomplishment. Our sincere thanks go out to our international reviewers, who volunteered their valuable time and effort. We also thank the organising team in CEPT University for developing the 2023 CAADRIA Conference as a strong collaborative effort between academic institutions, industry and practice. We thank Gabriel Wurzer for his relentless support with customizing the submission and review system to the needs of CAADRIA from the abstract submission all the way to production. Finally, I sincerely thank the CAADRIA community for offering me the opportunity and honour to serve as the chair of the Paper Selection Committee during the past 1 year of preparation.

show abstract

Embedding intelligence to control adaptive building envelopes

Cited by 7 publications

References 69 publications

Optimising the Control Strategies for Performance-Driven Dynamic Building Facades Using Machine Learning

Optimising the Control Strategies for Performance-Driven Dynamic Building Facades Using Machine Learning

Proceedings of the 28th Conference on Computer Aided Architectural Design Research in Asia (CAADRIA) [Volume 1]

CAADRIA 2023: HUMAN-CENTRIC - Volume 1

Contact Info

Product

Resources

About