Comparison between hybrid genetic-SPSA algorithm and GA for solving random fuzzy dependent-chance programming

This paper proposes a hybrid genetic-SPSA algorithm based on random fuzzy simulation for solving dependent-chance programming in random fuzzy environments. In the algorithm, random fuzzy simulation is designed to estimate the mean chance of a random fuzzy event, genetic algorithm (GA) is employed to search for the optimal solution in the entire space, and simultaneous perturbation stochastic approximation (SPSA) is used to improve the chromosomes obtained by crossover and mutation operations at each generation in GA. In order to illustrate the effectiveness of the presented algorithm, the comparison between the algorithm and GA is made, and an example is provided.