Self-Adaptive Differential Evolution with Hybrid Rules of Perturbation for Dynamic Optimization

• Autorzy: Trojanowski K. , Raciborski M. , Kaczyński P.
• Języki publikacji: EN

Abstrakty

EN

In this paper an adaptive differential evolution approach for dynamic optimization problems is studied. A new benchmark suite Syringa is also presented. The suite allows to generate test-cases from a multiple number of dynamic optimization classes. Two dynamic benchmarks: Generalized Dynamic Benchmark Generator (GDBG) and Moving Peaks Benchmark (MPB) have been simulated in Syringa and in the presented research they were subject of the experimental research. Two versions of adaptive differential evolution approach, namely the jDE algorithm have been heavily tested: the pure version of jDE and jDE equipped with solutions mutated with a new operator. The operator uses a symmetric ?-stable distribution variate for modification of the solution coordinates.

Słowa kluczowe

EN

adaptive differential evolution; dynamic optimization; symmetric a-stable distribution

• Wydawca: Instytut Łączności - Państwowy Instytut Badawczy
• Czasopismo: Journal of Telecommunications and Information Technology
• Rocznik: 2011
• Tom: nr 4
• Strony: 20--30
• Opis fizyczny: Bibliogr. 13 poz., rys., tab.

Twórcy

autor

Trojanowski K.

autor

Raciborski M.

autor

Kaczyński P.

• Institute of Computer Science, Polish Academy of Sciences, Ordona 21 01-237 Warsaw, Poland,

Bibliografia

• [1] Y. Jin and J. Branke, “Evolutionary algorithms in uncertain environments – a survey”, IEEE Trans. Evol. Comput., vol. 9, no. 3, pp. 303–317, 2005.
• [2] V. Feokistov, “Differential evolution”, in Search of Solutions, vol. 5 of Optimization and Its Applications. Springer, 2006.
• [3] K. V. Price, R. M. Storn, and J. A. Lampinen, Differential Evolution, A Practical Approach to Global Optimization. Natural Computing Series. Springer, 2005.
• [4] J. Brest, S. Greiner, B. Boskovic, M. Mernik, and V. Zumer, “Selfadapting control parameters in differential evolution: a comparative study on numerical benchmark problems”, IEEE Trans. Evol. Comput., vol. 10, no. 6, pp. 646–657, 2006.
• [5] J. Brest, A. Zamuda, B. Boskovic, M. S. Maucec, and V. Zumer, “Dynamic optimization using self-adaptive differential evolution”, in IEEE Congr. Evol. Comput., pp. 415–422. IEEE, 2009.
• [6] A. Obuchowicz and P. Pretki, “Isotropic symmetric a-stable mutations for evolutionary algorithms”, in Proc. Congr. Evol. Comput., vol. 1, pp. 404–410. IEEE Press, 2005.
• [7] K. Trojanowski, “Properties of quantum particles in multi-swarms for dynamic optimization”, Fundamenta Informaticae, vol. 95, no. 2–3, pp. 349–380, 2009.
• [8] C. Li and S. Yang, “A generalized approach to construct benchmark problems for dynamic optimization”, in Simulated Evolution and Learning, 7th Int. Conf. SEAL 2008, Melbourne, Australia, 2008, vol. 5361 of LNCS, pp. 391–400. Springer, 2008.
• [9] J. Branke, “Memory enhanced evolutionary algorithm for changing optimization problems”, in Proc. Congr. on Evol. Comput., vol. 3, pages 1875–1882. IEEE Press, Piscataway, NJ, 1999.
• [10] R. Salomon, “Reevaluating genetic algorithm performance under coordinate rotation of benchmark functions”, BioSystems, vol. 39, no. 3, pp. 263–278, 1996.
• [11] J. J. Liang, P. N. Suganthan, and K. Deb, “Novel composition test functions for numerical global optimization”, in Proc. IEEE Swarm Intelligence Symp., Pasadena, CA, USA, 2005, pp. 68–75.
• [12] P. N. Suganthan et al., “Problem definitions and evaluation criteria for the cec 2005 special session on real-parameter optimization”, Tech. Rep., Nanyang Technological University, Singapore, 2005.
• [13] M. Raciborski, K. Trojanowski, and P. Kaczyński, “Differential evolution for high scale dynamic optimization”, in Security and Intelligent Information Systems, LNCS. Springer, 2011 (will appear in vol. 7053).