Non-Euclidean Graph-Convolution Virtual Network Embedding for Space–Air–Ground Integrated Networks
For achieving seamless global coverage and real-time communications while providing intelligent applications with increased quality of service (QoS), AI-enabled space–air–ground integrated networks (SAGINs) have attracted widespread attention from all walks of life. However, high-intensity interacti...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-02-01
|
| Series: | Drones |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2504-446X/7/3/165 |
| _version_ | 1797612375789010944 |
|---|---|
| author | Ning Chen Shigen Shen Youxiang Duan Siyu Huang Wei Zhang Lizhuang Tan |
| author_facet | Ning Chen Shigen Shen Youxiang Duan Siyu Huang Wei Zhang Lizhuang Tan |
| author_sort | Ning Chen |
| collection | DOAJ |
| description | For achieving seamless global coverage and real-time communications while providing intelligent applications with increased quality of service (QoS), AI-enabled space–air–ground integrated networks (SAGINs) have attracted widespread attention from all walks of life. However, high-intensity interactions pose fundamental challenges for resource orchestration and security issues. Meanwhile, virtual network embedding (VNE) is applied to the function decoupling of various physical networks due to its flexibility. Inspired by the above, for SAGINs with non-Euclidean structures, we propose a graph-convolution virtual network embedding algorithm. Specifically, based on the excellent decision-making properties of deep reinforcement learning (DRL), we design an orchestration network combined with graph convolution to calculate the embedding probability of nodes. It fuses the information of the neighborhood structure, fully fits the original characteristics of the physical network, and utilizes the specified reward mechanism to guide positive learning. Moreover, by imposing security-level constraints on physical nodes, it restricts resource access. All-around and rigorous experiments are carried out in a simulation environment. Finally, results on long-term average revenue, VNR acceptance ratio, and long-term revenue–cost ratio show that the proposed algorithm outperforms advanced baselines. |
| first_indexed | 2024-03-11T06:40:25Z |
| format | Article |
| id | doaj.art-fedb514b5ac8449fb1ca15c65b3f9a28 |
| institution | Directory Open Access Journal |
| issn | 2504-446X |
| language | English |
| last_indexed | 2024-03-11T06:40:25Z |
| publishDate | 2023-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Drones |
| spelling | doaj.art-fedb514b5ac8449fb1ca15c65b3f9a282023-11-17T10:39:21ZengMDPI AGDrones2504-446X2023-02-017316510.3390/drones7030165Non-Euclidean Graph-Convolution Virtual Network Embedding for Space–Air–Ground Integrated NetworksNing Chen0Shigen Shen1Youxiang Duan2Siyu Huang3Wei Zhang4Lizhuang Tan5Qingdao Institute of Software, College of Computer Science and Technology, China University of Petroleum (East China), Qingdao 266580, ChinaSchool of Information Engineering, Huzhou University, Huzhou 313000, ChinaQingdao Institute of Software, College of Computer Science and Technology, China University of Petroleum (East China), Qingdao 266580, ChinaXiongan Institute of Innovation, Chinese Academy of Sciences, Baoding 071702, ChinaShandong Provincial Key Laboratory of Computer Networks, Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences), Jinan 250013, ChinaShandong Provincial Key Laboratory of Computer Networks, Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences), Jinan 250013, ChinaFor achieving seamless global coverage and real-time communications while providing intelligent applications with increased quality of service (QoS), AI-enabled space–air–ground integrated networks (SAGINs) have attracted widespread attention from all walks of life. However, high-intensity interactions pose fundamental challenges for resource orchestration and security issues. Meanwhile, virtual network embedding (VNE) is applied to the function decoupling of various physical networks due to its flexibility. Inspired by the above, for SAGINs with non-Euclidean structures, we propose a graph-convolution virtual network embedding algorithm. Specifically, based on the excellent decision-making properties of deep reinforcement learning (DRL), we design an orchestration network combined with graph convolution to calculate the embedding probability of nodes. It fuses the information of the neighborhood structure, fully fits the original characteristics of the physical network, and utilizes the specified reward mechanism to guide positive learning. Moreover, by imposing security-level constraints on physical nodes, it restricts resource access. All-around and rigorous experiments are carried out in a simulation environment. Finally, results on long-term average revenue, VNR acceptance ratio, and long-term revenue–cost ratio show that the proposed algorithm outperforms advanced baselines.https://www.mdpi.com/2504-446X/7/3/165future internet architecturespace–air–ground integrated networkresource orchestrationvirtual network embeddinggraph convolutionnon-Euclidean structure |
| spellingShingle | Ning Chen Shigen Shen Youxiang Duan Siyu Huang Wei Zhang Lizhuang Tan Non-Euclidean Graph-Convolution Virtual Network Embedding for Space–Air–Ground Integrated Networks Drones future internet architecture space–air–ground integrated network resource orchestration virtual network embedding graph convolution non-Euclidean structure |
| title | Non-Euclidean Graph-Convolution Virtual Network Embedding for Space–Air–Ground Integrated Networks |
| title_full | Non-Euclidean Graph-Convolution Virtual Network Embedding for Space–Air–Ground Integrated Networks |
| title_fullStr | Non-Euclidean Graph-Convolution Virtual Network Embedding for Space–Air–Ground Integrated Networks |
| title_full_unstemmed | Non-Euclidean Graph-Convolution Virtual Network Embedding for Space–Air–Ground Integrated Networks |
| title_short | Non-Euclidean Graph-Convolution Virtual Network Embedding for Space–Air–Ground Integrated Networks |
| title_sort | non euclidean graph convolution virtual network embedding for space air ground integrated networks |
| topic | future internet architecture space–air–ground integrated network resource orchestration virtual network embedding graph convolution non-Euclidean structure |
| url | https://www.mdpi.com/2504-446X/7/3/165 |
| work_keys_str_mv | AT ningchen noneuclideangraphconvolutionvirtualnetworkembeddingforspaceairgroundintegratednetworks AT shigenshen noneuclideangraphconvolutionvirtualnetworkembeddingforspaceairgroundintegratednetworks AT youxiangduan noneuclideangraphconvolutionvirtualnetworkembeddingforspaceairgroundintegratednetworks AT siyuhuang noneuclideangraphconvolutionvirtualnetworkembeddingforspaceairgroundintegratednetworks AT weizhang noneuclideangraphconvolutionvirtualnetworkembeddingforspaceairgroundintegratednetworks AT lizhuangtan noneuclideangraphconvolutionvirtualnetworkembeddingforspaceairgroundintegratednetworks |