A New Algorithm of Evolutionary Computation: Bio-Simulated Optimization
Genetic algorithm (GA), evolutionary programming (EP) and evolutionary strategy (ES) are called the three kinds of evolutionary computation methods. They have been widely used in many engineering fields. However, selecting individuals directly and random search lead to produce premature problem, and requirement for high precision decreases the search efficiency, these become the obstructs of application in engineering practice. This paper proposes a new algorithm of evolutionary computation, it is called bio-simulated optimization algorithm (BSO). BSO reproduces new generation through asexual propagation and sexual propagation. Here, the evolutionary operators effectively solve the problem of premature convergence. Furthermore, performance of global search and convergence are proved theoretically. Finally, Compared BSO with GA and EP in searching the optimal solution of a continuous multi-peaks function, three kinds of computation procedures are run in Matlab, the result shows that performance of BSO is superior to GA and EP.
KeywordsGenetic Algorithm Evolutionary Computation Evolutionary Generation Global Search Gene Recombination
Unable to display preview. Download preview PDF.
- 1.Zhang, J.Q., Cao, Y.F., Wang, C.Q.: A Genetic Algorithm Based on Common Path for TSP. Computer Engineering and Applications 40, 58–61 (2004)Google Scholar
- 3.Fogel, L.J., Angeline, P.J., Back, T.: Evolutionary Programming V. In: Proceedings of the 5th annual conference on evolutionary programming, San Diego CA, pp. 488–496. MIT Press, Cambridge (1996); Neurocomputing 17, 133–134 (1997)Google Scholar
- 4.Zhang, J.H., Xu, X.H.: Development on Simulated Evolutionary Computing. System Engineering and Electrionic Technology 8, 44–47 (1998)Google Scholar
- 6.Yu, W., Li, R.H.: A New Evolutionary Approach Based on Reproduction of Asexual Cells. Computer Engineering & Science 23, 7–10 (2003)Google Scholar
- 7.Tang, F., Teng, H.F., Sun, Z.G.: Schema Theorem of the Decimal-Coded Genetic Algorithm. Mini-Micro System 21, 364–367 (2000)Google Scholar
- 8.Li, H., Tang, H.W., Guo, C.H.: The Convergence Analysis of A Class of Evolution Strategies. OR Transaction 3, 79–83 (1999)Google Scholar