Efficient End-Edge-Cloud Task Offloading in 6G Networks Based on Multiagent Deep Reinforcement Learning

doi:10.1109/JIOT.2024.3372614

Efficient End-Edge-Cloud Task Offloading in 6G Networks Based on Multiagent Deep Reinforcement Learning

2024-06-01

0

PRE

AI

DOI：10.1109/JIOT.2024.3372614

Original

Original request for help

Save

Abstract

En 中文

With the progressive evolution of the sixth-generation (6G) network, an array of diverse application tasks is experiencing a steady surge, consequently intensifying the computational pressure. However, even with highly optimized task offloading approaches, ensuring overall service quality for rapidly expanding network applications remains challenging due to hardware resource limitations. This article proposes a deep reinforcement learning-based algorithm utilizing a multiagent approach in the end-edge-cloud architecture for 6G networks. The offloading issue can be reformulated to a decentralized partially observable Markov decision process, which transfers the NP-hard problem. We design an efficient algorithm based on multiagent deep deterministic policy gradient (MADDPG) to observe the states of user equipments (UEs), edge servers, and cloud servers, thereby reducing offloading delay and energy consumption. Numerical results demonstrate that our proposed algorithm demonstrates superior performance compared to conventional and state-of-the-art approaches.

Keywords:

Task analysis

6G mobile communication

Servers

Computational modeling

Cloud computing

Resource management

Delays

6G

end-edge-cloud

multiagent deep reinforcement learning (MADRL)

task offloading

Efficient End-Edge-Cloud Task Offloading in 6G Networks Based on Multiagent Deep Reinforcement Learning

Abstract

Journal

Organization