Wind speed prediction method based on deep neural network without future information leakage

The invention discloses a deep neural network-based wind speed prediction method without future information leakage. The method comprises the following steps of 1, performing data screening and data preprocessing on wind speed sequence data; screening an effective component Tc according to the sub-modal energy ratio and taking the effective component Tc as an output value of the prediction model; preprocessing the wind speed sequence data by adopting a real-time rolling decomposition strategy to obtain an input value of a prediction model without information leakage; constructing a data set by using the input values and the output values; 2, determining a prediction step length: determining a future time step number needing to be predicted according to an actual prediction demand; step 3, constructing a prediction model: constructing a bidirectional long-short-term memory network combined with an attention mechanism as the prediction model, and training and testing the prediction model by using the data set;