Task offloading optimization for AGVs with fixed routes in industrial IoT environment

In order to solve the delay requirements of computing intensive tasks in industrial Internet of things, edge computing is moving from theoretical research to practical applications. Edge servers (ESs) have been deployed in factories, and on-site auto guided vehicles (AGVs), besides doing their regular transportation tasks, can partly act as mobile collectors and distributors of computing data and tasks. Since AGVs may offload tasks to the same ES if they have overlapping path segments, resource allocation conflicts are inevitable. In this paper, we study the problem of efficient task offloading from AGVs to ESs, along their fixed trajectories. We propose a multi-AGV task offloading optimization algorithm (MATO), which first uses the weighted polling algorithm to preliminarily allocate tasks for individual AGVs based on load balancing, and then uses the Deep Q-Network (DQN) model to obtain the updated offloading strategy for the AGV group. The simulation results show that, compared with the existing methods, the proposed MATO algorithm can significantly reduce the maximum completion time of tasks and be stable un-der various parameter settings.