跳到主要导航 跳到搜索 跳到主要内容

Decentralized offloading strategies based on reinforcement learning for multi-access edge computing

  • Chunyang Hu
  • , Jingchen Li
  • , Haobin Shi
  • , Bin Ning
  • , Qiong Gu
  • Hubei University of Arts and Science
  • Northwestern Polytechnical University Xian

科研成果: 期刊稿件 › 文章 › 同行评审

3 引用 (Scopus)

摘要

Using reinforcement learning technologies to learn offloading strategies for multi-access edge computing systems has been developed by researchers. However, large-scale systems are unsuitable for reinforcement learning, due to their huge state spaces and offloading behaviors. For this reason, this work introduces the centralized training and decentralized execution mechanism, designing a decentralized reinforcement learning model for multi-access edge computing systems. Considering a cloud server and several edge servers, we separate the training and execution in the reinforcement learning model. The execution happens in edge devices of the system, and edge servers need no communication. Conversely, the training process occurs at the cloud device, which causes a lower transmission latency. The developed method uses a deep deterministic policy gradient algorithm to optimize offloading strategies. The simulated experiment shows that our method can learn the offloading strategy for each edge device efficiently.

源语言英语
期刊论文编号343
期刊Information (Switzerland)
卷12
期9
DOI
出版状态已出版 - 9月 2021

学术指纹

探究 'Decentralized offloading strategies based on reinforcement learning for multi-access edge computing' 的科研主题。它们共同构成独一无二的学术指纹。

引用此