A Design Ranking Method for Many-Objective Evolutionary Optimization

Likai Wang; Do Phuong Bui Tung; Patrick Janssen

doi:10.1007/978-3-031-37189-9_11

A Design Ranking Method for Many-Objective Evolutionary Optimization

Likai Wang^*, Do Phuong Bui Tung, Patrick Janssen

^*Corresponding author for this work

Xi'an Jiaotong-Liverpool University

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

Abstract

This study presents a design ranking method for evolutionary optimization that is aimed to address design optimization problems with many performance-related evaluation metrics. The application of the method consists of three strategies. First, all evaluation scores are expressed as percentages that indicate the proportion of the design achieving acceptable performance. Second, related evaluation scores are grouped, and for each group, a combined score is calculated using a weighted product approach. Third, design populations are evolved using the Pareto optimization of the combined evaluation scores. The combination of the three steps helps designers to define and organize the design evaluation metrics and can also produce optimization results revealing meaningful information. A case study is presented to demonstrate the efficacy of the proposed design ranking method. The relevance of the proposed method to performance-based evolutionary optimization research is also discussed.

Original language	English
Title of host publication	Computer-Aided Architectural Design. INTERCONNECTIONS
Subtitle of host publication	Co-computing Beyond Boundaries - 20th International Conference, CAAD Futures 2023, Selected Papers
Editors	Michela Turrin, Charalampos Andriotis, Azarakhsh Rafiee
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	159-173
Number of pages	15
ISBN (Print)	9783031371882
DOIs	https://doi.org/10.1007/978-3-031-37189-9_11
Publication status	Published - 2023
Event	20th International Conference on Computer-Aided Architectural Design Futures, CAAD Futures 2023 - Delft, Netherlands Duration: 5 Jul 2023 → 7 Jul 2023

Publication series

Name	Communications in Computer and Information Science
Volume	1819 CCIS
ISSN (Print)	1865-0929
ISSN (Electronic)	1865-0937

Conference

Conference	20th International Conference on Computer-Aided Architectural Design Futures, CAAD Futures 2023
Country/Territory	Netherlands
City	Delft
Period	5/07/23 → 7/07/23

Keywords

Architectural Design Optimization
Design Evaluation
Many-Objective Evolutionary Optimization
Performance-based Design

Access to Document

10.1007/978-3-031-37189-9_11

Cite this

Wang, L., Tung, D. P. B., & Janssen, P. (2023). A Design Ranking Method for Many-Objective Evolutionary Optimization. In M. Turrin, C. Andriotis, & A. Rafiee (Eds.), Computer-Aided Architectural Design. INTERCONNECTIONS: Co-computing Beyond Boundaries - 20th International Conference, CAAD Futures 2023, Selected Papers (pp. 159-173). (Communications in Computer and Information Science; Vol. 1819 CCIS). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-031-37189-9_11

Wang, Likai ; Tung, Do Phuong Bui ; Janssen, Patrick. / A Design Ranking Method for Many-Objective Evolutionary Optimization. Computer-Aided Architectural Design. INTERCONNECTIONS: Co-computing Beyond Boundaries - 20th International Conference, CAAD Futures 2023, Selected Papers. editor / Michela Turrin ; Charalampos Andriotis ; Azarakhsh Rafiee. Springer Science and Business Media Deutschland GmbH, 2023. pp. 159-173 (Communications in Computer and Information Science).

@inproceedings{56fc6a44a4334de98644dfa1047a2399,

title = "A Design Ranking Method for Many-Objective Evolutionary Optimization",

abstract = "This study presents a design ranking method for evolutionary optimization that is aimed to address design optimization problems with many performance-related evaluation metrics. The application of the method consists of three strategies. First, all evaluation scores are expressed as percentages that indicate the proportion of the design achieving acceptable performance. Second, related evaluation scores are grouped, and for each group, a combined score is calculated using a weighted product approach. Third, design populations are evolved using the Pareto optimization of the combined evaluation scores. The combination of the three steps helps designers to define and organize the design evaluation metrics and can also produce optimization results revealing meaningful information. A case study is presented to demonstrate the efficacy of the proposed design ranking method. The relevance of the proposed method to performance-based evolutionary optimization research is also discussed.",

keywords = "Architectural Design Optimization, Design Evaluation, Many-Objective Evolutionary Optimization, Performance-based Design",

author = "Likai Wang and Tung, {Do Phuong Bui} and Patrick Janssen",

note = "Funding Information: This work is part of the research project: “Optimization Algorithm for Rapid Sustainable Planning and Design”, supported by Housing Development Board (HDB), Singapore. Publisher Copyright: {\textcopyright} 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.; 20th International Conference on Computer-Aided Architectural Design Futures, CAAD Futures 2023 ; Conference date: 05-07-2023 Through 07-07-2023",

year = "2023",

doi = "10.1007/978-3-031-37189-9_11",

language = "English",

isbn = "9783031371882",

series = "Communications in Computer and Information Science",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "159--173",

editor = "Michela Turrin and Charalampos Andriotis and Azarakhsh Rafiee",

booktitle = "Computer-Aided Architectural Design. INTERCONNECTIONS",

}

Wang, L, Tung, DPB & Janssen, P 2023, A Design Ranking Method for Many-Objective Evolutionary Optimization. in M Turrin, C Andriotis & A Rafiee (eds), Computer-Aided Architectural Design. INTERCONNECTIONS: Co-computing Beyond Boundaries - 20th International Conference, CAAD Futures 2023, Selected Papers. Communications in Computer and Information Science, vol. 1819 CCIS, Springer Science and Business Media Deutschland GmbH, pp. 159-173, 20th International Conference on Computer-Aided Architectural Design Futures, CAAD Futures 2023, Delft, Netherlands, 5/07/23. https://doi.org/10.1007/978-3-031-37189-9_11

A Design Ranking Method for Many-Objective Evolutionary Optimization. / Wang, Likai; Tung, Do Phuong Bui; Janssen, Patrick.
Computer-Aided Architectural Design. INTERCONNECTIONS: Co-computing Beyond Boundaries - 20th International Conference, CAAD Futures 2023, Selected Papers. ed. / Michela Turrin; Charalampos Andriotis; Azarakhsh Rafiee. Springer Science and Business Media Deutschland GmbH, 2023. p. 159-173 (Communications in Computer and Information Science; Vol. 1819 CCIS).

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

TY - GEN

T1 - A Design Ranking Method for Many-Objective Evolutionary Optimization

AU - Wang, Likai

AU - Tung, Do Phuong Bui

AU - Janssen, Patrick

N1 - Funding Information: This work is part of the research project: “Optimization Algorithm for Rapid Sustainable Planning and Design”, supported by Housing Development Board (HDB), Singapore. Publisher Copyright: © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

PY - 2023

Y1 - 2023

N2 - This study presents a design ranking method for evolutionary optimization that is aimed to address design optimization problems with many performance-related evaluation metrics. The application of the method consists of three strategies. First, all evaluation scores are expressed as percentages that indicate the proportion of the design achieving acceptable performance. Second, related evaluation scores are grouped, and for each group, a combined score is calculated using a weighted product approach. Third, design populations are evolved using the Pareto optimization of the combined evaluation scores. The combination of the three steps helps designers to define and organize the design evaluation metrics and can also produce optimization results revealing meaningful information. A case study is presented to demonstrate the efficacy of the proposed design ranking method. The relevance of the proposed method to performance-based evolutionary optimization research is also discussed.

AB - This study presents a design ranking method for evolutionary optimization that is aimed to address design optimization problems with many performance-related evaluation metrics. The application of the method consists of three strategies. First, all evaluation scores are expressed as percentages that indicate the proportion of the design achieving acceptable performance. Second, related evaluation scores are grouped, and for each group, a combined score is calculated using a weighted product approach. Third, design populations are evolved using the Pareto optimization of the combined evaluation scores. The combination of the three steps helps designers to define and organize the design evaluation metrics and can also produce optimization results revealing meaningful information. A case study is presented to demonstrate the efficacy of the proposed design ranking method. The relevance of the proposed method to performance-based evolutionary optimization research is also discussed.

KW - Architectural Design Optimization

KW - Design Evaluation

KW - Many-Objective Evolutionary Optimization

KW - Performance-based Design

UR - http://www.scopus.com/inward/record.url?scp=85169040963&partnerID=8YFLogxK

U2 - 10.1007/978-3-031-37189-9_11

DO - 10.1007/978-3-031-37189-9_11

M3 - Conference Proceeding

AN - SCOPUS:85169040963

SN - 9783031371882

T3 - Communications in Computer and Information Science

SP - 159

EP - 173

BT - Computer-Aided Architectural Design. INTERCONNECTIONS

A2 - Turrin, Michela

A2 - Andriotis, Charalampos

A2 - Rafiee, Azarakhsh

PB - Springer Science and Business Media Deutschland GmbH

T2 - 20th International Conference on Computer-Aided Architectural Design Futures, CAAD Futures 2023

Y2 - 5 July 2023 through 7 July 2023

ER -

Wang L, Tung DPB, Janssen P. A Design Ranking Method for Many-Objective Evolutionary Optimization. In Turrin M, Andriotis C, Rafiee A, editors, Computer-Aided Architectural Design. INTERCONNECTIONS: Co-computing Beyond Boundaries - 20th International Conference, CAAD Futures 2023, Selected Papers. Springer Science and Business Media Deutschland GmbH. 2023. p. 159-173. (Communications in Computer and Information Science). doi: 10.1007/978-3-031-37189-9_11

A Design Ranking Method for Many-Objective Evolutionary Optimization

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Optimization Algorithm for Rapid Sustainable Planning and Design

Cite this

A Design Ranking Method for Many-Objective Evolutionary Optimization

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Activities

Optimization Algorithm for Rapid Sustainable Planning and Design

Cite this