A Multi-dimensional Resource Allocation Algorithm Based on Task Splitting and Adjustment in Satellite Networks

Abstract

Currently, most resource allocation algorithms in satellite networks only focus on single resource allocation scenarios. But there are many kinds of resources in the actual satellite network, and these resources restrict each other. In addition, most satellite network systems treat the services requested by users as an independent and indivisible task. However, the duration of the task is different and satellites have time windows to execute tasks, as well as multiple resource constraints. With the increase of tasks, the number of tasks that the satellite network system can complete and the resources utilization will be limited. For the above problems, this paper proposes a multi-dimensional resource allocation algorithm based on task splitting and adjustment, including task splitting algorithm (TSA) and dynamic task adjustment algorithm (DTAA). First, build a model that takes task completion rate, resource utilization and distriction window utilization as the optimization targets in a single distriction window, and solve the problem of lower resource utilization by splitting the last task that cannot be executed in the distriction window. Then, build a dynamic task adjustment model among multiple distriction windows, and solve the conflict problem of task execution through the original window task adjustment or the new window task adjustment strategy. Finally, compare the algorithm with the existing decoupled resource algorithm (DRA) and improved greedy algorithm (IGA), and verify its gains in the number of tasks completed, resource utilization and distriction window utilization through simulation experiments.