Key points are not available for this paper at this time.
As the Internet of Things (IoT) continues to expand rapidly, traditional ground networks are increasingly unable to meet the growing demands for connectivity and coverage. To address these challenges, integrated satellite-ground networks have emerged as a vital solution, enhancing both coverage and reliability. At the same time, Multi-Access Edge Computing (MEC) enables intelligent task execution on IoT devices by deploying resources at the network edge. In this paper, we propose a joint optimization framework for task placement and removal, access control, business instance selection, and bandwidth allocation within MEC-enabled integrated satellite-ground IoT networks. To manage the inherent complexities and uncertainties in dynamic environments, we integrate fuzzy logic into the optimization process. Additionally, we introduce a deep reinforcement learning-based algorithm, specifically the Multi-Agent Deep Deterministic Policy Gradient (MADDPG), to effectively solve this problem. Experimental results demonstrate that the proposed algorithm outperforms benchmark methods in terms of convergence, while achieving minimized economic costs and reduced task processing failures.
Du et al. (Tue,) studied this question.