The invention provides a wind power forecasting method dividing based on weather process. The wind power forecasting method comprises the following steps of: determining a numerical weather prediction matrix M and a numerical weather prediction standard matrix X; analyzing principle components of the numerical weather prediction standard matrix X; clustering a matrix Y composed of the first m-th principle components in the numerical weather prediction standard matrix X which is subjected to the principle component analysis; and establishing a wind power forecasting model, and forecasting wind power. According to the wind power forecasting method dividing based on weather process, based on the wind speed, wind direction and diurnal variation of pressure in NWP data, a sample is subjected to dimension reduction process by the principle component analysis, weather processes are classified by a clustering analysis method, weather types are divided into a high pressure stable type, a low pressure unstable type and the like according to the size and stability of control air pressure and the variation characteristics of wind speed and wind direction, and a forecasting model is established by adopting a BP neural network with respect to each weather process, and thereby the forecasting accuracy is effectively improved.