浏览全部资源
扫码关注微信
中国移动通信有限公司研究院,北京 100053
[ "史嫄嫄(1984- ),女,博士,中国移动通信有限公司研究院研究员,主要研究方向为5G/5G-Advanced核心网、网络智能化。" ]
[ "魏彬(1983- ),男,中国移动通信有限公司研究院网络与IT技术研究所副所长,主要研究方向为5G专网、5G工业互联网、网络智能化等领域的标准化、商用技术攻关及产业推动。" ]
[ "李爱华(1974- ),男,中国移动通信有限公司研究院网络与IT技术研究所技术经理,主要研究方向为5G-Advanced架构演进、网络智能化及运行大模型、物联网技术等。" ]
[ "胥铭(1997- ),男,博士,中国移动通信有限公司研究院研究员,主要研究方向为网络智能化、网络大模型等。" ]
[ "张煜民(1998- ),男,中国移动通信有限公司研究院研究员,主要研究方向为网络智能化、大模型技术、数据处理技术等。" ]
[ "沈珅(1988- ),男,中国移动通信有限公司研究院研究员,主要研究方向为人工智能与网络智能化。" ]
[ "孟晗(1997- ),女,博士,中国移动通信有限公司研究院研究员,主要研究方向为5G-Advanced架构演进、网络智能化、低空通感技术等。" ]
[ "姜宇(1994- ),男,中国移动通信有限公司研究院研究员,主要研究方向为网络AI融合、通信网络AI模型设计等。" ]
[ "刘乐(1996- ),男,中国移动通信有限公司研究院研究员,主要研究方向网络智能化的标准化、架构及关键技术。" ]
收稿日期:2024-09-14,
修回日期:2024-11-04,
纸质出版日期:2024-12-20
移动端阅览
史嫄嫄,魏彬,李爱华等.5G-Advanced核心网运行智能架构演进、关键技术及应用研究[J].电信科学,2024,40(12):146-162.
SHI Yuanyuan,WEI Bin,LI Aihua,et al.Research on the evolution, key technologies, and applications for AI enabled 5G-Advanced core network running[J].Telecommunications Science,2024,40(12):146-162.
史嫄嫄,魏彬,李爱华等.5G-Advanced核心网运行智能架构演进、关键技术及应用研究[J].电信科学,2024,40(12):146-162. DOI: 10.11959/j.issn.1000-0801.2024255.
SHI Yuanyuan,WEI Bin,LI Aihua,et al.Research on the evolution, key technologies, and applications for AI enabled 5G-Advanced core network running[J].Telecommunications Science,2024,40(12):146-162. DOI: 10.11959/j.issn.1000-0801.2024255.
5G作为万物互联新时代的关键基础设施,智能化是其重要发展方向。在5G-Advanced(简称5G-A)阶段,核心网运行智能通过AI技术与网络运行机制深度融合,可显著提升网络效率,实时感知并精准保障多样化业务需求。面向5G-A网络,重点介绍了核心网运行智能总体架构、关键技术及应用。首先,分析了5G-A核心网运行发展趋势并阐述重点智能应用;其次,提出了“四层四维”核心网运行智能架构,包括智能分析中心层、控制面智能内生层、边缘实时推理层、端侧轻量推理层共4层,可实时定制化采集切片、网元、用户和业务流4个维度,提供数据感知、训练、推理等智能分析服务;再次,介绍了核心网运行智能5项关键技术和能力;最后,聚焦于核心网运行智能典型业务需求,深入分析并总结了相关解决方案及其效果,为5G-A核心网智能化的应用和落地提供了新思路。
5G serves as the pivotal infrastructure for the emerging era of the Internet of everything
with intelligentization being its crucial direction. In the 5G-Advanced (5G-A) phase
AI enabled core network running can substantially enhance network efficiency
facilitate real-time perception
and precisely cater to diversified service demands through the deep integration of AI technology and network running mechanisms. For the 5G-A network
the overall intelligent architecture
key technologies
and applications of AI enabled core network operations were highlighted. Firstly
the development trend of AI enabled 5G-A core network running was analyzed and key intelligent applications were elaborated. Secondly
AI enabled core network running architecture combining four layers and four dimensions was proposed
encompassing a central intelligent analysis layer
a control plane intelligent endogenous layer
an edge real-time inference layer
and an on-device lightweight inference layer. This architecture enables customized
real-time data collection across four dimensions: slices
network elements
users
and service flows
thereby offering intelligent analysis services such as data perception
training
and inference. Then
five key technologies and capabilities of AI enabled core network running were introduced. Finally
focusing on the typical service requirements of AI enabled core network running
the relevant solutions and their results were analyzed and summarized
thus providing new ideas for the application and implementation of 5G-A core network intelligence.
CHEN Y X , LI R P , ZHAO Z F , et al . NetGPT: an AI-native network architecture for provisioning beyond personalized generative services [J ] . IEEE Network , 2024 ( 99 ): 1 .
3GPP. Architecture enhancements for 5G system to support network data analytics services (Release 15): TS 23.288 [S ] . 2020 .
中国移动通信有限公司研究院 . 网络运行智能架构与场景白皮书 [R ] . 2024 .
China Mobile Research Institute . Network intelligent architecture and running scene, the white paper [R ] . 2024 .
3GPP. Architecture enhancements for 5G system to support network data analytics services (Release 18): TS 23.288 V18.6.0 [S ] . 2024 .
3GPP. System architecture for the 5G system(5GS); Stage2: TS 23.501 V19.0.0 [S ] . 2024 .
华为技术有限公司 , 中国移动通信有限公司 , 鹏城实验室 . 6G网络内生智能架构及关键技术白皮书: 以数据为中心&ICDT深度融合的网络架构 [R ] . 2023 .
Huawei Technologies Co. , Ltd. , China Mobile Communications Co. , Ltd. , Pengcheng Lab . White paper on internal intelligent architecture and key technologies of 6G networks: data-centric & ICDT depth fusion network architecture [R ] . 2023 .
IMT-2030 (6G)推进组 . 面向6G网络的智能内生体系架构研究 [EB ] . 2023 .IMT-2030(6G) Promotion Group. Research on intelligent endogenous architecture for 6G network[EB ] . 2023.
任驰 , 马瑞涛 , 穆佳 . 支持原生数据分析能力的5G核心网架构增强研究 [J ] . 邮电设计技术 , 2021 ( 9 ): 940 - 945 .
REN C , MA R T , MU J . Research on 5G core network architecture enhancements for supporting native data analytics capability [J ] . Designing Techniques of Posts and Telecommunications , 2021 ( 9 ): 940 - 945 .
XU C W , MCAULEY J . A survey on model compression and acceleration for pretrained language models [J ] . Proceedings of the AAAI Conference on Artificial Intelligence , 2023 , 37 ( 9 ): 10566 - 10575 .
李爱华 , 吴晓波 , 陈超 , 等 . 5G网络大数据智能分析技术 [J ] . 电信科学 , 2022 , 38 ( 8 ): 129 - 139 .
LI A H , WU X B , CHEN C , et al . Big data intelligent analysis technology for 5G network [J ] . Telecommunications Science , 2022 , 38 ( 8 ): 129 - 139 .
QU G Q , CHEN Q Y , WEI W , et al . Mobile edge intelligence for large language models: a contemporary survey [EB ] . 2024 .
CCSA . 面向公众应用的移动互联网网络质量评价指标和评测方法云游戏类: T/CCSA 477-2023 [S ] . 2023 .
CCSA . Mobile Internet network quality evaluation index and evaluation method for public application Cloud Games: T/CCSA 477-2023 [S ] . 2023 .
TAYLOR V F , SPOLAOR R , CONTI M , et al . Robust smartphone app identification via encrypted network traffic analysis [J ] . IEEE Transactions on Information Forensics and Security , 2018 , 13 ( 1 ): 63 - 78 .
MENG X Y , LIN C C , WANG Y Q , et al . NetGPT: generative pretrained transformer for network traffic [J ] . arXiv prepint arXiv: 2304 . 09513 v 1 , 2023 .
DEVLIN J , CHANG M , LEE K , et al . BERT: pre-training of deep bidirectional transformers for language understanding [C ] // Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) . Association for Computational Linguistics , 2019 : 4171 - 4186 .
CHEN Z , BADRINARAYANAN V , LEE C Y , et al . GradNorm: gradient normalization for adaptive loss balancing in deep multitask networks [J ] . arXiv prepint arXiv: 1711.02257 , 2017 .
0
浏览量
19
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构