Automatic Virtual Network Embedding: A Deep Reinforcement Learning Approach with Graph Convolutional Networks
- Submitting institution
-
University of Exeter
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 6342
- Type
- D - Journal article
- DOI
-
10.1109/JSAC.2020.2986662
- Title of journal
- IEEE Journal on Selected Areas in Communications
- Article number
- -
- First page
- 1040
- Volume
- 38
- Issue
- 6
- ISSN
- 0733-8716
- Open access status
- Compliant
- Month of publication
- April
- Year of publication
- 2020
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
4
- Research group(s)
-
-
- Citation count
- 8
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This international collaboration work combines deep reinforcement learning with a novel neural network structure based on graph convolutional networks. This research has made significant contributions to the automation of virtual network services, which can push the fast deployment of 5G (e.g., efficient network slicing management defined in 3GPP Release 16 for the initial full 5G system) and also advance the important research of complex system modelling (e.g., a 5G system with multiple services running simultaneously). This work has led to the follow-up research in different disciplinary areas including COVID-19 epidemic modelling (10.1016/j.inffus.2020.08.002) and natural gas industrial ecosystem (10.1109/JIOT.2020.3029138).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -