Research on a novel adaptive genetic algorithm
D. Gong, Pan Fengping, Xiaoyan Sun · 2002
The function scaling diversity of population is put forth. Taking the relation between diversity of evolution population and evolution time into account, a factor function is presented. Based on it, a novel adaptive genetic algorithm is brought forward, in which the number of crossover and mutation operation points changes with diversity of population and effect function. The multi-peak value function optimization result shows that the algorithm presented in this paper can solve the premature convergence problem efficiently and converge to a globally optimal solution.