Abstract
In recent years, the accuracy of the wind power prediction has been urgently studied and improved to satisfy the requirements of power system operation. In this paper, the relevance vector machine (RVM)-based models are established to predict the wind power and its interval for a given confidence level. An NWP improvement module is presented considering the characteristic of NWP error. Moreover, two parameter optimization algorithms are applied to further improve the prediction model and to compare each performance. To take three wind farms in China as examples, the performance of two RVM-based models optimized, respectively, by genetic algorithm (GA) and particle swarm optimization (PSO) are compared with predictions based on a genetic algorithm–artificial neural network (GA–ANN) and support vector machine. Results show that the proposed models have better prediction accuracy with GA–RVM model and more efficient calculation with PSO–RVM.