Offloading Revenue Maximization in Multi-UAV-Assisted Mobile Edge Computing for Video Stream
Bin Li, Huimin Shan
TL;DR
This work tackles the challenge of real-time video processing in dense mobile-edge environments by proposing a multi-UAV MEC framework that leverages D2D offloading from idle UDs. It casts the joint optimization of offloading ratios, resource pricing, UAV trajectories, and transcoding as an MDp and solves it with the TD3 DRL method, enabling real-time, high-revenue decisions. Key findings show that TD3 outperforms PPO and DDPG in convergence speed and system revenue, with performance improving as UAVs, idle UDs, or busy UDs scale and with higher UAV computing capabilities. The approach offers a practical pathway for efficient, incentive-compatible, UAV-assisted video processing in dynamic networks, with potential extensions to more complex multi-agent settings.
Abstract
Traditional video transmission systems assisted by multiple Unmanned Aerial Vehicles (UAVs) are often limited by computing resources, making it challenging to meet the demands for efficient video processing. To solve this challenge, this paper presents a multi-UAV-assisted Device-to-Device (D2D) mobile edge computing system for the maximization of task offloading profits in video stream transmission. In particular, the system enables UAVs to collaborate with idle user devices to process video computing tasks by introducing D2D communications. To maximize the system efficiency, the paper jointly optimizes power allocation, video transcoding strategies, computing resource allocation, and UAV trajectory. The resulting non-convex optimization problem is formulated as a Markov decision process and solved relying on the Twin Delayed Deep Deterministic policy gradient (TD3) algorithm. Numerical results indicate that the proposed TD3 algorithm performs a significant advantage over other traditional algorithms in enhancing the overall system efficiency.