Abstract
In this paper, the Cross-Entropy (CE) optimization algorithm for continuous functions is studied. Aiming at the problem of computational efficiency caused by the large number of samples in Monte Carlo sampling, the Dynamic Weight strategy (DW) and the Adaptive sample Size strategy (AS) are proposed. The former can get the weighting coefficient of each sample by measuring the difference between the elite sample and the best sample, which can speed up the convergence rate of the algorithm. The latter can greatly reduce the number of calls to the objective functions by building relationship between the sample size and the standard deviation of elite samples, which can effectively improve the optimization efficiency. Finally, the validity of the proposed algorithm is verified by four unconstrained multimodal standard test cases and two constrained practical project examples. The results show that with similar capability to obtain the global optimal solution, the number of calls to the objective functions is reduced by 73.44%, 69.44%, 47.33%, 77.88%, 40.21% and 25.95% respectively compared with the traditional CE algorithm.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Rubinstein, R.: The CE algorithm for combinatorial and continuous optimization. Method. Comput. Appl. Probab. 1, 127 (1999)
Rubinstein, R.Y.: Combinatorial optimization, cross-entropy, ants and rare events. In: Uryasev, S., Pardalos, P.M. (eds.) Stochastic Optimization: Algorithms and Applications. Applied Optimization, vol. 54, pp. 303–363. Springer, Boston (2011)
Yang, J., Peng, Z.: A modified relative entropy algorithm for solving global optimization problems and its convergence. J. Hunan Inst. Technol. 22(2), 5 (2009)
Li, G., Xiao, Q.: A Cuckoo-CE hybrid optimization algorithm and its performance simulation. J. Shanghai Univ. Sci. Technol. 37(2), 7 (2015)
Chen, L., Yao, Y., Zheng, Q.: Discontinuous penalty approach with deviation integral for global constrained minimizaton. Appl. Math. Mech. 30(9), 1201 (2009)
An, S., Yang, S., Ho, S.L., Ni, P.: An improved cross entropy algorithm applied to inverse problems. Trans. Magn. 48(2), 4 (2012)
Botev, Z.I., Kroese, D.P., Rubinstein, R.Y., L’Ecuyer, P.: The cross-entropy method for optimization, Handbook of Statistics. In: Govindaraju, V., Rao, C.R. (eds.) Handbook of Statistics. Machine Learning, vol. 31, pp. 19–34. Elsevier, Chennai (2013)
Guo, Z., Luo, W., Chen, X.: Research on multi - method cooperative immune evolutionary algorithm. Comput. Eng. Appl. 48(14), 6 (2012)
Yao, W.: Uncertainty MDO Theory and Its Application in the Overall Design of Aircraft. National University of Defense Technology, Changsha (2007)
Yao, W.: Research on Optimization of Multidisciplinary Design for Uncertainty of Aircraft. National University of Defense Technology, Changsha (2011)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG
About this paper
Cite this paper
Ma, Z., Yao, W., Zhao, Y., Huang, Y. (2018). A Cross-Entropy Optimization Algorithm for Continuous Function Based on Improved Sampling. In: Schumacher, A., Vietor, T., Fiebig, S., Bletzinger, KU., Maute, K. (eds) Advances in Structural and Multidisciplinary Optimization. WCSMO 2017. Springer, Cham. https://doi.org/10.1007/978-3-319-67988-4_51
Download citation
DOI: https://doi.org/10.1007/978-3-319-67988-4_51
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-67987-7
Online ISBN: 978-3-319-67988-4
eBook Packages: EngineeringEngineering (R0)