Delay-Sensitive SFC Scheduling Optimization With DRL in Satellite-Terrestrial Networks

Meilin Xu; Min Jia; Qing Guo

doi:10.1109/ICCT59356.2023.10419739

Delay-Sensitive SFC Scheduling Optimization With DRL in Satellite-Terrestrial Networks

Meilin Xu
, Min Jia
, Qing Guo^*

^*Corresponding author for this work

School of Electronics and Information Engineering, Harbin Institute of Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

3 Scopus citations

Abstract

Large-scale low Earth orbit (LEO) satellite communication systems play a pivotal role in shaping the future of 6G communication networks. This study delves into the intricacies of deploying delay-sensitive virtual network functions (VNFs) and scheduling service function chain (SFC) requests in satellite-terrestrial networks. We frame the SFC request scheduling (SFCRS) challenge as an integer linear programming (ILP) problem. We introduce an effective Deep Reinforcement Learning (DRL) approach to effectively tackle the SFCRS problem. The DRL-SFCRS algorithm primarily employs a sequence-to-sequence model and leverages Asynchronous Advantage Actor-Critic (A3C) for updating network parameters to attain the optimal policy. Simulation results underscore the algorithm's ability to adeptly balance the trade-off between end-to-end delay and resource utilization in the context of the SFCRS problem. As a result, the algorithm yields enhanced operator profits.

Original language	English
Title of host publication	2023 IEEE 23rd International Conference on Communication Technology
Subtitle of host publication	Advanced Communication and Internet of Things, ICCT 2023
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1680-1684
Number of pages	5
ISBN (Electronic)	9798350325959
DOIs	https://doi.org/10.1109/ICCT59356.2023.10419739
State	Published - 2023
Externally published	Yes
Event	23rd IEEE International Conference on Communication Technology, ICCT 2023 - Wuxi, China Duration: 20 Oct 2023 → 22 Oct 2023

Publication series

Name	International Conference on Communication Technology Proceedings, ICCT
ISSN (Print)	2576-7844
ISSN (Electronic)	2576-7828

Conference

Conference	23rd IEEE International Conference on Communication Technology, ICCT 2023
Country/Territory	China
City	Wuxi
Period	20/10/23 → 22/10/23

Keywords

DRL
Low-orbit satellite
end-to-end delay
network function virtualization
service function chain

Access to Document

10.1109/ICCT59356.2023.10419739

Cite this

Xu, M., Jia, M., & Guo, Q. (2023). Delay-Sensitive SFC Scheduling Optimization With DRL in Satellite-Terrestrial Networks. In 2023 IEEE 23rd International Conference on Communication Technology: Advanced Communication and Internet of Things, ICCT 2023 (pp. 1680-1684). (International Conference on Communication Technology Proceedings, ICCT). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCT59356.2023.10419739

Xu, Meilin ; Jia, Min ; Guo, Qing. / Delay-Sensitive SFC Scheduling Optimization With DRL in Satellite-Terrestrial Networks. 2023 IEEE 23rd International Conference on Communication Technology: Advanced Communication and Internet of Things, ICCT 2023. Institute of Electrical and Electronics Engineers Inc., 2023. pp. 1680-1684 (International Conference on Communication Technology Proceedings, ICCT).

@inproceedings{836e9414e0044187a5f7c92b721c6bcd,

title = "Delay-Sensitive SFC Scheduling Optimization With DRL in Satellite-Terrestrial Networks",

abstract = "Large-scale low Earth orbit (LEO) satellite communication systems play a pivotal role in shaping the future of 6G communication networks. This study delves into the intricacies of deploying delay-sensitive virtual network functions (VNFs) and scheduling service function chain (SFC) requests in satellite-terrestrial networks. We frame the SFC request scheduling (SFCRS) challenge as an integer linear programming (ILP) problem. We introduce an effective Deep Reinforcement Learning (DRL) approach to effectively tackle the SFCRS problem. The DRL-SFCRS algorithm primarily employs a sequence-to-sequence model and leverages Asynchronous Advantage Actor-Critic (A3C) for updating network parameters to attain the optimal policy. Simulation results underscore the algorithm's ability to adeptly balance the trade-off between end-to-end delay and resource utilization in the context of the SFCRS problem. As a result, the algorithm yields enhanced operator profits.",

keywords = "DRL, Low-orbit satellite, end-to-end delay, network function virtualization, service function chain",

author = "Meilin Xu and Min Jia and Qing Guo",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 23rd IEEE International Conference on Communication Technology, ICCT 2023 ; Conference date: 20-10-2023 Through 22-10-2023",

year = "2023",

doi = "10.1109/ICCT59356.2023.10419739",

language = "英语",

series = "International Conference on Communication Technology Proceedings, ICCT",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "1680--1684",

booktitle = "2023 IEEE 23rd International Conference on Communication Technology",

address = "美国",

}

Xu, M, Jia, M & Guo, Q 2023, Delay-Sensitive SFC Scheduling Optimization With DRL in Satellite-Terrestrial Networks. in 2023 IEEE 23rd International Conference on Communication Technology: Advanced Communication and Internet of Things, ICCT 2023. International Conference on Communication Technology Proceedings, ICCT, Institute of Electrical and Electronics Engineers Inc., pp. 1680-1684, 23rd IEEE International Conference on Communication Technology, ICCT 2023, Wuxi, China, 20/10/23. https://doi.org/10.1109/ICCT59356.2023.10419739

Delay-Sensitive SFC Scheduling Optimization With DRL in Satellite-Terrestrial Networks. / Xu, Meilin; Jia, Min ; Guo, Qing.
2023 IEEE 23rd International Conference on Communication Technology: Advanced Communication and Internet of Things, ICCT 2023. Institute of Electrical and Electronics Engineers Inc., 2023. p. 1680-1684 (International Conference on Communication Technology Proceedings, ICCT).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Delay-Sensitive SFC Scheduling Optimization With DRL in Satellite-Terrestrial Networks

AU - Xu, Meilin

AU - Jia, Min

AU - Guo, Qing

PY - 2023

Y1 - 2023

N2 - Large-scale low Earth orbit (LEO) satellite communication systems play a pivotal role in shaping the future of 6G communication networks. This study delves into the intricacies of deploying delay-sensitive virtual network functions (VNFs) and scheduling service function chain (SFC) requests in satellite-terrestrial networks. We frame the SFC request scheduling (SFCRS) challenge as an integer linear programming (ILP) problem. We introduce an effective Deep Reinforcement Learning (DRL) approach to effectively tackle the SFCRS problem. The DRL-SFCRS algorithm primarily employs a sequence-to-sequence model and leverages Asynchronous Advantage Actor-Critic (A3C) for updating network parameters to attain the optimal policy. Simulation results underscore the algorithm's ability to adeptly balance the trade-off between end-to-end delay and resource utilization in the context of the SFCRS problem. As a result, the algorithm yields enhanced operator profits.

AB - Large-scale low Earth orbit (LEO) satellite communication systems play a pivotal role in shaping the future of 6G communication networks. This study delves into the intricacies of deploying delay-sensitive virtual network functions (VNFs) and scheduling service function chain (SFC) requests in satellite-terrestrial networks. We frame the SFC request scheduling (SFCRS) challenge as an integer linear programming (ILP) problem. We introduce an effective Deep Reinforcement Learning (DRL) approach to effectively tackle the SFCRS problem. The DRL-SFCRS algorithm primarily employs a sequence-to-sequence model and leverages Asynchronous Advantage Actor-Critic (A3C) for updating network parameters to attain the optimal policy. Simulation results underscore the algorithm's ability to adeptly balance the trade-off between end-to-end delay and resource utilization in the context of the SFCRS problem. As a result, the algorithm yields enhanced operator profits.

KW - DRL

KW - Low-orbit satellite

KW - end-to-end delay

KW - network function virtualization

KW - service function chain

UR - https://www.scopus.com/pages/publications/85186080075

U2 - 10.1109/ICCT59356.2023.10419739

DO - 10.1109/ICCT59356.2023.10419739

M3 - 会议稿件

AN - SCOPUS:85186080075

T3 - International Conference on Communication Technology Proceedings, ICCT

SP - 1680

EP - 1684

BT - 2023 IEEE 23rd International Conference on Communication Technology

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 23rd IEEE International Conference on Communication Technology, ICCT 2023

Y2 - 20 October 2023 through 22 October 2023

ER -

Xu M, Jia M , Guo Q. Delay-Sensitive SFC Scheduling Optimization With DRL in Satellite-Terrestrial Networks. In 2023 IEEE 23rd International Conference on Communication Technology: Advanced Communication and Internet of Things, ICCT 2023. Institute of Electrical and Electronics Engineers Inc. 2023. p. 1680-1684. (International Conference on Communication Technology Proceedings, ICCT). doi: 10.1109/ICCT59356.2023.10419739

Delay-Sensitive SFC Scheduling Optimization With DRL in Satellite-Terrestrial Networks

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this