SG-MAPG: A Three-Layer Hierarchical Model for Service Fairness and Cost Optimization in UAV-Assisted MEC Systems

Unmanned aerial vehicles (UAVs) play an important role in mobile edge computing (MEC) systems because of their high mobility and flexibility. However, existing task offloading strategies suffer from considerable resource allocation imbalances in multi-agent decision-making, leading to UAVs overload, increased task delays, and higher operational costs. To address these issues, this paper presents a Three-Layer Multi-Agent Strategic Decision-Making Model (3L-MSADM) that integrates Markov Decision Processes (MDP), Stackelberg game theory, and auction mechanisms to optimize task offloading, mitigate resource imbalances, and enhance computational efficiency. Additionally, a task offloading ratio optimization mechanism is proposed to dynamically adjust task distribution according to system load, thereby minimizing task latency and improving overall efficiency. Furthermore, we introduce the Stackelberg-guided multi-agent policy gradient (SG-MAPG) algorithm, utilizing a centralized training and decentralized execution (CTDE) paradigm to improve decision-making efficiency and service fairness. Simulation results demonstrate that our approach improves service fairness by 12.3% and reduces system costs by 22.7% compared to benchmark algorithms, significantly enhancing the task processing capabilities of UAVs-assisted MEC systems. This study provides an innovative solution for multi-agent decision-making and resource management in wireless networks, offering substantial theoretical and practical contributions.