Smart factory redundancy unloading method based on deep reinforcement learning

The invention discloses a smart factory redundancy unloading method based on deep reinforcement learning, and the method comprises the steps: enabling an industrial Internet equipment unloading task to queue in sequence after arriving at an edge box, and enabling the edge box to process the task and return a result for some lightweight tasks, and for some tasks needing more resources, the edge box transmits the tasks to the cloud computing system for processing. And for partial tasks unloaded to the cloud server. In order to maximize the utility of the unloading system under the task delay constraint, an optimal unloading scheme is determined by using a Markov decision method. According to the method, the time threshold value and the reliability are determined according to the server state and the related information of each industrial internet device, so that the upper bound and the lower bound of redundancy unloading are determined, the optimal number of redundancy transmission paths is obtained by adopting