Energy output prediction method and system for converging-diverging energy storage system, and medium

The invention discloses an energy output prediction method and system for a converging-diverging energy storage system and a medium, and the method comprises the steps: extracting an energy storage equipment feature vector of the energy output of each energy storage equipment type for the energy storage equipment type which affects the energy output of the converging-diverging energy storage system in the converging-diverging energy storage system; the method comprises the following steps of: extracting time sequence characteristics according to energy output data of a converging-diverging energy storage system on a historical typical day by adopting a gate control cycle unit GRU to obtain a historical characteristic vector at a current moment t; and integrating the feature vector of the energy storage equipment and the historical feature vector at the current moment t, and predicting by using a Bayesian neural network BNN which is pre-trained through an AO hawk optimization algorithm to obtain the probabilit