The invention discloses an ultra-short term
wind power forecasting method based on a
time series method. The forecasting method comprises the following steps: 1. gathering
wind measurement data of an anemometer
tower adjacent to a
wind power station; 2.
processing data: carrying out
smoothing and stabilizing treatments on the
wind speed recorded by the anemometer
tower; 3. carrying out wind speedprediction modeling by utilizing the
time series method, respectively modeling the
wind speed data subjected to the
smoothing and stabilizing treatments in the step 2 according to a forecasting
time resolution, and establishing 16 prediction models, and figuring out the forecast
wind speed within 0-4 hours; and 4. calculating the ultra-short term
wind power: calculating the prediction models which are used for forecasting the wind speed input wind power to obtain a wind power prediction result within the forecast validity. By utilizing the method provided by the invention, the wind
power output within 0-4 hours of the wind
power station can be forecast in a rolling mode, reasonable data support can be provided for
electric network frequency modulation and the maintenance of the stable operation of the
electric network, so that a dispatching department can adopt solutions in advance for various mutational situations caused by haste changes of the wind power during the
electric network operation by the dispatching department.