Task unloading and resource allocation method in energy harvesting MEC system

The invention belongs to the technical field of mobile communication, and particularly relates to a task unloading and resource allocation method in an energy harvesting MEC system, which comprises the following steps: considering an MEC system consisting of a plurality of terminal devices with an EH function and a base station provided with an edge server, and respectively establishing a task queue model, a task calculation model and an energy harvesting model; modeling a long-term stochastic optimization problem in a time average sense, wherein the objective is to minimize execution time and total energy consumption cost of task completion of terminal equipment; firstly, a random optimization problem is decoupled into an unloading decision sub-problem and a resource allocation sub-problem in each determined time slot through a Lyapunov random optimization theory, and then the two sub-problems are solved respectively through a deep reinforcement learning algorithm and an adaptive genetic algorithm; the total