Proportional Fairness-Aware Task Scheduling in Space-Air-Ground Integrated Networks
Gang Sun, Yuhui Wang, Hongfang Yu, Mohsen Guizani
Abstract
Space-Air-Ground Integrated Networks (SAGIN) is considered as the key structure of the next generation network. The space satellites and air nodes are potential candidates to assist and offload the computing tasks. An Unmanned Aerial Vehicle (UAV) collects computing tasks from IoT devices and then makes online offloading decisions. However, UAVs belonging to different service providers compete for computing resources from ground base stations during task scheduling, resulting in extremely long queue delays and load imbalance. In this paper, we designed a task scheduling algorithm based on Proportional Fairness-Aware Auction with Proximal Policy Optimization (PFAPPO), which decouples the task scheduling process in competitive scenarios into two parts: resource allocation and task offloading decision-making. We first propose an auction algorithm to allocate computing resources reasonably to each UAV, after resource allocation is completed, the UAV learns its available computing resources at each offloading destination. Based on the heterogeneous characteristics of the tasks, the UAV makes intelligent offloading decisions using the distributed deep reinforcement learning PPO algorithm. The simulation results show that our proposed PFAPPO has obvious performance improvement compared with existing methods in terms of system profit, load balancing, and system fairness.