A Two-Stage GCN-Based Deep Reinforcement Learning Framework for SFC Embedding in Multi-Datacenter Networks

Xiao, D; Zhang, JA; Liu, X; Qu, Y; Ni, W; Liu, RP

A Two-Stage GCN-Based Deep Reinforcement Learning Framework for SFC Embedding in Multi-Datacenter Networks

Xiao, D

Zhang, JA Liu, X Qu, Y Ni, W

Liu, RP

Permalink

Publisher:: IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Publication Type:: Journal Article
Citation:: IEEE Transactions on Network and Service Management, 2023, 20, (4), pp. 4297-4312
Issue Date:: 2023-12-01

Embargoed

	Filename	Description	Size
	A Two-Stage GCN-Based Deep Reinforcement Learning Framework for SFC Embedding in Multi-Datacenter Networks.pdf	Accepted version	1.19 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Embargoed
Open Access

This item is currently unavailable due to the publisher's embargo.

The embargo period expires on 8 Jun 2025

Full metadata record

Field	Value	Language
dc.contributor.author	Xiao, D https://orcid.org/0000-0003-3244-7176
dc.contributor.author	Zhang, JA
dc.contributor.author	Liu, X
dc.contributor.author	Qu, Y
dc.contributor.author	Ni, W https://orcid.org/0000-0002-4933-594X
dc.contributor.author	Liu, RP
dc.date.accessioned	2024-03-27T02:33:33Z
dc.date.available	2024-03-27T02:33:33Z
dc.date.issued	2023-12-01
dc.identifier.citation	IEEE Transactions on Network and Service Management, 2023, 20, (4), pp. 4297-4312
dc.identifier.issn	1932-4537
dc.identifier.issn	1932-4537
dc.identifier.uri	http://hdl.handle.net/10453/177238
dc.description.abstract	Network Function Virtualization (NFV), which decouples network functions from hardware and transforms them into Virtual Network Functions (VNFs), is a crucial technology for data center (DC) networks. A service function chain (SFC) is composed of an ordered set of VNFs and virtual links (VLs) connecting them. To optimize the resource allocation in DC networks, we need to efficiently map SFCs onto the physical network. Nevertheless, the dynamics and diversity of SFC requests in multi-datacenter (MDC) networks pose a significant challenge in embedding SFCs. To overcome this challenge, we design a two-stage graph convolutional network (GCN) assisted deep reinforcement learning (DRL) scheme. This framework aims to maximize the overall acceptance ratio of SFC requests while minimizing the total cost in an MDC network. In the first stage, we propose a GCN-based DRL algorithm as a coarse granularity solution to the SFC embedding problem from the macro perspective. This solution outlines a local observation scope (LOS) for each agent in the multi-agent system of the second stage, where all agents simultaneously handle SFC requests from their respective DCs using a multi-agent framework from the micro perspective. Numerical evaluations show that, compared to state-of-the-art methods, the proposed scheme improves the acceptance ratio by approximately 13% compared with the Kolin algorithm and 18% compared with the DQN algorithm and saves the cost by around 28% compared with the Kolin and the DQN.
dc.language	English
dc.publisher	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
dc.relation.ispartof	IEEE Transactions on Network and Service Management
dc.relation.isbasedon	10.1109/TNSM.2023.3284293
dc.rights	info:eu-repo/semantics/embargoedAccess
dc.subject	0805 Distributed Computing, 0906 Electrical and Electronic Engineering, 1005 Communications Technologies
dc.subject.classification	Networking & Telecommunications
dc.subject.classification	4006 Communications engineering
dc.subject.classification	4604 Cybersecurity and privacy
dc.subject.classification	4606 Distributed computing and systems software
dc.title	A Two-Stage GCN-Based Deep Reinforcement Learning Framework for SFC Embedding in Multi-Datacenter Networks
dc.type	Journal Article
utslib.citation.volume	20
utslib.for	0805 Distributed Computing
utslib.for	0906 Electrical and Electronic Engineering
utslib.for	1005 Communications Technologies
pubs.organisational-group	University of Technology Sydney
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	University of Technology Sydney/Strength - GBDTC - Global Big Data Technologies
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology/School of Electrical and Data Engineering
pubs.organisational-group	University of Technology Sydney/Strength - CCSP - Centre for Cyber Security and Privacy
utslib.copyright.status	embargoed	*
utslib.copyright.embargo	2025-06-08T00:00:00+1000Z
dc.date.updated	2024-03-27T02:33:31Z
pubs.issue	4
pubs.publication-status	Published
pubs.volume	20
utslib.citation.issue	4

Abstract:

Network Function Virtualization (NFV), which decouples network functions from hardware and transforms them into Virtual Network Functions (VNFs), is a crucial technology for data center (DC) networks. A service function chain (SFC) is composed of an ordered set of VNFs and virtual links (VLs) connecting them. To optimize the resource allocation in DC networks, we need to efficiently map SFCs onto the physical network. Nevertheless, the dynamics and diversity of SFC requests in multi-datacenter (MDC) networks pose a significant challenge in embedding SFCs. To overcome this challenge, we design a two-stage graph convolutional network (GCN) assisted deep reinforcement learning (DRL) scheme. This framework aims to maximize the overall acceptance ratio of SFC requests while minimizing the total cost in an MDC network. In the first stage, we propose a GCN-based DRL algorithm as a coarse granularity solution to the SFC embedding problem from the macro perspective. This solution outlines a local observation scope (LOS) for each agent in the multi-agent system of the second stage, where all agents simultaneously handle SFC requests from their respective DCs using a multi-agent framework from the micro perspective. Numerical evaluations show that, compared to state-of-the-art methods, the proposed scheme improves the acceptance ratio by approximately 13% compared with the Kolin algorithm and 18% compared with the DQN algorithm and saves the cost by around 28% compared with the Kolin and the DQN.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/177238