A New Neural Network Method of Wind Speed Interval Prediction Based on Empirical Error and MCMC

With the increasing energy demand, energy development has been widely concerned. As a kind of clean energy, wind power is the focus of energy development. But in the use of wind power, randomness is a major hidden danger in the safe operation of the system. So we can find that the research topic is critical to make wind speed prediction more efficient and accurate. In this study, the original sequence is divided by the variational mode decomposition (VMD) method, and the neural network usually act as a prediction model on the wind speed, and the training error is obtained. In interval prediction, an interval prediction method combining empirical error with quantile statistical Markov Chain Monte Carlo (MCMC) is creatively proposed. According to the randomness of MCMC, a large number of independent error prediction cases can be generated. According to the quantiles of the results of multiple random simulations, the quantiles are estimated to form a series of interval predictions with a given confidence. Finally, the point prediction value is added to the error prediction interval to accomplish the wind speed prediction interval completely. The prediction eventually show that: (1) the model processed by VMD is more accurate and stable than the single neural network prediction method; (2) in the interval prediction, the combination of empirical error and MCMC method shows better prediction effect; (3) the interval prediction with different confidence represents the consistency of statistical significance. In this paper, the proposal of a neural network method of wind speed interval prediction based on empirical error and MCMC is helpful for the relevant departments to adjust the dispatching plan in time, formulate reasonable control strategy of the wind farm, and improve stability and reliability of the system operation.