Cost-Effective Task Offloading and Resource Scheduling for Mobile Edge Computing in 6G Space-Air-Ground Integrated Network

With the advent of the sixth-generation (6G) wireless communications, transmission speeds are projected to exceed tenfold those of 5G, reaching theoretical peak download speeds of up to 1 Tbps. Data transmission capacity and speed will be significantly enhanced, enabling emerging applications, such as mixed reality, federated learning, and digital twins, driving exponential data traffic growth. To address this, the space-air-ground integrated network (SAGIN) combines satellite, aerial, and ground communication technologies, offering seamless global coverage and high-speed connectivity. In this article, we proposes an SAGIN framework integrated with mobile edge computing (MEC) to jointly optimize system energy consumption and delay costs. Specifically, we decompose the optimization problem into three subproblems: 1) uncrewed aerial vehicle (UAV) computational resource allocation; 2) satellite computational resource allocation; and 3) task offloading and channel allocation. The subproblems are then transformed and addressed using Newton's interior point method and the deep reinforcement learning DQN algorithm to derive optimal allocation strategies for UAV and satellite computing resources, along with task offloading and channel resources, that our proposed algorithm effectively reduces system energy consumption and delay costs compared to other algorithms.