A new differential mutation base generator for differential evolution
- 285 Downloads
A new differential mutation base strategy for differential evolution (DE), namely best of random, is proposed. The best individual among several randomly chosen individuals is chosen as the differential mutation base while the other worse individuals are donors for vector differences. Hence both good diversity and fast evolution speed can be obtained in DE using the new differential mutation base. A comprehensive comparative study is carried out over a set of benchmark functions. Numerical results show that a better balance of reliability and efficiency can be obtained in differential evolution implementing the new generator of differential mutation base, especially in functions with high dimension.
KeywordsDifferential evolution Differential mutation Best of random Diversity
Unable to display preview. Download preview PDF.
- 1.Storn, R., Price, K.: Differential evolution—a simple and efficient adaptive scheme for global optimization over continuous spaces. Technical Report TR-95-012, International Computer Science Institute, Berkley, CA (1995)Google Scholar
- 3.Price K.V.: An introduction to differential evolution. In: Corn, D., Dorigo, M., Glover, F. (eds) New Ideas in Optimization, chap. 6., pp. 79–108. McGraw-Hill, London (1999)Google Scholar
- 4.Price K.V., Storn R.M., Lampinen J.A.: Differential Evolution: A Practical Approach to Global Optimization. Springer, Berlin (2005)Google Scholar
- 5.Qing A.: Differential Evolution: Fundamentals and Applications in Engineering. Wiley, New York (2009)Google Scholar
- 6.Feoktistov V.: Differential Evolution: In Search of Solutions. Springer, Berlin (2006)Google Scholar
- 7.Joshi, R., Sanderson, A.C.: Multisensor fusion and model selection using a minimal representation size framework. In: IEEE/SICE/RSJ International Conference on Multisensor Fusion Integration Intelligent Systems, Washington, DC, December 8–11, 1996, pp. 25–32 (1996)Google Scholar
- 8.Storn, R.: On the usage of differential evolution for function optimization. In: North American Fuzzy Information Processing Society Conference, Berkeley, pp. 519–523 (1996)Google Scholar
- 10.Vesterstrøm, J., Thomsen, R.: A comparative study of differential evolution, particle swarm optimization, and evolutionary algorithms on numerical benchmark problems. In: IEEE Congress Evolutionary Computation, Portland, OR, June 19–23, 2004, vol. 2, pp. 1980–1987 (2004)Google Scholar
- 12.Wong, K.P., Dong, Z.Y.: Differential evolution, an alternative approach to evolutionary algorithm. In: 13th International Conference Intelligent Systems Application Power Systems. Arlington, VA, Nov. 6–10, pp. 73–83 (2005)Google Scholar
- 14.Qing, A.: A parametric study on differential evolution based on benchmark electromagnetic inverse scattering problem. In: IEEE Congress Evolutionary Computation, Singapore, Sept. 25–28, 2007, pp. 1904–1909 (2007)Google Scholar
- 15.Qing, A.: A study on base vector for differential evolution. IEEE World Congress Computational Intelligence/2008 IEEE Congress Evolutionary Computation, Hong Kong, June 1–6, 2008, pp. 550–556 (2008)Google Scholar