Configuring advanced evolutionary algorithms for multicriteria building spatial design optimisation

K. van der Blom, S. Boonstra, H. Hofmeyer, T. Bäck, M.T.M. Emmerich

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/CongresprocedureConferentiebijdrageAcademicpeer review

5 Citaties (Scopus)

Uittreksel

In this paper solution approaches for solving the building spatial design optimisation problem for structural and energy performance are advanced on multiple fronts. A new initialisation operator is introduced to generate an unbiased initial population for a tailored version of SMS-EMOA with problem specific operators. Improvements to the mutation operator are proposed to eliminate bias and allow mutations consisting of multiple steps. Moreover, landscape analysis is applied in order to explore the landscape of both objectives and investigate the behaviour of the mutation operator. Parameter tuning is applied with the irace package and the Mixed Integer Evolution Strategy to find improved parameter settings and explore tuning with a relatively small number of expensive evaluations. Finally, the performances of the standard and tailored SMS-EMOA algorithms with tuned parameters are compared.

TaalEngels
Titel2017 IEEE Congress on Evolutionary Computation (CEC) Proceedings, June 5-8, 2017, Donostia - San Sebastián, Spain
UitgeverijInstitute of Electrical and Electronics Engineers
Pagina's1803-1810
Aantal pagina's8
ISBN van elektronische versie9781509046010
ISBN van geprinte versie978-1-5090-4601-0
DOI's
StatusGepubliceerd - 5 jul 2017
Evenement2017 IEEE Congress on Evolutionary Computation (CEC2017) June 5-8, 2017, Donostia - San Sebastián, Spain - San Sebastian, Spanje
Duur: 5 jun 20178 jun 2017
http://www.cec2017.org/

Congres

Congres2017 IEEE Congress on Evolutionary Computation (CEC2017) June 5-8, 2017, Donostia - San Sebastián, Spain
Verkorte titelCEC2017
LandSpanje
StadSan Sebastian
Periode5/06/178/06/17
Internet adres

Vingerafdruk

Evolutionary algorithms
Tuning
Design optimization

Citeer dit

van der Blom, K., Boonstra, S., Hofmeyer, H., Bäck, T., & Emmerich, M. T. M. (2017). Configuring advanced evolutionary algorithms for multicriteria building spatial design optimisation. In 2017 IEEE Congress on Evolutionary Computation (CEC) Proceedings, June 5-8, 2017, Donostia - San Sebastián, Spain (blz. 1803-1810). [7969520] Institute of Electrical and Electronics Engineers. DOI: 10.1109/CEC.2017.7969520
van der Blom, K. ; Boonstra, S. ; Hofmeyer, H. ; Bäck, T. ; Emmerich, M.T.M./ Configuring advanced evolutionary algorithms for multicriteria building spatial design optimisation. 2017 IEEE Congress on Evolutionary Computation (CEC) Proceedings, June 5-8, 2017, Donostia - San Sebastián, Spain. Institute of Electrical and Electronics Engineers, 2017. blz. 1803-1810
@inproceedings{304bfad8504c4e338dd32cea605dd680,
title = "Configuring advanced evolutionary algorithms for multicriteria building spatial design optimisation",
abstract = "In this paper solution approaches for solving the building spatial design optimisation problem for structural and energy performance are advanced on multiple fronts. A new initialisation operator is introduced to generate an unbiased initial population for a tailored version of SMS-EMOA with problem specific operators. Improvements to the mutation operator are proposed to eliminate bias and allow mutations consisting of multiple steps. Moreover, landscape analysis is applied in order to explore the landscape of both objectives and investigate the behaviour of the mutation operator. Parameter tuning is applied with the irace package and the Mixed Integer Evolution Strategy to find improved parameter settings and explore tuning with a relatively small number of expensive evaluations. Finally, the performances of the standard and tailored SMS-EMOA algorithms with tuned parameters are compared.",
author = "{van der Blom}, K. and S. Boonstra and H. Hofmeyer and T. B{\"a}ck and M.T.M. Emmerich",
year = "2017",
month = "7",
day = "5",
doi = "10.1109/CEC.2017.7969520",
language = "English",
isbn = "978-1-5090-4601-0",
pages = "1803--1810",
booktitle = "2017 IEEE Congress on Evolutionary Computation (CEC) Proceedings, June 5-8, 2017, Donostia - San Sebasti{\'a}n, Spain",
publisher = "Institute of Electrical and Electronics Engineers",
address = "United States",

}

van der Blom, K, Boonstra, S, Hofmeyer, H, Bäck, T & Emmerich, MTM 2017, Configuring advanced evolutionary algorithms for multicriteria building spatial design optimisation. in 2017 IEEE Congress on Evolutionary Computation (CEC) Proceedings, June 5-8, 2017, Donostia - San Sebastián, Spain., 7969520, Institute of Electrical and Electronics Engineers, blz. 1803-1810, San Sebastian, Spanje, 5/06/17. DOI: 10.1109/CEC.2017.7969520

Configuring advanced evolutionary algorithms for multicriteria building spatial design optimisation. / van der Blom, K.; Boonstra, S.; Hofmeyer, H.; Bäck, T.; Emmerich, M.T.M.

2017 IEEE Congress on Evolutionary Computation (CEC) Proceedings, June 5-8, 2017, Donostia - San Sebastián, Spain. Institute of Electrical and Electronics Engineers, 2017. blz. 1803-1810 7969520.

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/CongresprocedureConferentiebijdrageAcademicpeer review

TY - GEN

T1 - Configuring advanced evolutionary algorithms for multicriteria building spatial design optimisation

AU - van der Blom,K.

AU - Boonstra,S.

AU - Hofmeyer,H.

AU - Bäck,T.

AU - Emmerich,M.T.M.

PY - 2017/7/5

Y1 - 2017/7/5

N2 - In this paper solution approaches for solving the building spatial design optimisation problem for structural and energy performance are advanced on multiple fronts. A new initialisation operator is introduced to generate an unbiased initial population for a tailored version of SMS-EMOA with problem specific operators. Improvements to the mutation operator are proposed to eliminate bias and allow mutations consisting of multiple steps. Moreover, landscape analysis is applied in order to explore the landscape of both objectives and investigate the behaviour of the mutation operator. Parameter tuning is applied with the irace package and the Mixed Integer Evolution Strategy to find improved parameter settings and explore tuning with a relatively small number of expensive evaluations. Finally, the performances of the standard and tailored SMS-EMOA algorithms with tuned parameters are compared.

AB - In this paper solution approaches for solving the building spatial design optimisation problem for structural and energy performance are advanced on multiple fronts. A new initialisation operator is introduced to generate an unbiased initial population for a tailored version of SMS-EMOA with problem specific operators. Improvements to the mutation operator are proposed to eliminate bias and allow mutations consisting of multiple steps. Moreover, landscape analysis is applied in order to explore the landscape of both objectives and investigate the behaviour of the mutation operator. Parameter tuning is applied with the irace package and the Mixed Integer Evolution Strategy to find improved parameter settings and explore tuning with a relatively small number of expensive evaluations. Finally, the performances of the standard and tailored SMS-EMOA algorithms with tuned parameters are compared.

UR - http://www.scopus.com/inward/record.url?scp=85026810776&partnerID=8YFLogxK

U2 - 10.1109/CEC.2017.7969520

DO - 10.1109/CEC.2017.7969520

M3 - Conference contribution

SN - 978-1-5090-4601-0

SP - 1803

EP - 1810

BT - 2017 IEEE Congress on Evolutionary Computation (CEC) Proceedings, June 5-8, 2017, Donostia - San Sebastián, Spain

PB - Institute of Electrical and Electronics Engineers

ER -

van der Blom K, Boonstra S, Hofmeyer H, Bäck T, Emmerich MTM. Configuring advanced evolutionary algorithms for multicriteria building spatial design optimisation. In 2017 IEEE Congress on Evolutionary Computation (CEC) Proceedings, June 5-8, 2017, Donostia - San Sebastián, Spain. Institute of Electrical and Electronics Engineers. 2017. blz. 1803-1810. 7969520. Beschikbaar vanaf, DOI: 10.1109/CEC.2017.7969520