A two-layer UAV cooperative computing offloading strategy based on deep reinforcement learning

Jianfei Zhang

doi:10.23919/JCC.ja.2024-0650

A two-layer UAV cooperative computing offloading strategy based on deep reinforcement learning

2025-11-12

0

PRE

AI

DOI：10.23919/JCC.ja.2024-0650

Original

Original request for help

Save

Abstract

En 中文

In the wake of major natural disasters or human-made disasters, the communication infrastructure within disaster-stricken areas is frequently damaged. Unmanned aerial vehicles (UAVs), thanks to their merits such as rapid deployment and high mobility, are commonly regarded as an ideal option for constructing temporary communication networks. Considering the limited computing capability and battery power of UAVs, this paper proposes a two-layer UAV cooperative computing offloading strategy for emergency disaster relief scenarios. The multi-agent twin delayed deep deterministic policy gradient (MATD3) algorithm integrated with prioritized experience replay (PER) is utilized to jointly optimize the scheduling strategies of UAVs, task offloading ratios, and their mobility, aiming to diminish the energy consumption and delay of the system to the minimum. In order to address the aforementioned non-convex optimization issue, a Markov decision process (MDP) has been established. The results of simulation experiments demonstrate that, compared with the other four baseline algorithms, the algorithm introduced in this paper exhibits better convergence performance, verifying its feasibility and efficacy.

Keywords:

cooperative computational offloading

deep reinforcement learning

mobile edge computing

prioritized experience replay

two-layer unmanned aerial vehicles

A two-layer UAV cooperative computing offloading strategy based on deep reinforcement learning

Abstract

Journal

Organization