Native intelligence for 6G mobile network: technical challenges,
architecture and key features

doi:10.19682/j.cnki.1005-8885.2022.2004

中国邮电高校学报(英文) ›› 2022, Vol. 29 ›› Issue (1): 27-40.doi: 10.19682/j.cnki.1005-8885.2022.2004

Native intelligence for 6G mobile network: technical challenges, architecture and key features

Liu Guangyi, Deng Juan, Zheng Qingbi, Li Gang, Sun Xin, Huang Yuhong

Future Research Lab, China Mobile Research Institute, Beijing 100032, China

收稿日期:2021-12-13 修回日期:2022-01-19 接受日期:2022-01-25 出版日期:2022-02-26 发布日期:2022-02-28
通讯作者: Corresponding author: Zheng Qingbi E-mail:zhengqingbi@chinamobile.com
基金资助:
This work was supported by the National Key R&D Program of China (2020YFB1806800).

Native intelligence for 6G mobile network: technical challenges, architecture and key features

Liu Guangyi, Deng Juan, Zheng Qingbi, Li Gang, Sun Xin, Huang Yuhong

Future Research Lab, China Mobile Research Institute, Beijing 100032, China

Received:2021-12-13 Revised:2022-01-19 Accepted:2022-01-25 Online:2022-02-26 Published:2022-02-28
Contact: Corresponding author: Zheng Qingbi E-mail:zhengqingbi@chinamobile.com
Supported by:
This work was supported by the National Key R&D Program of China (2020YFB1806800).

摘要/Abstract

摘要： The application of the artificial intelligence (AI) technology in the 5th generation mobile communication system (5G) networks promotes the development of the mobile communication network and its application in vertical industries, however, the application models of "patching" and "plug-in" have hindered the effect of AI applications. Meanwhile, the application of AI in all walks of life puts forward requirements for new capabilities of the future network, such as distributed training, real-time collaborative inference, local data processing, etc. , which require "native intelligence design” in future networks. This paper discusses the requirements of native intelligence in the 6th generation mobile communication system (6G) networks from the perspectives of 5G intelligent network challenges and the “ubiquitous intelligence” vision of 6G, and analyzes the technical challenges of the AI workflows in its lifecycle and the AI as a service (AIaaS) in cloud network. The progress and deficiencies of the current research on AI functional architecture in various industry organizations are summarized. The end-to-end functional architecture for native AI for 6G network and its three key technical characteristics are proposed: quality of AI services (QoAIS) based AI service orchestration for its full lifecycle, deep integration of native AI computing and communication, and integration of native AI and digital twin network. The directions of future research are also prospected.

关键词: the 5th generation mobile communication system, the 6th generation mobile communication system, artificial intelligence, native intelligence, network intelligence, network architecture, mobile communication

Abstract: The application of the artificial intelligence (AI) technology in the 5th generation mobile communication system (5G) networks promotes the development of the mobile communication network and its application in vertical industries, however, the application models of "patching" and "plug-in" have hindered the effect of AI applications. Meanwhile, the application of AI in all walks of life puts forward requirements for new capabilities of the future network, such as distributed training, real-time collaborative inference, local data processing, etc. , which require "native intelligence design” in future networks. This paper discusses the requirements of native intelligence in the 6th generation mobile communication system (6G) networks from the perspectives of 5G intelligent network challenges and the “ubiquitous intelligence” vision of 6G, and analyzes the technical challenges of the AI workflows in its lifecycle and the AI as a service (AIaaS) in cloud network. The progress and deficiencies of the current research on AI functional architecture in various industry organizations are summarized. The end-to-end functional architecture for native AI for 6G network and its three key technical characteristics are proposed: quality of AI services (QoAIS) based AI service orchestration for its full lifecycle, deep integration of native AI computing and communication, and integration of native AI and digital twin network. The directions of future research are also prospected.

Key words: the 5th generation mobile communication system, the 6th generation mobile communication system, artificial intelligence, native intelligence, network intelligence, network architecture, mobile communication

中图分类号:

TN929.5

Liu Guangyi, Deng Juan, Zheng Qingbi, Li Gang, Sun Xin, Huang Yuhong. Native intelligence for 6G mobile network: technical challenges, architecture and key features[J]. The Journal of China Universities of Posts and Telecommunications, 2022, 29(1): 27-40.

参考文献

References

[1] LIU G Y, JIN J, WANG Q X, et al. 6G vision and demand: Digital twin and intelligent ubiquitous. Mobile Communications, 2020, 44(6): 3 - 9 (in Chinese).

[2] ITU-T Y. 3173—2020. Framework for evaluating intelligence levels of future networks including IMT-2020 (Study Group 13).

[3] 3GPP TS 37. 816 Version 1. 0. 0. Study on RAN-centric data collection and utilization for LTE and NR. 2019.

[4] 3GPP TR 23. 791. Study of enablers for network automation for 5G. 2018.

[5] 3GPP TSG-SA SP-190785. New WID self-organizing networks (SON) for 5G networks. 2021.

[6] ASHMORE R, CALINESCU R, PATERSON C. Assuring the machine learning lifecycle: Desiderata, methods, and challenges. ACM Computing Surveys, 2021, 54(5): Article 111.

[7] LETAIEF K B, CHEN W, SHI Y M, et al. The roadmap to 6G: AI empowered wireless networks. IEEE Communications Magazine, 2019, 57(8): 84 - 90.

[8] SHAFIN R, LIU L J, CHANDRASEKHAR V, et al. Artificial intelligence-enabled cellular networks: A critical path to beyond-5G and 6G. IEEE Wireless Communications, 2020, 27(2): 212 - 217.

[9] KATO N, MAO B M, TANG F X, et al. Ten challenges in advancing machine learning technologies toward 6G. IEEE Wireless Communications, 2020, 27(3): 96 - 103.

[10] LIN M T, ZHAO Y P. Artificial intelligence-empowered resource management for future wireless communications: A survey. China Communications, 2020, 17(3): 66 - 85.

[11] VAZQUEZ M N, PALLOIS J P, DEBBAH M, et al. Deploying artificial intelligence in the wireless infrastructure: The challenges ahead. Proceeding of the IEEE 2nd 5G World Forum (5GWF'19), 2019, Sept 30 - Oct 2, Dresden, Germany. Piscataway, NJ, USA: IEEE, 2019.

[12] LEE G M, UM T W, CHOI J K. AI as a microservice (AIMS) over 5G network. Proceeding of the 2018 ITU Kaleidoscope: Machine Learning for a 5G Future (ITU K'18), 2018, Nov 26 - 28, Santa Fe, Argentina. Piscataway, NJ, USA: IEEE, 2018.

[13] From cloud AI to network AI: A view from 6GANA. 6GANA (6G Alliance of Network AI). 2021.

[14] OUYANG Y, WANG L L, YANG A D, et al. The next decade of telecommunications artificial intelligence. ArXiv: 2101. 091632021.

[15] Improved operator experience through Experiential Networked Intelligence (ENI). ETSI White Paper No 22. 2017.

[16] Study on applying AI in telecommunication network. CCSA TC1-WG1#58 meeting, 2017.

[17] 3GPP RAN3 SI. RAN-centric data collection and utilization. 2018.

[18] 3GPP. 3GPP TR28. 805 V1. 1. 0. Study on management aspects of communication services. 2019.

[19] ITU-T Y. 3172—2019. Architectural framework for machine learning in future networks including IMT-2020 (Study Group 13).

[20] AI in Network use cases in China. White paper. GSMA, 2019.

[21] 3GPP. 3GPP TR28. 810 V17. 0. 0. Study on concept, requirements and solutions for levels of autonomous network (Release 17).

[22] FG ML5G Technical Specification "Requirements, architecture, and design for machine learning function orchestrator". ITU-T SG13-TD578 / WP1.

[23] FG ML5G Technical Specification "Machine learning sandbox for future networks including IMT-2020: Requirements and architecture framework". ITU-T SG13-TD575 / WP1.

[24] LIU G Y, HUANG Y H, LI N, et al. Vision, requirements and network architecture of 6G mobile network beyond 2030. China Communications, 2020, 17(9): 92 - 104.

[25] AMIRI M M, GUNDUZ D. Federated learning over wireless fading channels. IEEE Transactions on Wireless Communications, 2020, 19(5): 3546 - 3557.

[26] HUANG Y P, CHENG Y L, BAPNA A, et al. GPipe: Efficient training of giant neural networks using pipeline parallelism. Proceedings of the 33rd International Conference on Neural Information Processing Systems (NIPS'18), 2018, Dec 8 - 14, Vancouver, Canada. Red Hook, NY, USA: Curran Associates Inc, 2018: 1 - 10.

[27] TEERAPITTAYANON S, MCDANEL B, KUNG H T. Distributed deep neural networks over the cloud, the edge and end devices. Proceeding of the IEEE 37th International Conference on Distributed Computing Systems (ICDCS'17). 2017, Jun 5 - 8, Atlanta, GA, USA. Piscataway, NJ, USA: IEEE, 2017.

[28] WANG S Q, TUOR T, SALONIDIS T, et al. Adaptive federated learning in resource constrained edge computing systems. IEEE Journal on Selected Areas in Communications, 2019, 37(6): 1205 - 1221.

[29] DUNNER C, LUCCHI A, GARGIANI M, et al. A distributed second-order algorithm you can trust. Proceeding of the 35th International Conference on Machine Learning (ICML'18), 2018, Jul 10 - 15, Stockholm, Schweden. Piscataway, NJ, USA: IEEE, 2018: 1358 - 1366.

[30] ITU-T SG 13. Draft new recommendation ITU-T Y. DTN-ReqArch: "Requirements and architecture of digital twin network". 2020.

[31] DENG J, ZHENG Q B, LIU G Y, et al. A digital twin approach for self-optimization of mobile networks. 2021 IEEE Wireless Communications and Networking Conference Workshops (WCNCW), 2021, March 29, Nanjing, China. Piscataway, NJ, USA: IEEE, 2021: 1 - 6.

[32] LIU G Y, LI N, DENG J, et al. The SOLIDS 6G mobile network architecture: Driving forces, features, and functional topology. Engineering, 2021, DOI: 10.1016/j.eng.2021.07.013.

Native intelligence for 6G mobile network: technical challenges, architecture and key features

Native intelligence for 6G mobile network: technical challenges, architecture and key features

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	Guo Hui, Zhao Xuehui. Maximum throughput design of wireless powered communication network with IRS-NOMA based on user clustering [J]. 中国邮电高校学报(英文), 2023, 30(3): 55-64.
[2]	Zhang Ping, Xu Xiaodong, Dong Chen, Han Shujun, Wang Bizhu. Intellicise communication system: model-driven semantic communications[J]. 中国邮电高校学报(英文), 2022, 29(1): 2-12.
[3]	Sun Junshuai, Zhu Xinghui, Xiao Yeqiu, Cheng Ke, Zhao Shuangrui. Adaptive TTI bundling with self-healing scheme for 5G[J]. 中国邮电高校学报(英文), 2022, 29(1): 64-70.
[4]	Guo Hui, Zhao Xuehui. Maximum throughput design for IRS aided WPCN system based on NOMA[J]. 中国邮电高校学报(英文), 2022, 29(1): 93-101.
[5]	刘旭谢洋. Channel estimation for multi-panel millimeter wave MIMO based on joint compressed sensing [J]. 中国邮电高校学报(英文版), 2020, 27(6): 1-7.
[6]	郑霖, 汪震, 陈建梅, 林梦莹, 邓小芳. MIMO-FSK non-coherent detection with spatial multiplexing in fast-fading environment[J]. 中国邮电高校学报(英文版), 2020, 27(5): 47-54.
[7]	张永昌. Game-Based Distributed Noncooperation Interference Coordination Scheme in Ultra-Dense Networks[J]. 中国邮电高校学报(英文版), 2020, 27(5): 55-62.
[8]	李新民, 李国民, 刘洋, 郭甜, 李璞. Low-complexity transmit antenna selection algorithm for massive MIMO[J]. 中国邮电高校学报(英文版), 2020, 27(5): 63-68.
[9]	郭艳艳, Li Shuai, Wu Chao. QoS-based optimal and fair resource allocation for energy-efficiency uplink NOMA networks[J]. 中国邮电高校学报(英文版), 2020, 27(3): 83-92.
[10]	Xing Shuchen, Wen Xiangming, Lu Zhaoming, Pan Qi, Jing Wenpeng. Performance analysis and enhancement of random access process in cellular-IoT[J]. 中国邮电高校学报(英文版), 2019, 26(6): 1-10.
[11]	Peng Weiping, Su Zhe, Song Cheng, Jia Zongpu. Research on adaptive dual task offloading decision algorithm for parking space recommendation service[J]. 中国邮电高校学报(英文版), 2019, 26(6): 30-42.
[12]	李鑫谢刚高锦春. TMAHS: a truthful multi-unit double auction framework for heterogeneous spectrum in secondary market[J]. 中国邮电高校学报(英文版), 2019, 26(1): 82-94.
[13]	Qu Tuosi, Cao Haiyan, Xu Fangmin, Wang Xiumin. Low complexity detection algorithm based on optimized Neumann series for massive MIMO system[J]. 中国邮电高校学报(英文版), 2018, 25(6): 97-100.
[14]	黄沛昱史江盼甄岩. Spectrum allocation for wireless backhaul in heterogeneous ultra-dense networks[J]. 中国邮电高校学报(英文版), 2018, 25(3): 24-32.
[15]	Li Wanghong, Zhu Qi. Network selection algorithm based on AHP and similarity[J]. 中国邮电高校学报(英文版), 2018, 25(2): 77-88.