Large scale evolutionary optimization using cooperative coevolution

Notes

• based on Differential Evolution for High-Dimensional Function Optimization;

CC (cooperative coevolution)

• steps:
  • problem decomposition;
  • subcomponent optimization;
  • subcomponent coadaptation;
• citations: 6, 10, 11, 15, 16, 25;

DE (differential evolution)

• description, cited 1, 13, 18;
• benchmarks, cited 23;
• parameters, cited 3, 13, 28;
• adaptations, cited 20;
• operators:
  • crossover:
    • we must ensure that at least one element is changed (they select a random index and ensure that it is used in crossover);

NSDE (differential evolution with neighbourhood search)

• description, cited 17;

SaNSDE (self-adaptive NSDE)

• description, cited 26;
• benchmarks, cited 19;

EACC-G

• for each cycle a new subcomponent permutation is chosen; the grouping structure changes dynamically;

• the subcomponent weights are still applied; adaptive weighting for coadaptation among subcomponents after each cycle;

• definition of separable and non-separable problems cited from 19;

DECC-G

• combination between EACC-G and SaNSDE;

DECC-O

• the same as DECC-G, but with = 1;

DECC-G-NW

• the same as DECC-G, but without weights;

Benchmark

• functions, cited 19, 27;
• competitors FEPCC (cited 6), DECC-O (cited 15);
• parameters:

  • : 100;

  • : 100;

  • cycles: 50;

Citations

• 1: Self-adapting control parameters in differential evolution: a comparative study on numerical benchmark problems; J. Brest, S. Greiner, B. Boskovic, M. Mernik, V. Zumer; 2006;

• 3: A parameter study for differential evolution; R. Gamperle, S. D. Muller, P. Koumoutsakos; 2002;

• 6: Scaling up fast evolutionary programming with cooperative coevolution; Y. Liu, X. Yao, Q. Zhao, T. Higuchi; 2001;

• 10: A cooperative coevolutionary approach to function optimization; M. Potter, K. De Jong; 1994;

• 11: Cooperative coevolution: an architecture for evolving coadapted subcomponents; M. Potter, K. De Jong; 2000;

• 13: Self-adaptive differential evolution algorithm for numerical optimization; A. K. Qin, P. N. Suganthan; 2005;

• 15: Cooperative co-evolutionary differential evolution for function optimization; Y. Shi, H. Teng, Z. Li; 2005;

• 16: A blended population approach to cooperative coevolution for decomposition of complex problems; D. Sofge, K. De Jong, A. Schultz; 2002;

• 18: Differential evolution -- a simple and efficient heuristic for global optimization over continuous spaces; R. Storn, K. Price; 1997;

• 19: Problem definitions and evaluation criteria for the CEC 2005 special session on real-parameter optimization; P. N. Suganthan, N. Hansen, J. J. Liang, K. Deb, Y. P. Chen, A. Auger, S. Tiwari; 2005;

• 20: DE/EDA: a new evolutionary algorithm for global optimization; J. Sun, Q. Zhang, E. Tsang; 2005;

• 23: A comparative study of differential evolution, particle swarm optimization, and evolutionary algorithms on numerical benchmark problems; J. Vesterstrom, R. Thomsen; 2004;

• 25: Differential evolution for high-dimensional function optimization; Z. Yang, K. Tang, X. Yao; 2007;

• 26: Self-adaptive differential evolution with neighborhood search; Z. Yang, K. Tang, X. Yao; 2008;

• 27: Evolutionary programming made faster; X. Yao, Y. Liu, G. Lin; 1999;

• 28: Critical values for the control parameters of differential evolution algorithms; D. Zaharie; 2002;