6G Network AI Architecture for Everyone-Centric Customized Services

Yang Yang; Mulei Ma; Hequan Wu; Quan Yu; Xiaohu You; Jianjun Wu; Chenghui Peng; Tak Shing Peter Yum; A. Hamid Aghvami; Geoffrey Y. Li; Jiangzhou Wang; Guangyi Liu; Peng Gao; Xiongyan Tang; Chang Cao; John Thompson; Kat Kit Wong; Shanzhi Chen; Zhiqin Wang; Merouane Debbah; Schahram Dustdar; Frank Eliassen; Tao Chen; Xiangyang Duan; Shaohui Sun; Xiaofeng Tao; Qinyu Zhang; Jianwei Huang; Wenjun Zhang; Jie Li; Yue Gao; Honggang Zhang; Xu Chen; Xiaohu Ge; Yong Xiao; Cheng Xiang Wang; Zaichen Zhang; Song Ci; Guoqiang Mao; Changle Li; Ziyu Shao; Yong Zhou; Junrui Liang; Kai Li; Liantao Wu; Fanglei Sun; Kunlun Wang; Zening Liu; Kun Yang; Jun Wang; Teng Gao; Hongfeng Shu

doi:10.1109/MNET.124.2200241

6G Network AI Architecture for Everyone-Centric Customized Services

Yang Yang, Mulei Ma, Hequan Wu, Quan Yu, Xiaohu You, Jianjun Wu, Chenghui Peng, Tak Shing Peter Yum, A. Hamid Aghvami, Geoffrey Y. Li, Jiangzhou Wang, Guangyi Liu, Peng Gao, Xiongyan Tang, Chang Cao, John Thompson, Kat Kit Wong, Shanzhi Chen, Zhiqin Wang, Merouane DebbahSchahram Dustdar, Frank Eliassen, Tao Chen, Xiangyang Duan, Shaohui Sun, Xiaofeng Tao, Qinyu Zhang, Jianwei Huang, Wenjun Zhang, Jie Li, Yue Gao, Honggang Zhang, Xu Chen, Xiaohu Ge, Yong Xiao, Cheng Xiang Wang, Zaichen Zhang, Song Ci, Guoqiang Mao, Changle Li, Ziyu Shao, Yong Zhou, Junrui Liang, Kai Li, Liantao Wu, Fanglei Sun, Kunlun Wang, Zening Liu, Kun Yang, Jun Wang, Teng Gao, Hongfeng Shu

BA6401 Connectivity solutions

Research output: Contribution to journal › Article › Scientific › peer-review

22 Citations (Scopus)

Abstract

Mobile communication standards were developed for enhancing transmission and network performance by using more radio resources and improving spectrum and energy efficiency. How to effectively address diverse user requirements and guarantee everyone's Quality of Experience (QoE) remains an open problem. The Sixth Generation (6G) mobile systems will solve this problem by utilizing heterogenous network resources and pervasive intelligence to support everyone-centric customized services anywhere and anytime. In this article, we first coin the concept of Service Requirement Zone (SRZ) on the user side to characterize and visualize the integrated service requirements and preferences of specific tasks of individual users. On the system side, we further introduce the concept of User Satisfaction Ratio (USR) to evaluate the system's overall service ability of satisfying a variety of tasks with different SRZs. Then, we propose a network Artificial Intelligence (AI) architecture with integrated network resources and pervasive AI capabilities for supporting customized services with guaranteed QoEs. Finally, extensive simulations show that the proposed network AI architecture can consistently offer a higher USR performance than the cloud AI and edge AI architectures with respect to different task scheduling algorithms, random service requirements, and dynamic network conditions.

Original language	English
Pages (from-to)	71-80
Number of pages	10
Journal	IEEE Network
Volume	37
Issue number	5
DOIs	https://doi.org/10.1109/MNET.124.2200241
Publication status	Published - 1 Sept 2023
MoE publication type	A1 Journal article-refereed

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/MNET.124.2200241

Cite this

@article{fd1b1f3907d54b78b971e662be0f7f61,

title = "6G Network AI Architecture for Everyone-Centric Customized Services",

abstract = "Mobile communication standards were developed for enhancing transmission and network performance by using more radio resources and improving spectrum and energy efficiency. How to effectively address diverse user requirements and guarantee everyone's Quality of Experience (QoE) remains an open problem. The Sixth Generation (6G) mobile systems will solve this problem by utilizing heterogenous network resources and pervasive intelligence to support everyone-centric customized services anywhere and anytime. In this article, we first coin the concept of Service Requirement Zone (SRZ) on the user side to characterize and visualize the integrated service requirements and preferences of specific tasks of individual users. On the system side, we further introduce the concept of User Satisfaction Ratio (USR) to evaluate the system's overall service ability of satisfying a variety of tasks with different SRZs. Then, we propose a network Artificial Intelligence (AI) architecture with integrated network resources and pervasive AI capabilities for supporting customized services with guaranteed QoEs. Finally, extensive simulations show that the proposed network AI architecture can consistently offer a higher USR performance than the cloud AI and edge AI architectures with respect to different task scheduling algorithms, random service requirements, and dynamic network conditions.",

author = "Yang Yang and Mulei Ma and Hequan Wu and Quan Yu and Xiaohu You and Jianjun Wu and Chenghui Peng and Yum, {Tak Shing Peter} and Aghvami, {A. Hamid} and Li, {Geoffrey Y.} and Jiangzhou Wang and Guangyi Liu and Peng Gao and Xiongyan Tang and Chang Cao and John Thompson and Wong, {Kat Kit} and Shanzhi Chen and Zhiqin Wang and Merouane Debbah and Schahram Dustdar and Frank Eliassen and Tao Chen and Xiangyang Duan and Shaohui Sun and Xiaofeng Tao and Qinyu Zhang and Jianwei Huang and Wenjun Zhang and Jie Li and Yue Gao and Honggang Zhang and Xu Chen and Xiaohu Ge and Yong Xiao and Wang, {Cheng Xiang} and Zaichen Zhang and Song Ci and Guoqiang Mao and Changle Li and Ziyu Shao and Yong Zhou and Junrui Liang and Kai Li and Liantao Wu and Fanglei Sun and Kunlun Wang and Zening Liu and Kun Yang and Jun Wang and Teng Gao and Hongfeng Shu",

note = "Publisher Copyright: {\textcopyright} 1986-2012 IEEE.",

year = "2023",

month = sep,

day = "1",

doi = "10.1109/MNET.124.2200241",

language = "English",

volume = "37",

pages = "71--80",

journal = "IEEE Network",

issn = "0890-8044",

publisher = "IEEE Institute of Electrical and Electronic Engineers",

number = "5",

}

Yang, Y, Ma, M, Wu, H, Yu, Q, You, X, Wu, J, Peng, C, Yum, TSP, Aghvami, AH, Li, GY, Wang, J, Liu, G, Gao, P, Tang, X, Cao, C, Thompson, J, Wong, KK, Chen, S, Wang, Z, Debbah, M, Dustdar, S, Eliassen, F, Chen, T, Duan, X, Sun, S, Tao, X, Zhang, Q, Huang, J, Zhang, W, Li, J, Gao, Y, Zhang, H, Chen, X, Ge, X, Xiao, Y, Wang, CX, Zhang, Z, Ci, S, Mao, G, Li, C, Shao, Z, Zhou, Y, Liang, J, Li, K, Wu, L, Sun, F, Wang, K, Liu, Z, Yang, K, Wang, J, Gao, T & Shu, H 2023, '6G Network AI Architecture for Everyone-Centric Customized Services', IEEE Network, vol. 37, no. 5, pp. 71-80. https://doi.org/10.1109/MNET.124.2200241

TY - JOUR

T1 - 6G Network AI Architecture for Everyone-Centric Customized Services

AU - Yang, Yang

AU - Ma, Mulei

AU - Wu, Hequan

AU - Yu, Quan

AU - You, Xiaohu

AU - Wu, Jianjun

AU - Peng, Chenghui

AU - Yum, Tak Shing Peter

AU - Aghvami, A. Hamid

AU - Li, Geoffrey Y.

AU - Wang, Jiangzhou

AU - Liu, Guangyi

AU - Gao, Peng

AU - Tang, Xiongyan

AU - Cao, Chang

AU - Thompson, John

AU - Wong, Kat Kit

AU - Chen, Shanzhi

AU - Wang, Zhiqin

AU - Debbah, Merouane

AU - Dustdar, Schahram

AU - Eliassen, Frank

AU - Chen, Tao

AU - Duan, Xiangyang

AU - Sun, Shaohui

AU - Tao, Xiaofeng

AU - Zhang, Qinyu

AU - Huang, Jianwei

AU - Zhang, Wenjun

AU - Li, Jie

AU - Gao, Yue

AU - Zhang, Honggang

AU - Chen, Xu

AU - Ge, Xiaohu

AU - Xiao, Yong

AU - Wang, Cheng Xiang

AU - Zhang, Zaichen

AU - Ci, Song

AU - Mao, Guoqiang

AU - Li, Changle

AU - Shao, Ziyu

AU - Zhou, Yong

AU - Liang, Junrui

AU - Li, Kai

AU - Wu, Liantao

AU - Sun, Fanglei

AU - Wang, Kunlun

AU - Liu, Zening

AU - Yang, Kun

AU - Wang, Jun

AU - Gao, Teng

AU - Shu, Hongfeng

PY - 2023/9/1

Y1 - 2023/9/1

N2 - Mobile communication standards were developed for enhancing transmission and network performance by using more radio resources and improving spectrum and energy efficiency. How to effectively address diverse user requirements and guarantee everyone's Quality of Experience (QoE) remains an open problem. The Sixth Generation (6G) mobile systems will solve this problem by utilizing heterogenous network resources and pervasive intelligence to support everyone-centric customized services anywhere and anytime. In this article, we first coin the concept of Service Requirement Zone (SRZ) on the user side to characterize and visualize the integrated service requirements and preferences of specific tasks of individual users. On the system side, we further introduce the concept of User Satisfaction Ratio (USR) to evaluate the system's overall service ability of satisfying a variety of tasks with different SRZs. Then, we propose a network Artificial Intelligence (AI) architecture with integrated network resources and pervasive AI capabilities for supporting customized services with guaranteed QoEs. Finally, extensive simulations show that the proposed network AI architecture can consistently offer a higher USR performance than the cloud AI and edge AI architectures with respect to different task scheduling algorithms, random service requirements, and dynamic network conditions.

AB - Mobile communication standards were developed for enhancing transmission and network performance by using more radio resources and improving spectrum and energy efficiency. How to effectively address diverse user requirements and guarantee everyone's Quality of Experience (QoE) remains an open problem. The Sixth Generation (6G) mobile systems will solve this problem by utilizing heterogenous network resources and pervasive intelligence to support everyone-centric customized services anywhere and anytime. In this article, we first coin the concept of Service Requirement Zone (SRZ) on the user side to characterize and visualize the integrated service requirements and preferences of specific tasks of individual users. On the system side, we further introduce the concept of User Satisfaction Ratio (USR) to evaluate the system's overall service ability of satisfying a variety of tasks with different SRZs. Then, we propose a network Artificial Intelligence (AI) architecture with integrated network resources and pervasive AI capabilities for supporting customized services with guaranteed QoEs. Finally, extensive simulations show that the proposed network AI architecture can consistently offer a higher USR performance than the cloud AI and edge AI architectures with respect to different task scheduling algorithms, random service requirements, and dynamic network conditions.

UR - http://www.scopus.com/inward/record.url?scp=85135748158&partnerID=8YFLogxK

U2 - 10.1109/MNET.124.2200241

DO - 10.1109/MNET.124.2200241

M3 - Article

AN - SCOPUS:85135748158

SN - 0890-8044

VL - 37

SP - 71

EP - 80

JO - IEEE Network

JF - IEEE Network

IS - 5

ER -

6G Network AI Architecture for Everyone-Centric Customized Services

Abstract

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this