6G Network AI Architecture for Everyone-Centric Customized Services

Yang Yang; Mulei Ma; Hequan Wu; Quan Wu; Ping Zhang; Xiaohu You; Jianjun Wu; Chenghui Peng; Tak-Shing Peter Yum; Sherman Shen; A.H. Aghvami; Geoffrey Y Li; Jiangzhou Wang; Guangyu  Liu; Peng Gao; Xiongyan Tang; Chang Cao; John Thompson; Kai Kit Wong; Shanzi Chen; Merouane Debbah; Schahram Dustdar; Frank Eliassen; Tao Chen; Xiangyuan Duan; Shaohui Sun; Tao Xiaofeng; Qinyu Zhang; Jianwei Huang; Shugang Cui; 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 Wu
, Ping Zhang
, Xiaohu You
, Jianjun Wu
, Chenghui Peng
, Tak-Shing Peter Yum
, Sherman Shen
, A.H. Aghvami
, Geoffrey Y Li
, Jiangzhou Wang
, Guangyu Liu
, Peng Gao
, Xiongyan Tang
, Chang Cao
, John Thompson
, Kai Kit Wong
, Shanzi Chen

Merouane Debbah, Schahram Dustdar, Frank Eliassen, Tao Chen, Xiangyuan Duan, Shaohui Sun, Tao Xiaofeng, Qinyu Zhang, Jianwei Huang, Shugang Cui, 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

School of Engineering

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

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)	1-10
Journal	IEEE Microwave Magazine
Early online date	25 Jul 2022
DOIs	https://doi.org/10.1109/MNET.124.2200241 https://doi.org/10.1109/MNET.124.2200241
Publication status	E-pub ahead of print - 25 Jul 2022

Access to Document

20220714-NetworkAI-v39-NetMagAccepted author manuscript, 722 KB

Cite this

Yang, Y., Ma, M., Wu, H., Wu, Q., Zhang, P., You, X., Wu, J., Peng, C., Yum, T.-S. P., Shen, S., Aghvami, A. H., Li, G. Y., Wang, J., Liu, G., Gao, P., Tang, X., Cao, C., Thompson, J., Wong, K. K., ... Shu, H. (2022). 6G Network AI Architecture for Everyone-Centric Customized Services. IEEE Microwave Magazine, 1-10. Advance online publication. https://doi.org/10.1109/MNET.124.2200241, https://doi.org/10.1109/MNET.124.2200241

@article{54f49b5a89a54cd192b1ca6cc7ea3b05,

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{\textquoteright}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 Wu and Ping Zhang and Xiaohu You and Jianjun Wu and Chenghui Peng and Yum, \{Tak-Shing Peter\} and Sherman Shen and A.H. Aghvami and Li, \{Geoffrey Y\} and Jiangzhou Wang and Guangyu Liu and Peng Gao and Xiongyan Tang and Chang Cao and John Thompson and Wong, \{Kai Kit\} and Shanzi Chen and Merouane Debbah and Schahram Dustdar and Frank Eliassen and Tao Chen and Xiangyuan Duan and Shaohui Sun and Tao Xiaofeng and Qinyu Zhang and Jianwei Huang and Shugang Cui and Wenjun Zhang and Jie Li and Yue Gao and Honggang Zhang and Xu Chen and Xiaohu Ge and Yong Xiao and Cheng-xiang Wang 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: IEEE",

year = "2022",

month = jul,

day = "25",

doi = "10.1109/MNET.124.2200241",

language = "English",

pages = "1--10",

journal = "IEEE Microwave Magazine",

issn = "1527-3342",

publisher = "Institute of Electrical and Electronics Engineers",

}

Yang, Y, Ma, M, Wu, H, Wu, Q, Zhang, P, You, X, Wu, J, Peng, C, Yum, T-SP, Shen, S, Aghvami, AH, Li, GY, Wang, J, Liu, G, Gao, P, Tang, X, Cao, C, Thompson, J, Wong, KK, Chen, S, Debbah, M, Dustdar, S, Eliassen, F, Chen, T, Duan, X, Sun, S, Xiaofeng, T, Zhang, Q, Huang, J, Cui, S, Zhang, W, Li, J, Gao, Y, Zhang, H, Chen, X, Ge, X, Xiao, Y, Wang, C, 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 2022, '6G Network AI Architecture for Everyone-Centric Customized Services', IEEE Microwave Magazine, pp. 1-10. https://doi.org/10.1109/MNET.124.2200241, 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 - Wu, Quan

AU - Zhang, Ping

AU - You, Xiaohu

AU - Wu, Jianjun

AU - Peng, Chenghui

AU - Yum, Tak-Shing Peter

AU - Shen, Sherman

AU - Aghvami, A.H.

AU - Li, Geoffrey Y

AU - Wang, Jiangzhou

AU - Liu, Guangyu

AU - Gao, Peng

AU - Tang, Xiongyan

AU - Cao, Chang

AU - Thompson, John

AU - Wong, Kai Kit

AU - Chen, Shanzi

AU - Debbah, Merouane

AU - Dustdar, Schahram

AU - Eliassen, Frank

AU - Chen, Tao

AU - Duan, Xiangyuan

AU - Sun, Shaohui

AU - Xiaofeng, Tao

AU - Zhang, Qinyu

AU - Huang, Jianwei

AU - Cui, Shugang

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

N1 - Publisher Copyright: IEEE

PY - 2022/7/25

Y1 - 2022/7/25

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.

U2 - 10.1109/MNET.124.2200241

DO - 10.1109/MNET.124.2200241

M3 - Article

SN - 1527-3342

SP - 1

EP - 10

JO - IEEE Microwave Magazine

JF - IEEE Microwave Magazine

ER -

6G Network AI Architecture for Everyone-Centric Customized Services

Abstract

Access to Document

Fingerprint

Cite this