Affiliation(s):
School of Computer Science, Beijing University of Posts and Telecommunications, Beijing, China;
moreAffiliation(s): School of Computer Science, Beijing University of Posts and Telecommunications, Beijing, China; School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China; Department of Infrastructure Network Technology Research, China Mobile Research Institute, Beijing, China;
less
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: 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
Open peer comments: Debate/Discuss/Question/Opinion
<1>