Differential Genetic Algorithms with Varying Population Size Based on the Lifetime
5
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
The standard genetic algorithm has some limitations, such as the prematureconvergence in the process of evolution, quick decrease of individual diversity, and eventrapping in local minimum. Aiming at the above defects, this paper puts for ward thedifferential genetic algorithms with varying population size based on the lifetime(DEGAVaPS). First, it adopts variable population genetic algorithm to endow each individual"lifetime", realizing the adaptive control of the population number. Then it conductscorresponding genetic operations, improves the crossover and mutation of geneticalgorithm, introduces differential calculation, applies Nelder Mead direct search method forlocal search, preventing the repeat around the local optimal point in search process. Later, it narrows the optimization scope of genetic algorithm, and guides the rapidevolution of species. Experiments have proved that the method has high precision, fastsearch speed and other characteristics, achieving the satisfied effect when testing theoptimization of the function.
Abstract
The standard genetic algorithm has some limitations, such as the prematureconvergence in the process of evolution, quick decrease of individual diversity, and eventrapping in local minimum. Aiming at the above defects, this paper puts for ward thedifferential genetic algorithms with varying population size based on the lifetime(DEGAVaPS). First, it adopts variable population genetic algorithm to endow each individual"lifetime", realizing the adaptive control of the population number. Then it conductscorresponding genetic operations, improves the crossover and mutation of geneticalgorithm, introduces differential calculation, applies Nelder Mead direct search method forlocal search, preventing the repeat around the local optimal point in search process. Later, it narrows the optimization scope of genetic algorithm, and guides the rapidevolution of species. Experiments have proved that the method has high precision, fastsearch speed and other characteristics, achieving the satisfied effect when testing theoptimization of the function.
참고문헌 (10)
- Arabas J, "GAVaPS-a genetic algorithm with varying population size", Proc. of the First IEEE Conf. on Evolutionary Computation, pp.73~78 (1994)
- ZhangTong., "Mutative Scale Chaos Optimization Algorithm and Its Application", CONTROL AND DECISION, 14(3), pp.285~288 (1999)
- HE Hong, "Fuzzy Genetic Algorithm with Varying Population Size", Mini-micro Systems, 27(6), pp.992~995 (2006)
- WANG Yan, "Hybrid genetic algorithm based on mutative scale chaos optimization strategy", Control and Decision, 17(6), pp.958~960 (2002)
- J. Molina, "SSPMO: A scatter tabu search procedure for non-linear multiobjective optimization", INFORMS Journal on Computing (2005)
- McKay MD, "A comparison of three methods for selecting values of input variables in the analysis of output from a computer code", Technometrics, 21(2), pp.239~245 (1979)
- ZITZLER E, "Comparison of multiobjective evolutionary algorithms: empirical results", Evolutionary Computation, 8(2), pp.173~195 (2000)
- Nelder J A, "A simplex method for function minimization", Computer Journal, 7(4), pp.308~313 (1965)
- Qin A, "Self-adaptive differential evolution algorithm for numerical optimization", Proceedings of 2005 IEEE congress on evolutionary computation, pp.1785~91 (2005)
- Liang J, "Dynamic multi-swarm particle swarm optimizer with local search", Proceedings of 2005 IEEE congress on evolutionary computation, pp.522~8 (2005)