Function Optimization Based on an Improved Adaptive Genetic Algorithm

Traditional genetic algorithms have some disadvantages in the one-dimensional multi-peaked function optimization problems. For example, it is easy to fall into local extremes, the rate of convergence is low and the stability is not ideal. This paper proposes a new adaptive genetic algorithm. Nonlinear functions are used to measure the probabilities of crossover and mutation operators. In addition, a modified algorithm flow based on the adaptive differential evolution algorithm and an elitist strategy are applied. Compared with other existing algorithms, the results of experiments indicate that the proposed algorithm has a higher convergence probability, a smaller number of iterations and a more reliable stability.