Satellite-ground collaborative network slice resource allocation method based on reinforcement learning

The invention relates to a satellite-ground collaborative network slice resource allocation method based on reinforcement learning, which comprises the following steps of: connecting a low-orbit satellite network with a local network data center through a ground gateway station, and creating an exclusive slice matched with a service type according to a service request; the method comprises the following steps of: establishing a multi-slice resource allocation process model of a single ground gateway station by taking a process of allocating resources to each service request by a ground gateway station node as a Markov decision process; aiming at the resource request of each exclusive slice, constructing a system total utility function considering the total spectrum resource utilization rate of the ground gateway station and the user demand satisfaction; taking a calculation result of the total utility function of the system as a reward value of the multi-slice resource allocation process model of the single g