Abstract
This paper proposes a novel Self-Adaptive algorithm for Multi-Objective Constrained Optimization by using Radial Basis Function ApproximationsSAMO-COBRA. The algorithm automatically determines the best Radial Basis Function-fit as surrogates for the objectives as well as the constraintsto find new feasible Pareto-optimal solutions. The algorithm also uses hyper-parameter tuning on the fly to improve its local search strategy. In every iteration one solution is added and evaluatedresulting in a strategy requiring only a small number of function evaluations for finding a set of feasible solutions on the Pareto frontier. The proposed algorithm is compared to a wide set of other state-of-the-art algorithms (NSGA-IINSGA-IIICEGOSMES-RBF) on 18 constrained multi-objective problems. In the experiments we show that our algorithm outperforms the other algorithms in terms of achieved Hypervolume after given a fixed small evaluation budget. These results suggest that SAMO-COBRA is a good choice for optimizing constrained multi-objective optimization problems with expensive function evaluations.
This is a preview of subscription contentlog in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
BagheriS.KonenW.BäckT.: Online selection of surrogate models for constrained black-box optimization. In: 2016 IEEE Symposium Series on Computational Intelligence (SSCI)pp. 1–8. IEEE (2016)
BagheriS.KonenW.BäckT.: Comparing kriging and radial basis function surrogates. In: Proceedings 27 Workshop Computational Intelligencepp. 243–259 (2017)
BagheriS.KonenW.EmmerichM.BäckT.: Self-adjusting parameter control for surrogate-assisted constrained optimization under limited budgets. Appl. Soft Comput. 61377–393 (2017). https://doi.org/10.1016/j.asoc.2017.07.060
BeumeN.NaujoksB.EmmerichM.: SMS-EMOA: multiobjective selection based on dominated hypervolume. Eur. J. Oper. Res. 181(3)1653–1669 (2007). https://doi.org/10.1016/j.ejor.2006.08.008
van der BlomK.et al.: Towards realistic optimization benchmarks: a questionnaire on the properties of real-world problems. In: Proceedings of the 2020 Genetic and Evolutionary Computation Conference Companion. GECCO 2020New YorkNYUSApp. 293–294. Association for Computing Machinery (2020)
BossekJ.DoerrC.KerschkeP.: Initial design strategies and their effects on sequential model-based optimization. arXiv preprint arXiv:2003.13826 (2020)
CoelloC.A.C.LamontG.B.Van VeldhuizenD.A.et al.: Evolutionary Algorithms for Solving Multi-objective Problems. Genetic and Evolutionary Computation Series. GEVOvol. 5. SpringerBoston (2007). https://doi.org/10.1007/978-0-387-36797-2
DattaR.RegisR.G.: A surrogate-assisted evolution strategy for constrained multi-objective optimization. Expert Syst. Appl. 57270–284 (2016). https://doi.org/10.1016/j.eswa.2016.03.044
DebK.: Multi-objective Optimization Using Evolutionary Algorithmsvol. 16. John Wiley & SonsNew York (2001)
DebK.PratapA.AgarwalS.MeyarivanT.: A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE Trans. Evol. Comput. 6(2)182–197 (2002). https://doi.org/10.1109/4235.996017
DebK.PratapA.MeyarivanT.: Constrained test problems for multi-objective evolutionary optimization. In: ZitzlerE.ThieleL.DebK.Coello CoelloC.A.CorneD. (eds.) EMO 2001. LNCSvol. 1993pp. 284–298. SpringerHeidelberg (2001). https://doi.org/10.1007/3-540-44719-9_20
ForresterA.SobesterA.KeaneA.: Engineering Design via Surrogate Modelling: A Practical Guide. John Wiley & SonsNew York (2008). https://doi.org/10.2514/4.479557
GongW.CaiZ.ZhuL.: An efficient multiobjective differential evolution algorithm for engineering design. Struct. Multi. Optim. 38(2)137–157 (2009). https://doi.org/10.1007/s00158-008-0269-9
HadkaD.B.: Platypus: multiobjective optimization in python (2020). https://platypus.readthedocs.io/
JainH.DebK.: An evolutionary many-objective optimization algorithm using reference-point based non dominated sorting approachpart II: handling constraints and extending to an adaptive approach. IEEE Trans. Evol. Comput. 18(4)602–622 (2014). https://doi.org/10.1109/tevc.2013.2281534
KnowlesJ.: ParEGO: a hybrid algorithm with on-line landscape approximation for expensive multiobjective optimization problems. IEEE Trans. Evol. Comput. 10(1)50–66 (2006). https://doi.org/10.1109/tevc.2005.851274
LiuH.OngY.-S.CaiJ.: A survey of adaptive sampling for global metamodeling in support of simulation-based complex engineering design. Struct. Multi. Optim. 57(1)393–416 (2017). https://doi.org/10.1007/s00158-017-1739-8
MicchelliC.A.: Interpolation of scattered data: distance matrices and conditionally positive definite functions. Constr. Approximation 2(1)11–22 (1986)
MirjaliliS.JangirP.SaremiS.: Multi-objective ant lion optimizer: a multi-objective optimization algorithm for solving engineering problems. Appl. Intell. 46(1)79–95 (2016). https://doi.org/10.1007/s10489-016-0825-8
ParsonsM.G.ScottR.L.: Formulation of multicriterion design optimization problems for solution with scalar numerical optimization methods. J. Ship Res. 48(1)61–76 (2004). https://doi.org/10.1007/s10489-016-0825-8
PonweiserW.WagnerT.BiermannD.VinczeM.: Multiobjective optimization on a limited budget of evaluations using model-assisted \(\cal{S}\)-metric selection. In: RudolphG.JansenT.BeumeN.LucasS.PoloniC. (eds.) PPSN 2008. LNCSvol. 5199pp. 784–794. SpringerHeidelberg (2008). https://doi.org/10.1007/978-3-540-87700-4_78
PowellM.J.D.: A direct search optimization method that models the objective and constraint functions by linear interpolation. In: GomezS.HennartJ.P. (eds.) Advances in Optimization and Numerical Analysis. MAIAvol. 275pp. 51–67. SpringerNetherlands (1994). https://doi.org/10.1007/978-94-015-8330-5_4
RegisR.G.ShoemakerC.A.: A quasi-multistart framework for global optimization of expensive functions using response surface models. J. Global Optim. 56(4)1719–1753 (2013). https://doi.org/10.1007/s10898-012-9940-1
RehbachF.ZaeffererM.NaujoksB.Bartz-BeielsteinT.: Expected improvement versus predicted value in surrogate-based optimization. arXiv preprint arXiv:2001.02957 (2020). https://doi.org/10.1145/3377930.3389816
SinghP.CouckuytI.FerrantiF.DhaeneT.: A constrained multi-objective surrogate-based optimization algorithm. In: 2014 IEEE Congress on Evolutionary Computation (CEC). IEEE (2014). https://doi.org/10.1109/cec.2014.6900581
TanabeR.OyamaA.: A note on constrained multi-objective optimization benchmark problems. In: 2017 IEEE Congress on Evolutionary Computation (CEC)pp. 1127–1134. IEEE (2017). https://doi.org/10.1109/cec.2017.7969433
UrquhartM.LjungskogE.SebbenS.: Surrogate-based optimisation using adaptively scaled radial basis functions. Appl. Soft Comput. 88106050 (2020)
de WinterR.: SAMO-COBRA: self-adaptive algorithm for multi-objective constrained optimization by using radial basis function approximations (2020). https://doi.org/10.5281/zenodo.4281140
de WinterR.van SteinB.DijkmanM.BäckT.: Designing ships using constrained multi-objective efficient global optimization. In: NicosiaG.PardalosP. (eds.) Machine LearningOptimizationand Data Science. LNCSvol. 11331. SpringerCham (2018). https://doi.org/10.1007/978-3-030-13709-0_16
ZitzlerE.LaumannsM.ThieleL.: SPEA2: improving the strength pareto evolutionary algorithm. TIK-reportvol. 103 (2001)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
de WinterR.van SteinB.BäckT. (2021). SAMO-COBRA: A Fast Surrogate Assisted Constrained Multi-objective Optimization Algorithm. In: IshibuchiH.et al. Evolutionary Multi-Criterion Optimization. EMO 2021. Lecture Notes in Computer Science()vol 12654. SpringerCham. https://doi.org/10.1007/978-3-030-72062-9_22
Download citation
DOI: https://doi.org/10.1007/978-3-030-72062-9_22
Published:
Publisher Name: SpringerCham
Print ISBN: 978-3-030-72061-2
Online ISBN: 978-3-030-72062-9
eBook Packages: Computer ScienceComputer Science (R0)Springer Nature Proceedings Computer Science