Abstract: The high-precision prediction of distributed photovoltaic power generation is of great significance to the safe and stable operation of the distribution network. In this paper, based on weather information and depth learning method, a short-term power prediction method for distributed photovoltaic power generation equipment is proposed. First, classify and fuse the weather to achieve full coverage of the training set. Then, build a distributed photovoltaic short-term power prediction model based on the long short-term memory (LSTM) deep learning network. Finally, realize distributed photovoltaic power prediction.