JZUS - Journal of Zhejiang University SCIENCE

Frontiers of Information Technology & Electronic Engineering

Accepted manuscript available online (unedited version)

Incentive-based task offloading for digital twin in 6G native AI networks: al earning approach

Author(s): Tianjiao CHEN, Xiaoyun WANG, Meihui HUA, Qinqin TANG
Affiliation(s): China Mobile Research Institute, Beijing 100053, China; more
Corresponding email(s): chentianjiao@chinamobile.com
Key Words: Digital twin network; Native AI; Stackelberg game; Task offloading; Deep reinforcement learning

Share this article to： More <<< Previous Paper \|Next Paper >>>

Tianjiao CHEN, Xiaoyun WANG, Meihui HUA, Qinqin TANG. Incentive-based task offloading for digital twin in 6G native AI networks: al earning approach[J]. Frontiers of Information Technology & Electronic Engineering,in press.https://doi.org/10.1631/FITEE.2400240

@article{title="Incentive-based task offloading for digital twin in 6G native AI networks: al earning approach",
author="Tianjiao CHEN, Xiaoyun WANG, Meihui HUA, Qinqin TANG",
journal="Frontiers of Information Technology & Electronic Engineering",
year="in press",
publisher="Zhejiang University Press & Springer",
doi="https://doi.org/10.1631/FITEE.2400240"
}

%0 Journal Article
%T Incentive-based task offloading for digital twin in 6G native AI networks: al earning approach
%A Tianjiao CHEN
%A Xiaoyun WANG
%A Meihui HUA
%A Qinqin TANG
%J Frontiers of Information Technology & Electronic Engineering
%P
%@ 2095-9184
%D in press
%I Zhejiang University Press & Springer
doi="https://doi.org/10.1631/FITEE.2400240"

TY - JOUR
T1 - Incentive-based task offloading for digital twin in 6G native AI networks: al earning approach
A1 - Tianjiao CHEN
A1 - Xiaoyun WANG
A1 - Meihui HUA
A1 - Qinqin TANG
J0 - Frontiers of Information Technology & Electronic Engineering
SP -
EP -
%@ 2095-9184
Y1 - in press
PB - Zhejiang University Press & Springer
ER -
doi="https://doi.org/10.1631/FITEE.2400240"

Abstract
Chinese Summary
Academic Network
Reviewer Comment

Abstract: A communication network can natively provide artificial intelligence (AI) training services for resourcelimited network entities to quickly build accurate digital twins and achieve high-level network autonomy. Considering that network entities that require digital twins and those that provide AI services may belong to different operators, incentive mechanisms are needed to maximize the utility of both. In this paper, we establish a Stackelberg game to model the AI training task offloading for digital twins in native AI networks with the operator of base stations as the leader and resource-limited network entities as the followers. We analyze the Stackelberg equilibrium to obtain equilibrium solutions. Considering the time-varying wireless network environment, we further design a deep reinforcement learning algorithm to achieve dynamic pricing and task offloading. Finally, extensive simulation experiments are conducted to verify the effectiveness of our proposal.

Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article

Reference

Open peer comments: Debate/Discuss/Question/Opinion

<1>

- Go to

Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article

Reference