The invention discloses a photovoltaic power station generated power super-short-term prediction method. The method includes the following steps that firstly, historical measured power data and short-term predicted power data of a photovoltaic power station are acquired; secondly, the historical measured power data and the short-term predicted power data of the photovoltaic power station are preprocessed; thirdly, according to the preprocessed historical measured power data and the preprocessed short-term predicted power data of the photovoltaic power station, super-short-term prediction powers, corresponding to different prediction periods, of the photovoltaic power station are acquired through a photovoltaic power station generated power super-short-term prediction model based on the prediction periods; fourthly, according to the acquired super-short-term prediction powers of the photovoltaic power station, the optimal prediction period of the photovoltaic power station generated power super-short-term prediction model is determined; fifthly, super-short-term power prediction of the photovoltaic power station is conducted based on the photovoltaic power station generated power super-short-term prediction model based on the optimal prediction period. According to the method, the photovoltaic power station generated power super-short-term prediction accuracy is improved.