JZUS - Journal of Zhejiang University SCIENCE

Frontiers of Information Technology & Electronic Engineering

Accepted manuscript available online (unedited version)

Combining Graph Neural Network with Deep Reinforcement Learning for Resource Allocation in Computing Force Networks

Author(s): Xueying HAN, Mingxi XIE, Ke YU, Xiaohong HUANG, Zongpeng DU, Huijuan YAO
Affiliation(s): School of Computer Science, Beijing University of Posts and Telecommunications, Beijing, China; more
Corresponding email(s): hanxueying@bupt.edu.cn, yuke@bupt.edu.cn
Key Words: Computing force network; Routing optimization; Deep learning; Graph neural network; Resource allocation

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

Xueying HAN, Mingxi XIE, Ke YU, Xiaohong HUANG, Zongpeng DU, Huijuan YAO. Combining Graph Neural Network with Deep Reinforcement Learning for Resource Allocation in Computing Force Networks[J]. Frontiers of Information Technology & Electronic Engineering,in press.https://doi.org/10.1631/FITEE.2300009

@article{title="Combining Graph Neural Network with Deep Reinforcement Learning for Resource Allocation in Computing Force Networks",
author="Xueying HAN, Mingxi XIE, Ke YU, Xiaohong HUANG, Zongpeng DU, Huijuan YAO",
journal="Frontiers of Information Technology & Electronic Engineering",
year="in press",
publisher="Zhejiang University Press & Springer",
doi="https://doi.org/10.1631/FITEE.2300009"
}

%0 Journal Article
%T Combining Graph Neural Network with Deep Reinforcement Learning for Resource Allocation in Computing Force Networks
%A Xueying HAN
%A Mingxi XIE
%A Ke YU
%A Xiaohong HUANG
%A Zongpeng DU
%A Huijuan YAO
%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.2300009"

TY - JOUR
T1 - Combining Graph Neural Network with Deep Reinforcement Learning for Resource Allocation in Computing Force Networks
A1 - Xueying HAN
A1 - Mingxi XIE
A1 - Ke YU
A1 - Xiaohong HUANG
A1 - Zongpeng DU
A1 - Huijuan YAO
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.2300009"

Abstract
Chinese Summary
Academic Network
Reviewer Comment

Abstract: Fueled by the explosive growth of ultra-low latency and real-time applications with specific computing and network performance requirements, the Computing Force Network (CFN) has become a hot research subject. The primary CFN challenge is to leverage both network resources and computing resources jointly. Although recent advances in Deep Reinforcement Learning (DRL) have brought significant improvement in network optimization, these methods still suffer from topology changes and fail to generalize for those topologies not seen in training. This paper proposes a Graph Neural Network (GNN) based DRL framework to accommodate network traffic and computing resources jointly and efficiently. By taking advantage of the generalization capability in the GNN, the proposed method can operate over variable topologies and obtain high performance superior to the other DRL methods.

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