An effective intelligent algorithm for stochastic optimization problem

Stochastic optimization problems widely exist in engineering, management, control and many other fields. In order to search a more effective algorithm for solving these problems, generalized regression neural network is used as a fitness prediction model and an intelligent algorithm which combines generalized regression neural network with particle swarm optimization is presented. In this intelligent algorithm, according to the mechanism combined prediction model with particle swarm optimization and prediction strategy, some of the individuals´ fitness is predicted and the rest is estimated by random simulation. Results of simulations show that the algorithm reduces the computational cost greatly in the premise of performance guarantee.