Predicted wind speed correction method based on wind speed correction factor representation model

The invention belongs to the technical field of new energy power generation power prediction of an electric power system, and particularly relates to a predicted wind speed correction method based on a wind speed correction factor characterization model, which comprises the following steps: defining a wind speed correction factor for characterizing correlation between an actually measured wind speed and a numerical weather forecast predicted wind speed and a prediction error, analyzing probability density distribution of wind speed correction factors of different wind power plants; training a generative adversarial network model to learn wind speed correction factors based on the probability density distribution of the wind speed correction factors of different wind power plants, realizing self-correction of the wind speed, and obtaining a wind speed correction factor representation model; and based on the wind speed correction factor representation model, correcting the predicted wind speed by using the wind