基于个体适应度梯度的定向进化算法

Directional Evolutionary Algorithm Based on Fitness Gradient of Individuals

基于进化过程中父代个体和子代个体在种群中的适应度梯度,提出进化方向的概念,并对其进行定性分析,在此基础上提出最优进化方向.通过最优进化方向的指导可加速进化过程,提高进化算法的收敛效率.基于进化方向和最优进化方向的描述,设计并实现基于个体适应度梯度的定向进化算法,并针对该算法给出2种不同的个体繁殖策略.对算法的收敛性和复杂度进行理论分析.最后通过仿真实验说明该算法具有精度高、收敛速度快等优点,在一定程度上克服目前进化算法的搜索低效问题.

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.