Abstract The evolutionary direction is proposed based on the fitness gradient between the individuals of the current population and its parent. The evolutionary direction is analyzed qualitatively. The optimal evolutionary direction is proposed based on the gradient. The directional evolutionary algorithm (DEA) based on gradient of individuals is put forward under the description of evolutionary direction and optimal evolutionary direction. Two different reproduction strategies are proposed for DEA to generate individuals of next generation. The efficiency of DEA is validated theoretically. The experimental results show that the proposed algorithm has a high quality of precision, stability and convergence rate. Moreover, the improved evolutionary algorithm overcomes the shortcoming of low efficiency in traditional evolutionary algorithms to a certain extent.
[1] Bck T, Hammel U, Schwefel H P. Evolutionary Computation: Comments on the History and Current State. IEEE Trans on Evolutionary Computation, 1997, 1(1): 3-17 [2] Yao Xin, Xu Yong. Recent Advances in Evolutionary Computation. Journal of Computer and Science, 2006, 21(1): 1-18 [3] Xu Zongben, Chen Zhiping, Zhang Xiangsun. Theoretical Development on Genetic Algorithms: A Review. Advances in Mathematics, 2000, 29(2): 97-114 (in Chinese) (徐宗本,陈志平,章祥荪.遗传算法基础理论研究的新近发展.数学进展, 2000, 29(2): 97-114) [4] Bck T. Evolutionary Algorithms in Theory and Practice: Evolution Strategies, Evolutionary Programming, Genetic Algorithms. Oxford, UK: Oxford University Press, 1996 [5] Yamamoto K, Inoue O. New Evolutionary Direction Operator for Genetic Algorithms. AIAA Journal, 1995, 33(10): 1990-1993 [6] Xiao Zhiquan, Cui Lingli. Several Strategies of Evolutionary Direction Operator for Genetic Algorithm. Control and Decision, 2003, 18(6): 730-732 (in Chinese) (肖志权,崔玲丽.遗传算法采用进化方向算子的几种策略.控制与决策, 2003, 18(6): 730-732) [7] Fan Huiyuan, Wang Shangjin, Xi Guang. Directional Evolution Operator Applied to Genetic Algorithm. Journal of Xian Jiaotong University, 1999, 33(5): 45-49 (in Chinese) (樊会元,王尚锦,席 光.遗传算法引入进化方向算子的一个改进及应用.西安交通大学学报, 1999, 33(5): 45-49) [8] Fan Huiyuan, Jane W Z L, Xu Zongben. An Empirical Comparison of Three Novel Genetic Algorithms. Engineering Computations: International Journal for Computer-Aided Engineering, 2000, 17(8): 981-1002 [9] Su Xiaohong, Yang Bo, Wang Yadong. A Genetic Algorithm Based on Evolutionarily Stable Strategy. Journal of Software, 2003, 14(11): 1863-1868 (in Chinese) (苏小红,杨 博,王亚东.基于进化稳定策略的遗传算法.软件学报, 2003, 14(11): 1863-1868) [10] Ying Weiqin, Li Yuanxiang, Shen P C Y. Improving the Computational Efficiency of Thermo Dynamical Genetic Algorithms. Journal of Software, 2008, 19(7): 1613-1622 (in Chinese) (应伟勤,李元香,Shen P C Y.热力学遗传算法计算效率的改进.软件学报, 2008, 19(7): 1613-1622) [11] Wang Liwei, Hong Yong, Hong Jiarong. On the Convergence of Genetic Algorithms. Chinese Journal of Computers, 1996, 19(10): 794-797 (in Chinese) (王丽薇,洪 勇,洪家荣.遗传算法的收敛性研究.计算机学报, 1996, 19(10): 794-797) [12] Guo Chonghui, Tang Huanwen. Global Convergence Properties of Evolutionary Strategies. Mathematica Numerica Sinica, 2001, 23(1): 105-110 (in Chinese) (郭崇慧,唐焕文.演化策略的全局收敛性.计算数学, 2001, 23(1): 105-110) [13] Noman N, Iba H. Accelerating Differential Evolution Using an Adaptive Local Search. IEEE Trans on Evolutionary Computation, 2008, 12(1): 107-125 [14] Jiao Licheng, Liu Jing, Zhong Weicai.Co-Evolutionary Computation Multi-Agent Systems. Beijing, China: Science Press, 2006 (in Chinese) (焦李成,刘 静,钟伟才.协同进化计算与多智能体系统.北京:科学出版社, 2006) [15] Herrera F, Lozano M, Verdegay J L. Tracking Real-Code Genetic Algorithms: Operators and Tools for Behavioral Analysis. Artificial Intelligence Review, 1998, 12(4): 265-319 [16] Kennedy J, Eberhart R. Particle Swarm Optimization // Proc of the IEEE International Conference on Neural Networks. Perth, Australia, 1995, Ⅳ: 1942-1948 [17] Zeng Jianchao, Jie Jing, Cui Zhihua. Particle Swarm Algorithm. Beijing, China: Science Press, 2004 (in Chinese) (曾建潮,介 婧,崔志华.微粒群算法.北京:科学出版社, 2004) [18] Hassan R, Cohanim B, de Weck O. A Comparison of Particle Swarm Optimization and the Genetic Algorithm // Proc of the 46th AIAA/ASME/ASCE/AHS/ASC Structures, Structural Dynamics Materials Conference. Austin, USA, 2005: 1-13 [19] Zhang Guangwei, He Rui, Liu Yu, et al. An Evolutionary Algorithm Based on Cloud Model. Chinese Journal of Computers, 2008, 37(7): 1082-1091 (in Chinese) (张光卫,何 锐,刘 禹,等.基于云模型的进化算法.计算机学报, 2008, 37(7): 1082-1091)
2010, Vol. 23 
