NFLCS: An Service Function Chain Path Optimization Strategy Based on Network-Functional Layout Clustering

Duan, Y; Lu, Y; Shen, S; Yu, S; Zhang, P; Zhang, W; Igorevich, KK

NFLCS: An Service Function Chain Path Optimization Strategy Based on Network-Functional Layout Clustering

Duan, Y Lu, Y Shen, S Yu, S

Zhang, P Zhang, W Igorevich, KK

Permalink

Publisher:: IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Publication Type:: Journal Article
Citation:: IEEE Transactions on Vehicular Technology, 2023, 72, (8), pp. 10813-10825
Issue Date:: 2023-08-01

Closed Access

	Filename	Description	Size
	NFLCS_An_Service_Function_Chain_Path_Optimization_Strategy_Based_on_Network-Functional_Layout_Clustering.pdf	Published version	3.67 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Duan, Y
dc.contributor.author	Lu, Y
dc.contributor.author	Shen, S
dc.contributor.author	Yu, S https://orcid.org/0000-0003-4485-6743
dc.contributor.author	Zhang, P
dc.contributor.author	Zhang, W
dc.contributor.author	Igorevich, KK
dc.date.accessioned	2024-03-12T04:13:17Z
dc.date.available	2024-03-12T04:13:17Z
dc.date.issued	2023-08-01
dc.identifier.citation	IEEE Transactions on Vehicular Technology, 2023, 72, (8), pp. 10813-10825
dc.identifier.issn	0018-9545
dc.identifier.issn	1939-9359
dc.identifier.uri	http://hdl.handle.net/10453/176561
dc.description.abstract	Under the background of 5G and 6G super bandwidth and ultra-low delay, Software Defined Networking and Network Function Virtualization (SDN&NFV) makes the communication technology develop rapidly. Service Function Chain (SFC) selection is a crucial aspect of SDN&NFV, which faces many challenges of poor algorithm performance, high latency, and low profit. Moreover, most of the existing studies are stuck in optimizing for a single metric, which leads to a poor generalization of the proposed path optimization method. In this paper, we propose an SFC path optimization strategy based on the clustering of network functional layouts to address the urgent problem. First, we design a topological network identification algorithm, model the SFC path optimization problem as an attention problem and use a multi-headed attention mechanism to optimize different kinds of SFC layouts in a targeted manner. Among them, the multi-headed attention mechanism achieves the effective capture of multiple features in the SFC path selection problem compared with the traditional strategy. The experimental results demonstrate the effectiveness of Network-Functional Layout Clustering Strategy (NFLCS) in optimizing SFC paths and show the ability to optimize the service function chain paths well in future complex network situations.
dc.language	English
dc.publisher	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
dc.relation.ispartof	IEEE Transactions on Vehicular Technology
dc.relation.isbasedon	10.1109/TVT.2023.3258916
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject	08 Information and Computing Sciences, 09 Engineering, 10 Technology
dc.subject.classification	Automobile Design & Engineering
dc.subject.classification	40 Engineering
dc.subject.classification	46 Information and computing sciences
dc.title	NFLCS: An Service Function Chain Path Optimization Strategy Based on Network-Functional Layout Clustering
dc.type	Journal Article
utslib.citation.volume	72
utslib.for	08 Information and Computing Sciences
utslib.for	09 Engineering
utslib.for	10 Technology
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/Faculty of Engineering and Information Technology/School of Computer Science
pubs.organisational-group	University of Technology Sydney/Strength - CCSP - Centre for Cyber Security and Privacy
utslib.copyright.status	closed_access	*
dc.date.updated	2024-03-12T04:13:16Z
pubs.issue	8
pubs.publication-status	Published
pubs.volume	72
utslib.citation.issue	8

Abstract:

Under the background of 5G and 6G super bandwidth and ultra-low delay, Software Defined Networking and Network Function Virtualization (SDN&NFV) makes the communication technology develop rapidly. Service Function Chain (SFC) selection is a crucial aspect of SDN&NFV, which faces many challenges of poor algorithm performance, high latency, and low profit. Moreover, most of the existing studies are stuck in optimizing for a single metric, which leads to a poor generalization of the proposed path optimization method. In this paper, we propose an SFC path optimization strategy based on the clustering of network functional layouts to address the urgent problem. First, we design a topological network identification algorithm, model the SFC path optimization problem as an attention problem and use a multi-headed attention mechanism to optimize different kinds of SFC layouts in a targeted manner. Among them, the multi-headed attention mechanism achieves the effective capture of multiple features in the SFC path selection problem compared with the traditional strategy. The experimental results demonstrate the effectiveness of Network-Functional Layout Clustering Strategy (NFLCS) in optimizing SFC paths and show the ability to optimize the service function chain paths well in future complex network situations.

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

http://hdl.handle.net/10453/176561