The invention provides a vehicle-side collaborative task unloading scheduling and
resource allocation method in
the Internet of Vehicles. The method mainly comprises the following steps: 1, generating a task description set mu = Hi * the absolute value of i which is greater than or equal to 1 and less than or equal to I, Hi = (si, ci), and constructing a
mathematical model P1 of task unloading scheduling and
resource allocation in a network; 2, under the condition that the CPU frequency is given, solving a problem P1 based on a
deep learning DQN
algorithm, obtaining a task unloading scheduling decision (xi, alphai), and obtaining a target value V; 3, on the basis of the obtained unloading scheduling decision (xi, alphai), constructing a
mathematical model P2, and solving a CPU frequency and a target value V' by adopting a
gradient descent method;; 4, comparing the target value V with the target value V', if the difference value of V-V' is less than x, exiting, or repeating the step 2 and the step 3. By applying the method, the problems of task unloading scheduling and
resource allocation optimization in the
mobile vehicle edge network are solved, and the task
execution time delay and
energy consumption in the network are effectively reduced.