A multi-objective genetic algorithm framework for earlier phases of architectural design

Serkan Kocabay; Sema Alaçam

A multi-objective genetic algorithm framework for earlier phases of architectural design

Serkan Kocabay, Sema Alaçam

Department of Architecture

Istanbul Technical University

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

6 Citations (Scopus)

Abstract

This paper presents an algorithmic framework proposal for implementation of a multi-objective genetic algorithm (Moga) in architectural design process. Different than the previous studies, we introduce a dynamic and extendible modular framework for multiple objectives. The objective modules with different fitness functions are connected simultaneously in the Rhino/Octopus interface, after multiplication with a constant value or a variable. In this study, we discuss the potentials and limitations of Moga in 3D form generation, implications of Moga in a case study and the qualitative and quantitative changes in relation to the change of constant value/ the impact ratio of competing objectives. The outcomes of the case study are investigated based on its potentiality in providing feedback in the earlier phases of decision processes in design.

Original language	English
Title of host publication	CAADRIA 2017 - 22nd International Conference on Computer-Aided Architectural Design Research in Asia
Subtitle of host publication	Protocols, Flows and Glitches
Editors	Marc Aurel Schnabel, Aleksandra Raonic, Patrick Janssen, Paul Loh
Publisher	The Association for Computer-Aided Architectural Design Research in Asia (CAADRIA)
Pages	293-302
Number of pages	10
ISBN (Electronic)	9789881902689
Publication status	Published - 2017
Event	22nd International Conference on Computer-Aided Architectural Design Research in Asia: Protocols, Flows and Glitches, CAADRIA 2017 - Suzhou, China Duration: 5 Apr 2017 → 8 Apr 2017

Publication series

Name	CAADRIA 2017 - 22nd International Conference on Computer-Aided Architectural Design Research in Asia: Protocols, Flows and Glitches

Conference

Conference	22nd International Conference on Computer-Aided Architectural Design Research in Asia: Protocols, Flows and Glitches, CAADRIA 2017
Country/Territory	China
City	Suzhou
Period	5/04/17 → 8/04/17

Bibliographical note

Publisher Copyright:
© 2017, The Association for Computer-Aided Architectural Design Research in Asia (CAADRIA), Hong Kong.

Keywords

Architectural design process
Case study
Genetic algorithm
Multi-objective

Cite this

Kocabay, S., & Alaçam, S. (2017). A multi-objective genetic algorithm framework for earlier phases of architectural design. In M. A. Schnabel, A. Raonic, P. Janssen, & P. Loh (Eds.), CAADRIA 2017 - 22nd International Conference on Computer-Aided Architectural Design Research in Asia: Protocols, Flows and Glitches (pp. 293-302). (CAADRIA 2017 - 22nd International Conference on Computer-Aided Architectural Design Research in Asia: Protocols, Flows and Glitches). The Association for Computer-Aided Architectural Design Research in Asia (CAADRIA).

Kocabay, Serkan ; Alaçam, Sema. / A multi-objective genetic algorithm framework for earlier phases of architectural design. CAADRIA 2017 - 22nd International Conference on Computer-Aided Architectural Design Research in Asia: Protocols, Flows and Glitches. editor / Marc Aurel Schnabel ; Aleksandra Raonic ; Patrick Janssen ; Paul Loh. The Association for Computer-Aided Architectural Design Research in Asia (CAADRIA), 2017. pp. 293-302 (CAADRIA 2017 - 22nd International Conference on Computer-Aided Architectural Design Research in Asia: Protocols, Flows and Glitches).

@inproceedings{e9ea55b3f5444940b6af20b127c448f7,

title = "A multi-objective genetic algorithm framework for earlier phases of architectural design",

abstract = "This paper presents an algorithmic framework proposal for implementation of a multi-objective genetic algorithm (Moga) in architectural design process. Different than the previous studies, we introduce a dynamic and extendible modular framework for multiple objectives. The objective modules with different fitness functions are connected simultaneously in the Rhino/Octopus interface, after multiplication with a constant value or a variable. In this study, we discuss the potentials and limitations of Moga in 3D form generation, implications of Moga in a case study and the qualitative and quantitative changes in relation to the change of constant value/ the impact ratio of competing objectives. The outcomes of the case study are investigated based on its potentiality in providing feedback in the earlier phases of decision processes in design.",

keywords = "Architectural design process, Case study, Genetic algorithm, Multi-objective",

author = "Serkan Kocabay and Sema Ala{\c c}am",

note = "Publisher Copyright: {\textcopyright} 2017, The Association for Computer-Aided Architectural Design Research in Asia (CAADRIA), Hong Kong.; 22nd International Conference on Computer-Aided Architectural Design Research in Asia: Protocols, Flows and Glitches, CAADRIA 2017 ; Conference date: 05-04-2017 Through 08-04-2017",

year = "2017",

language = "English",

series = "CAADRIA 2017 - 22nd International Conference on Computer-Aided Architectural Design Research in Asia: Protocols, Flows and Glitches",

publisher = "The Association for Computer-Aided Architectural Design Research in Asia (CAADRIA)",

pages = "293--302",

editor = "Schnabel, \{Marc Aurel\} and Aleksandra Raonic and Patrick Janssen and Paul Loh",

booktitle = "CAADRIA 2017 - 22nd International Conference on Computer-Aided Architectural Design Research in Asia",

}

Kocabay, S & Alaçam, S 2017, A multi-objective genetic algorithm framework for earlier phases of architectural design. in MA Schnabel, A Raonic, P Janssen & P Loh (eds), CAADRIA 2017 - 22nd International Conference on Computer-Aided Architectural Design Research in Asia: Protocols, Flows and Glitches. CAADRIA 2017 - 22nd International Conference on Computer-Aided Architectural Design Research in Asia: Protocols, Flows and Glitches, The Association for Computer-Aided Architectural Design Research in Asia (CAADRIA), pp. 293-302, 22nd International Conference on Computer-Aided Architectural Design Research in Asia: Protocols, Flows and Glitches, CAADRIA 2017, Suzhou, China, 5/04/17.

A multi-objective genetic algorithm framework for earlier phases of architectural design. / Kocabay, Serkan; Alaçam, Sema.
CAADRIA 2017 - 22nd International Conference on Computer-Aided Architectural Design Research in Asia: Protocols, Flows and Glitches. ed. / Marc Aurel Schnabel; Aleksandra Raonic; Patrick Janssen; Paul Loh. The Association for Computer-Aided Architectural Design Research in Asia (CAADRIA), 2017. p. 293-302 (CAADRIA 2017 - 22nd International Conference on Computer-Aided Architectural Design Research in Asia: Protocols, Flows and Glitches).

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

TY - GEN

T1 - A multi-objective genetic algorithm framework for earlier phases of architectural design

AU - Kocabay, Serkan

AU - Alaçam, Sema

PY - 2017

Y1 - 2017

N2 - This paper presents an algorithmic framework proposal for implementation of a multi-objective genetic algorithm (Moga) in architectural design process. Different than the previous studies, we introduce a dynamic and extendible modular framework for multiple objectives. The objective modules with different fitness functions are connected simultaneously in the Rhino/Octopus interface, after multiplication with a constant value or a variable. In this study, we discuss the potentials and limitations of Moga in 3D form generation, implications of Moga in a case study and the qualitative and quantitative changes in relation to the change of constant value/ the impact ratio of competing objectives. The outcomes of the case study are investigated based on its potentiality in providing feedback in the earlier phases of decision processes in design.

AB - This paper presents an algorithmic framework proposal for implementation of a multi-objective genetic algorithm (Moga) in architectural design process. Different than the previous studies, we introduce a dynamic and extendible modular framework for multiple objectives. The objective modules with different fitness functions are connected simultaneously in the Rhino/Octopus interface, after multiplication with a constant value or a variable. In this study, we discuss the potentials and limitations of Moga in 3D form generation, implications of Moga in a case study and the qualitative and quantitative changes in relation to the change of constant value/ the impact ratio of competing objectives. The outcomes of the case study are investigated based on its potentiality in providing feedback in the earlier phases of decision processes in design.

KW - Architectural design process

KW - Case study

KW - Genetic algorithm

KW - Multi-objective

UR - https://www.scopus.com/pages/publications/85021710169

M3 - Conference contribution

AN - SCOPUS:85021710169

T3 - CAADRIA 2017 - 22nd International Conference on Computer-Aided Architectural Design Research in Asia: Protocols, Flows and Glitches

SP - 293

EP - 302

BT - CAADRIA 2017 - 22nd International Conference on Computer-Aided Architectural Design Research in Asia

A2 - Schnabel, Marc Aurel

A2 - Raonic, Aleksandra

A2 - Janssen, Patrick

A2 - Loh, Paul

PB - The Association for Computer-Aided Architectural Design Research in Asia (CAADRIA)

T2 - 22nd International Conference on Computer-Aided Architectural Design Research in Asia: Protocols, Flows and Glitches, CAADRIA 2017

Y2 - 5 April 2017 through 8 April 2017

ER -

Kocabay S, Alaçam S. A multi-objective genetic algorithm framework for earlier phases of architectural design. In Schnabel MA, Raonic A, Janssen P, Loh P, editors, CAADRIA 2017 - 22nd International Conference on Computer-Aided Architectural Design Research in Asia: Protocols, Flows and Glitches. The Association for Computer-Aided Architectural Design Research in Asia (CAADRIA). 2017. p. 293-302. (CAADRIA 2017 - 22nd International Conference on Computer-Aided Architectural Design Research in Asia: Protocols, Flows and Glitches).

A multi-objective genetic algorithm framework for earlier phases of architectural design

Abstract

Publication series

Conference

Bibliographical note

Keywords

Other files and links

Fingerprint

Cite this