Equalization method of energy storage battery pack management system based on neural network and medium

The invention discloses an equalization method of an energy storage battery pack management system based on a neural network and a medium, and relates to the technical field of battery energy storage, and the method comprises the steps: obtaining basic data and health state parameters of each battery pack; establishing an attention mechanism-based LSTM neural network model, and outputting a battery pack equalization control strategy; training an LSTM model and generating a battery pack equalization control strategy by using the trained LSTM model; adjusting a balance control strategy according to the health state of the battery pack to reduce the charge and discharge quantity of the corresponding battery pack; using a reinforcement learning model to provide the balance control strategy as environment input to a strategy network Actor, and generating a battery pack plan scheduling action; the planned scheduling action is input into the value network Critic, and the Critic outputs the value Q of the planned sch