Differential Evolution with Modified Mutation Strategy for Solving Global Optimization Problems
In the present work we propose a modified variant of Differential Evolution (DE) algorithm named MDE. MDE differs from the basic DE in the manner in which the base vector is generated. While in simple/basic DE, base vector is usually randomly selected from the population of individuals, in MDE base vector is generated as convex linear combination (clc) of three randomly selected vectors out of which one is the one having best fitness value. This mutation scheme is used stochastically with mutation scheme in which the base generated using a clc of three randomly generated vectors. MDE is validated on a set of benchmark problems and is compared with basic DE and other DE variants. Numerical and statistical analysis shows the competence of proposed MDE.
Keywordsdifferential evolution mutation strategy global optimization
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. Berkeley, CA, Tech. Rep. TR-95-012 (1995)Google Scholar
- 6.Vesterstrom, J., Thomsen, R.: A Comparative Study of Differential Evolution, Particle Swarm Optimization and Evolutionary Algorithms on Numerical Benchmark Problems. In: Congress on Evolutionary Computation, pp. 980–987 (2004)Google Scholar
- 7.Montes, E.M., Reyes, J.V.: A Comperative Study of Differential Evolution Variants for Global Optimization. In: GECCO, Seattle Washington USA, pp. 485–492 (2006)Google Scholar
- 8.Pant, M., Ali, M., Abraham, A.: Mixed Mutation Strategy Embedded Differential Evolution. In: IEEE Congress on Evolutionary Computation, pp. 1240–1246 (2009)Google Scholar
- 10.Fan, H.Y., Lampinen J., Dulikravich, G.S.: Improvements to Mutation Donor Formulation of Differential Evolution. In: International Congress on Evolutionary Methods for Design Optimization and Control with Applications to Industrial Problems Eurogen (2003)Google Scholar
- 15.Suganthan, P., Hansen, N., Liang, J.: Problem Definitions and Evaluation Criteria for the CEC 2005 Special Session on Real-Parameter Optimization (2005)Google Scholar
- 17.Zhu, R.: Statistical Analysis Methods. China Forestry Publishing House, Beijing (1989)Google Scholar