Offloading Revenue Maximization in Multi-UAV-Assisted Mobile Edge Computing for Video Stream

TL;DR

This paper proposes a multi-UAV-assisted mobile edge computing system that optimizes video stream processing by jointly managing resources, UAV trajectories, and D2D communications using advanced reinforcement learning.

Contribution

It introduces a novel joint optimization framework for UAV trajectory, resource allocation, and D2D communication in video streaming, solved via a TD3-based reinforcement learning approach.

Findings

TD3 algorithm outperforms traditional methods in efficiency

Joint optimization improves video processing performance

System effectively leverages UAVs and user devices for computing

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.