Distributed Computation Offloading using Deep Reinforcement Learning in Internet of Vehicles

In this paper, we first take the moving vehicles as a RP (resource pool), by which we proposed a distributed computation offloading scheme to fully utilize the available resources and reduce task execution time in I0V (Internet of Vehicles). After that, we divide a complex task into many sub-tasks and indicate that how to assign these small tasks to satisfy the task execution time in RP is a NP problem. The executing time of a task is modeled as the longest calculation time among all small tasks, which is actually a min-max problem. For a dynamically vehicular environment, a distributed computing offloading strategy based on deep reinforcement learning is proposed to find the best offloading scheme to minimize the execution time of a task. Numerical results demonstrate that our scheme is better than Partial Flooding Algorithm and can make full use of the available computing resources of surrounding vehicles by considering the mobility of vehicles, the delay of communication transmission, and the separability of the tasks, thus greatly reducing the execution time of the computing tasks.