A System Utility Optimization-based Task Offloading and Computing Scheduling Algorithm for Low Earth Orbit Satellite Networks

In this paper, we investigate the joint task offloading and computing scheduling in low earth orbit (LEO) satellite networks, which consists of a number of ground terminals (GTs) and multiple LEO satellites. Considering the characteristics of tasks and the energy consumption of task execution, we define a system utility function, and formulate the problem of task offloading and computing scheduling as a constrained system utility function maximization problem. The formulated optimization problem is a mixed integer non-linear programming problem which cannot be solved conveniently. To solve the formulated optimization problem, we first propose local computing scheduling algorithm to determine the task local partition strategy. And then priority-based offloading and computing scheduling algorithm is proposed to determine the task offloading strategy. The effectiveness of the proposed algorithm is verified through simulations in satellite tool kit (STK) and MATLAB.