Age of information-aware multi-tenant resource orchestration in network slicing

Xianfu Chen, Celimuge Wu, Tao Chen, Nan Wu, Honggang Zhang, Yusheng Ji

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

Abstract

To satisfy diverse services from mobile users (MUs) over a common network infrastructure, network slicing is envisioned as a promising technology. This paper considers radio access network (RAN)-only slicing, where the physical RAN is judiciously tailored to accommodate computation and communication functionalities. Multiple service providers (SPs, a.k.a., tenants) compete for a limited number of channels across the discrete scheduling slots in order to serve their respective subscribed MUs. From a MU perspective, the age of information of data packets from traditional mobile services and the energy consumption at mobile device are of practical importance. We characterize the interactions among the SPs via a stochastic game, in which a SP selfishly maximizes its own expected long-term payoff. To approximate the Nash equilibrium solutions, we build an abstract stochastic game exploring the local information of SPs. Furthermore, the decision-making process at a SP can be much simplified by linearly decomposing the per-SP Markov decision process, for which we derive a deep reinforcement learning based scheme to find the optimal abstract control policies. TensorFlow-based experiments validate our studies and show that the proposed scheme outperforms the three baselines and yields the best performance in average utility.

Original languageEnglish
Title of host publication2019 IEEE Intl Conf on Dependable, Autonomic and Secure Computing, Intl Conf on Pervasive Intelligence and Computing, Intl Conf on Cloud and Big Data Computing, Intl Conf on Cyber Science and Technology Congress (DASC/PiCom/CBDCom/CyberSciTech)
PublisherIEEE Institute of Electrical and Electronic Engineers
Pages1001-1007
ISBN (Electronic)978-1-7281-3024-8
ISBN (Print)978-1-7281-3025-5
DOIs
Publication statusPublished - Aug 2019
MoE publication typeA4 Article in a conference publication
Event17th IEEE International Conference on Dependable, Autonomic and Secure Computing, IEEE 17th International Conference on Pervasive Intelligence and Computing, IEEE 5th International Conference on Cloud and Big Data Computing, 4th Cyber Science and Technology Congress, DASC-PiCom-CBDCom-CyberSciTech 2019 - Fukuoka, Japan
Duration: 5 Aug 20198 Aug 2019

Conference

Conference17th IEEE International Conference on Dependable, Autonomic and Secure Computing, IEEE 17th International Conference on Pervasive Intelligence and Computing, IEEE 5th International Conference on Cloud and Big Data Computing, 4th Cyber Science and Technology Congress, DASC-PiCom-CBDCom-CyberSciTech 2019
CountryJapan
CityFukuoka
Period5/08/198/08/19

Fingerprint

Orchestration
Slicing
Stochastic Games
Resources
Reinforcement learning
Mobile devices
Energy utilization
Decision making
Scheduling
Mobile Services
Equilibrium Solution
Communication
Markov Decision Process
Control Policy
Reinforcement Learning
Nash Equilibrium
Mobile Devices
Energy Consumption
Baseline
Infrastructure

Keywords

  • Age of information
  • Deep reinforcement learning
  • Markov decision process
  • Network slicing
  • Stochastic game

Cite this

Chen, X., Wu, C., Chen, T., Wu, N., Zhang, H., & Ji, Y. (2019). Age of information-aware multi-tenant resource orchestration in network slicing. In 2019 IEEE Intl Conf on Dependable, Autonomic and Secure Computing, Intl Conf on Pervasive Intelligence and Computing, Intl Conf on Cloud and Big Data Computing, Intl Conf on Cyber Science and Technology Congress (DASC/PiCom/CBDCom/CyberSciTech) (pp. 1001-1007). [8890362] IEEE Institute of Electrical and Electronic Engineers . https://doi.org/10.1109/DASC/PiCom/CBDCom/CyberSciTech.2019.00182
Chen, Xianfu ; Wu, Celimuge ; Chen, Tao ; Wu, Nan ; Zhang, Honggang ; Ji, Yusheng. / Age of information-aware multi-tenant resource orchestration in network slicing. 2019 IEEE Intl Conf on Dependable, Autonomic and Secure Computing, Intl Conf on Pervasive Intelligence and Computing, Intl Conf on Cloud and Big Data Computing, Intl Conf on Cyber Science and Technology Congress (DASC/PiCom/CBDCom/CyberSciTech). IEEE Institute of Electrical and Electronic Engineers , 2019. pp. 1001-1007
@inproceedings{473f4bc52cce456895c1daec1d216ec2,
title = "Age of information-aware multi-tenant resource orchestration in network slicing",
abstract = "To satisfy diverse services from mobile users (MUs) over a common network infrastructure, network slicing is envisioned as a promising technology. This paper considers radio access network (RAN)-only slicing, where the physical RAN is judiciously tailored to accommodate computation and communication functionalities. Multiple service providers (SPs, a.k.a., tenants) compete for a limited number of channels across the discrete scheduling slots in order to serve their respective subscribed MUs. From a MU perspective, the age of information of data packets from traditional mobile services and the energy consumption at mobile device are of practical importance. We characterize the interactions among the SPs via a stochastic game, in which a SP selfishly maximizes its own expected long-term payoff. To approximate the Nash equilibrium solutions, we build an abstract stochastic game exploring the local information of SPs. Furthermore, the decision-making process at a SP can be much simplified by linearly decomposing the per-SP Markov decision process, for which we derive a deep reinforcement learning based scheme to find the optimal abstract control policies. TensorFlow-based experiments validate our studies and show that the proposed scheme outperforms the three baselines and yields the best performance in average utility.",
keywords = "Age of information, Deep reinforcement learning, Markov decision process, Network slicing, Stochastic game",
author = "Xianfu Chen and Celimuge Wu and Tao Chen and Nan Wu and Honggang Zhang and Yusheng Ji",
year = "2019",
month = "8",
doi = "10.1109/DASC/PiCom/CBDCom/CyberSciTech.2019.00182",
language = "English",
isbn = "978-1-7281-3025-5",
pages = "1001--1007",
booktitle = "2019 IEEE Intl Conf on Dependable, Autonomic and Secure Computing, Intl Conf on Pervasive Intelligence and Computing, Intl Conf on Cloud and Big Data Computing, Intl Conf on Cyber Science and Technology Congress (DASC/PiCom/CBDCom/CyberSciTech)",
publisher = "IEEE Institute of Electrical and Electronic Engineers",
address = "United States",

}

Chen, X, Wu, C, Chen, T, Wu, N, Zhang, H & Ji, Y 2019, Age of information-aware multi-tenant resource orchestration in network slicing. in 2019 IEEE Intl Conf on Dependable, Autonomic and Secure Computing, Intl Conf on Pervasive Intelligence and Computing, Intl Conf on Cloud and Big Data Computing, Intl Conf on Cyber Science and Technology Congress (DASC/PiCom/CBDCom/CyberSciTech)., 8890362, IEEE Institute of Electrical and Electronic Engineers , pp. 1001-1007, 17th IEEE International Conference on Dependable, Autonomic and Secure Computing, IEEE 17th International Conference on Pervasive Intelligence and Computing, IEEE 5th International Conference on Cloud and Big Data Computing, 4th Cyber Science and Technology Congress, DASC-PiCom-CBDCom-CyberSciTech 2019, Fukuoka, Japan, 5/08/19. https://doi.org/10.1109/DASC/PiCom/CBDCom/CyberSciTech.2019.00182

Age of information-aware multi-tenant resource orchestration in network slicing. / Chen, Xianfu; Wu, Celimuge; Chen, Tao; Wu, Nan; Zhang, Honggang; Ji, Yusheng.

2019 IEEE Intl Conf on Dependable, Autonomic and Secure Computing, Intl Conf on Pervasive Intelligence and Computing, Intl Conf on Cloud and Big Data Computing, Intl Conf on Cyber Science and Technology Congress (DASC/PiCom/CBDCom/CyberSciTech). IEEE Institute of Electrical and Electronic Engineers , 2019. p. 1001-1007 8890362.

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

TY - GEN

T1 - Age of information-aware multi-tenant resource orchestration in network slicing

AU - Chen, Xianfu

AU - Wu, Celimuge

AU - Chen, Tao

AU - Wu, Nan

AU - Zhang, Honggang

AU - Ji, Yusheng

PY - 2019/8

Y1 - 2019/8

N2 - To satisfy diverse services from mobile users (MUs) over a common network infrastructure, network slicing is envisioned as a promising technology. This paper considers radio access network (RAN)-only slicing, where the physical RAN is judiciously tailored to accommodate computation and communication functionalities. Multiple service providers (SPs, a.k.a., tenants) compete for a limited number of channels across the discrete scheduling slots in order to serve their respective subscribed MUs. From a MU perspective, the age of information of data packets from traditional mobile services and the energy consumption at mobile device are of practical importance. We characterize the interactions among the SPs via a stochastic game, in which a SP selfishly maximizes its own expected long-term payoff. To approximate the Nash equilibrium solutions, we build an abstract stochastic game exploring the local information of SPs. Furthermore, the decision-making process at a SP can be much simplified by linearly decomposing the per-SP Markov decision process, for which we derive a deep reinforcement learning based scheme to find the optimal abstract control policies. TensorFlow-based experiments validate our studies and show that the proposed scheme outperforms the three baselines and yields the best performance in average utility.

AB - To satisfy diverse services from mobile users (MUs) over a common network infrastructure, network slicing is envisioned as a promising technology. This paper considers radio access network (RAN)-only slicing, where the physical RAN is judiciously tailored to accommodate computation and communication functionalities. Multiple service providers (SPs, a.k.a., tenants) compete for a limited number of channels across the discrete scheduling slots in order to serve their respective subscribed MUs. From a MU perspective, the age of information of data packets from traditional mobile services and the energy consumption at mobile device are of practical importance. We characterize the interactions among the SPs via a stochastic game, in which a SP selfishly maximizes its own expected long-term payoff. To approximate the Nash equilibrium solutions, we build an abstract stochastic game exploring the local information of SPs. Furthermore, the decision-making process at a SP can be much simplified by linearly decomposing the per-SP Markov decision process, for which we derive a deep reinforcement learning based scheme to find the optimal abstract control policies. TensorFlow-based experiments validate our studies and show that the proposed scheme outperforms the three baselines and yields the best performance in average utility.

KW - Age of information

KW - Deep reinforcement learning

KW - Markov decision process

KW - Network slicing

KW - Stochastic game

UR - http://www.scopus.com/inward/record.url?scp=85075173441&partnerID=8YFLogxK

U2 - 10.1109/DASC/PiCom/CBDCom/CyberSciTech.2019.00182

DO - 10.1109/DASC/PiCom/CBDCom/CyberSciTech.2019.00182

M3 - Conference article in proceedings

AN - SCOPUS:85075173441

SN - 978-1-7281-3025-5

SP - 1001

EP - 1007

BT - 2019 IEEE Intl Conf on Dependable, Autonomic and Secure Computing, Intl Conf on Pervasive Intelligence and Computing, Intl Conf on Cloud and Big Data Computing, Intl Conf on Cyber Science and Technology Congress (DASC/PiCom/CBDCom/CyberSciTech)

PB - IEEE Institute of Electrical and Electronic Engineers

ER -

Chen X, Wu C, Chen T, Wu N, Zhang H, Ji Y. Age of information-aware multi-tenant resource orchestration in network slicing. In 2019 IEEE Intl Conf on Dependable, Autonomic and Secure Computing, Intl Conf on Pervasive Intelligence and Computing, Intl Conf on Cloud and Big Data Computing, Intl Conf on Cyber Science and Technology Congress (DASC/PiCom/CBDCom/CyberSciTech). IEEE Institute of Electrical and Electronic Engineers . 2019. p. 1001-1007. 8890362 https://doi.org/10.1109/DASC/PiCom/CBDCom/CyberSciTech.2019.00182