In order to enhance the performance of surrogate-assisted evolutionary algorithms for solving high-dimensional expensive optimization problems, this paper proposed a dual model-driven differential evolution with multi-preference strategy adaption (SOEA-SS). SOEA-SS relied on three multi-preference evolutionary strategies supported by global and local surrogates. At each iteration, SOEA-SS adaptively adjusted the evolutionary strategies in a sequential manner to strike the global exploration and local exploitation equilibrium, according to the online feedback concerning the update of optimal solution. In order to promote the optimal information sharing among the population, an elites-driven differential perturbation strategy was developed to enrich the prior knowledge of the optimal regions. Experimental results show that SOEA-SS has significant superiority over four advanced algorithms on at least 17 out of 26 high-dimensional benchmark problems.
BAYSALO, ELESHAKYM E. Aerodynamic design optimization using sensitivity analysis and computational fluid dynamics[J]. Aiaa Journal, 1992, 30(3): 718-725.
[2]
ZHAOW, GUPTAA, REGANC D, et al. Component data assisted finite element model updating of composite flying-wing aircraft using multi-level optimization[J]. Aerospace Science and Technology, 2019,95: 105486.
[3]
ELSKENT, METZENJ H, HUTTERF, et al. Neural architecture search: A survey[J]. Journal of Machine Learning Research, 2019, 20(55): 1-21.
[4]
KENNEDYJ, EBERHARTR. Particle swarm optimization[C]//Proceedings of ICNN’95-International Conference on Neural Networks, 2002: 1942-1948.
[5]
STORNR, PRICEK. Differential evolution-a simple and efficient heuristic for global optimization over continuous spaces[J]. Journal of Global Optimization, 1997,11(4): 341-359.
[6]
LIY, SONGX, GUANW. Mobile robot path planning based on ABC-PSO algorithm[C]// 2022 IEEE 6th Information Technology and Mechatronics Engineering Conference (ITOEC), 2022: 530-534.
[7]
TIANJ, TANY, ZENGJ, et al. Multiobjective infill criterion driven gaussian process-assisted particle swarm optimization of high-dimensional expensive problems[J]. IEEE Transactions on Evolutionary Computation, 2019,23(3): 459-472.
[8]
PARKJ, SANDBERGI W. Universal approximation using radial-basis-function networks[J]. Neural Computation, 1991,3(2): 246-257.
[9]
KRITHIKAAM, MALLIPEDDIR. Differential evolution with an ensemble of low-quality surrogates for expensive optimization problems[C]//IEEE Congress on Evolutionary Computation (CEC), 2016: 78-85.
[10]
LOSHCHILOVI, SCHOENAUERM, SEBAGM. Comparison-based optimizers need comparison-based surrogates[C]//Proceedings of the 11th International Conference on Parallel Problem Solving from Nature: Part I, 2010: 364-373.
[11]
WANGX, WANGG, SONGB, et al. A novel evolutionary sampling assisted optimization method for high dimensional expensive problems[J]. IEEE Transactions on Evolutionary Computation, 2019,23(5): 815-827.
TIANJie, SUNChaoli, TANYing, et al. Similarity-based multipoint infill criterion for surrogate-assisted social learning particle swarm optimization[J]. Control and Decision, 2020, 35(1): 131-138. (in Chinese)
[14]
REGISR. Evolutionary programming for high-dimensional constrained expensive black-box optimization using radial basis functions[J]. IEEE Transactions on Evolutionary Computation, 2014,18(3): 326-347.
[15]
CHUGHT, JINY, MiettinenK, et al. A surrogate-assisted reference vector guided evolutionary algorithm for computationally expensive many-objective optimization[J]. IEEE Transactions on Evolutionary Computation, 2018,22(1): 129-142.
[16]
CAIX, GAOL, LIX. Efficient generalized surrogate-assisted evolutionary algorithm for high-dimensional expensive problems[J]. IEEE Transactions on Evolutionary Computation, 2020, 24(2): 365-379.
[17]
CHENC, WANGX, DONGH, et al. Surrogate-assisted hierarchical learning water cycle algorithm for high-dimensional expensive optimization[J]. Swarm and Evolutionary Computation, 2022, 75: 101169.
[18]
ZHOUX G, ZHANGG J. Abstract convex underestimation assisted multistage differential evolution[J]. IEEE Transactions on Cybernetics, 2017,47(9): 2730-2741.
[19]
LIG, ZHANGQ, LINQ, et al. A three-level radial basis function method for expensive optimization[J]. IEEE Transactions on Cybernetics, 2022,52(7): 5720-5731.
[20]
WANGX, GAOL, LIX. Multiple surrogates and offspring-assisted differential evolution for high-dimensional expensive problems[J]. Information Sciences, 2022, 592: 174-191.
[21]
GUOD, JINY, DINGJ, et al. Heterogeneous ensemble-based infill criterion for evolutionary multiobjective optimization of expensive problems[J]. IEEE Transactions on Cybernetics, 2019,49(3): 1012-1025.
[22]
LIF, CAIX, GAOL. Ensemble of surrogates assisted particle swarm optimization of medium scale expensive problems[J]. Applied Soft Computing, 2019,74: 291-305.
HELTONJ C, DAVISF J. Latin hypercube sampling and the propagation of uncertainty in analyses of complex systems[J]. Reliability Engineering & System Safety, 2003,81(1): 23-69.
[26]
SUNC, JINY, CHENGR, et al. Surrogate-assisted cooperative swarm optimization of high-dimensional expensive problems[J]. IEEE Transactions on Evolutionary Computation, 2017,21(4): 644-660.
[27]
YUH, TANY, ZENGJ, et al. Surrogate-assisted hierarchical particle swarm optimization[J]. Information Sciences, 2018, 454-455: 59-72.
[28]
LIF, CAIX, GAOL, et al. A surrogate-assisted multiswarm optimization algorithm for high-dimensional computationally expensive problems[J]. IEEE Transactions on Cybernetics, 2021,51(3): 1390-1402.
[29]
WEIF F, CHENW N, YANGQ, et al. A classifier-assisted level-based learning swarm optimizer for expensive optimization[J]. IEEE Transactions on Evolutionary Computation, 2021,25(2): 219-233.
[30]
SUGANTHANP N, HANSENN, LIANGJ J, et al. Problem definitions and evaluation criteria for the CEC 2005 special session on real-parameter optimization[C]//Natural Computing, 2005: 341-357.
[31]
LIUB, CHENQ, ZHANGQ, et al. Behavioral study of the surrogate model-aware evolutionary search framework[C]//IEEE Congress on Evolutionary Computation (CEC), 2014: 715-722.