MADDPG-Based Optimization for UAV-MEC Systems with RIS in 6G IoT Environments

In the dynamic and demanding 6 G IoT environments, UAV-enabled Mobile Edge Computing (MEC) systems face significant challenges such as varying communication conditions, energy constraints, and high task demands. To address these challenges effectively, we propose a novel optimization framework that integrates Reconfigurable Intelligent Surfaces (RIS) and employs the Multi-Agent Deep Deterministic Policy Gradient (MADDPG) algorithm. The primary goals of this framework are to minimize latency, maximize throughput, and ensure energy efficiency by dynamically coordinating UAV trajectories, task offloading decisions, and RIS phase shifts. Through extensive simulations, we demonstrate that the proposed framework significantly reduces delay and improves throughput compared to traditional methods, highlighting the substantial benefits of combining RIS with UAV-MEC systems in dynamic IoT scenarios. These findings suggest that the integration of RIS can effectively enhance system performance and adaptability in next-generation wireless networks, providing a promising approach to tackle the complex challenges of 6G IoT environments.