A Multi-agent Reinforcement Learning based Offloading Strategy for Multi-access Edge Computing

Li Ma, Haobin Shi, Jingchen Li, Kao Shing Hwang

科研成果: 书/报告/会议事项章节会议稿件同行评审

4 引用 (Scopus)

摘要

As a front-end distributed computing paradigm, Multi-access edge computing (MEC) requires an efficient offloading strategy in the case of computation-intensive tasks. Traditional heuristic and reinforcement learning-based methods are limited by the number of edge serves. In this work, the task offloading in MEC is regarded as a multi-agent reinforcement learning (MARL) scenario, and an end-to-end model is developed to train the offloading strategy. The proposal is a decentralized framework, which is consistent with the edge computing servers. We fully consider the state sequences for edge servers and limited communication abilities, proposing a recurrent neural network as the communication module. Using a gating mechanism, we design a dual-recurrent network for combining the state sequences and historical communication results. Several experiments show that our method can achieve low latency and distributed data processing, and it outperforms heuristic methods and other reinforcement learning-based frameworks.

源语言英语
主期刊名2021 International Automatic Control Conference, CACS 2021
出版商Institute of Electrical and Electronics Engineers Inc.
ISBN(电子版)9781665444125
DOI
出版状态已出版 - 2021
活动2021 International Automatic Control Conference, CACS 2021 - Chiayi, 中国台湾
期限: 3 11月 20216 11月 2021

出版系列

姓名2021 International Automatic Control Conference, CACS 2021

会议

会议2021 International Automatic Control Conference, CACS 2021
国家/地区中国台湾
Chiayi
时期3/11/216/11/21

指纹

探究 'A Multi-agent Reinforcement Learning based Offloading Strategy for Multi-access Edge Computing' 的科研主题。它们共同构成独一无二的指纹。

引用此