| 231 | 0 | 32 |
| 下载次数 | 被引频次 | 阅读次数 |
未来6G移动通信系统中，智能机器类通信（MTC）将在工业自动化、车联网等场景中发挥关键作用，对通信系统中无线信道建模的精度、实时性与自适应能力提出了前所未有的挑战。数字孪生信道（DTC）作为一种新兴的信道表征范式，能够在数字世界中构建物理信道的高保真映射，为6G系统提供动态环境下的感知、预测与决策支持。为推动DTC从理论概念走向实际应用，进一步提升其多模态数据融合以及多场景泛化能力，首次将信道大模型（ChannelLM）引入DTC实现框架，并围绕其核心架构展开关键技术设计与验证。具体而言，DTC架构由多模态环境感知与重构、无线环境知识（WEK），以及可泛化的ChannelLM三大核心技术支撑，分别实现对物理环境的高精度建模、环境-信道关系的可解释性构建，以及基于知识驱动的信道预测与通信策略生成。MTC典型场景的实验结果表明，所提方案在信道预测精度与场景泛化性方面有显著提升，为DTC技术在6G网络中的应用落地提供了有效的支撑路径。
Abstract：In future 6G mobile communication systems, intelligent machine-type communication(MTC) will play a pivotal role in scenarios such as industrial automation and vehicular networks, posing unprecedented challenges to the accuracy, real-time performance, and adaptability of wireless channel modeling. As an emerging paradigm for channel representation, the digital twin channel(DTC) enables highfidelity mapping of physical channels into the digital domain, providing sensing, prediction, and decision-making support for 6G systems in dynamic environments. To promote the transition of DTC from theoretical concept to practical engineering application, and to enhance its multimodal data fusion and cross-scenario generalization capabilities, this work integrates the channel large model(ChannelLM) into the DTC framework, focusing on the design and implementation of core technologies. Specifically, the DTC architecture is enabled by three key components: multimodal environment sensing and reconstruction, wireless environment knowledge(WEK) construction, and a generalizable ChannelLM. These components respectively support high-precision modeling of physical environments, interpretable construction of environment-channel relationships, knowledge-driven channel prediction, and communication strategy generation. Experimental results across typical MTC scenarios demonstrate that the proposed framework achieves high channel prediction accuracy and strong environmental adaptability, offering a viable pathway for the practical deployment of DTC in future 6G networks.
[1]张建华,田艺璇,孙语瞳,等.面向6G无线环境可预测的感知重构、语义表征及应用[J].中兴通讯技术, 2023, 29(5):38-44. DOI:10.12142/ZTETJ.202305007
[2] ZHANG J H, LIN J X, TANG P, et al. Channel measurement,modeling, and simulation for 6G:a survey and tutorial[EB/OL].(2023-05-26)[2025-03-21]. https://arxiv.org/abs/2305.16616
[3]张建华,王珩,张宇翔,等. 6G信道新特性与建模研究:挑战、进展与展望[J].中国科学:信息科学, 2024, 54(5):1114-1143. DOI:10.1360/SSI-2023-0259
[4] LIU G Y, HUANG Y H, LI N, et al. Vision, requirements and network architecture of 6G mobile network beyond 2030[J]. China communications, 2020, 17(9):92-104. DOI:10.23919/JCC.2020.09.008
[5]张建华，王玉洁，唐盼，等.工业互联网信道特性与建模研究综述[J].电波科学学报，2023, 38(1):3-14. DOI:10.13443/j.cjors.2022070401
[6] MO Q M, ZHANG Y X, WANG J L, et al. Multi-frequency channel measurement in smart factories:comparative analysis with 3GPP InF scenarios[C]//2024 IEEE 100th Vehicular Technology Conference(VTC2024-Fall). IEEE, 2024:1-5. DOI:10.1109/VTC2024-Fall63153.2024.10757555
[7] JIANG T, ZHANG J H, TANG P, et al. 3GPP standardized 5G channel model for IIo T scenarios:a survey[J]. IEEE Internet of Things Journal, 2021, 8(9):7196-7210.DOI:10.1109/JIOT.2020.3048992
[8] AHN Y, KIM W, SHIM B. Active user detection and channel estimation for massive machine-type communication:deep learning approach[J]. IEEE Internet of Things journal, 2021, 9(14):11904-11917. DOI:10.1109/JIOT.2021.3132329
[9] KHAREL B, LóPEZ O L A, ALVES H, et al. Ultra-reliable communication for critical machine type communication via CRAN-enabled multi-connectivity diversity schemes[J]. Sensors(basel), 2021, 21(23):8064. DOI:10.3390/s21238064
[10] SHARMILA M, SATYANARAYANA R V S. An intelligent resource allocation strategy for machine type communication environment[J]. International journal of communication systems, 2024, 37(1):e5628. DOI:10.1002/dac.5628
[11] WANG H, ZHANG J H, NIE G F, et al. Digital twin channel for6G:concepts, architectures and potential applications[J]. IEEE communications magazine, 2025, 63(3):24-30. DOI:10.1109/MCOM.001.2400213
[12] ZHANG J H. The interdisciplinary research of big data and wireless channel:a cluster-nuclei based channel model[J].China communications, 2016, 13(2):14-26. DOI:10.1109/CC.2016.7405719
[13] YU L, ZHANG Y X, ZHANG J H, et al. Implementation framework and validation of cluster-nuclei based channel model using environmental mapping for 6G communication systems[J].China communications, 2022, 19(4):1-13. DOI:10.23919/JCC.2022.04.001
[14]张建华,杨育捷,张平.确定智能基站位置的方法、装置及存储介质:ZL201811176132.4[P]. 2018-10-10
[15] ZHANG Z, ZHANG Y X, ZHANG J H, et al. Adversarial trainingaided time-varying channel prediction for TDD/FDD systems[J].China communications, 2023, 20(6):100-115. DOI:10.23919/JCC.fa.2020-0698.202306
[16] WANG K, YU L, ZHANG J H, et al. Multi-modal environmental sensing based path loss prediction for V2I communications[EB/OL].(2024-12-10)[2025-06-20]. https://arxiv.org/abs/2412.07681
[17] LIU G Y, WANG J Z, LI R P, et al. Artificial-intelligenceempowered digital-twin-based network autonomy[J]. Frontiers of information technology&electronic engineering, 2025, 26(2):157-160. DOI:10.1631/FITEE.2510000
[18] LIU G Y, ZHU Y H, KANG M C, et al. Native design for 6G digital twin network:use cases,architecture,functions and key technologies[EB/OL].(2025-03-24)[2025-05-15].https://ieeexplore.ieee.org/abstract/document/10937141
[19]SHI L Z,ZHANG J H,YU L,et al.Can wireless environment information decrease pilot overhead:a channel prediction example[J].IEEE wireless communications letters,2025,14(3):861-865.DOI:10.1109/LWC.2025.3526271
[20]ZHANG Z,ZHANG J H,ZHANG Y X,et al.AI-based time-,frequency-,and space-domain channel extrapolation for 6G:opportunities and challenges[J].IEEE vehicular technology magazine,2023,18(1):29-39.DOI:10.1109/MVT.2023.3234169
[21]SHEN Z B,YU L,ZHANG Y X,et al.DataAI-6G:a system parameters configurable channel dataset for AI-6G research[C]//Proceedings of IEEE Globecom Workshops (GC Wkshps).IEEE,2023:1910-1915.DOI:10.1109/GCWkshps58843.2023.10464657
[22]SUN Y T,ZHANG J H,ZHANG Y X,et al.Environment featuresbased model for path loss prediction[J].IEEE wireless communications letters,2022,11(9):2010-2014.DOI:10.1109/LWC.2022.3192516
[23]SUN Y T,ZHANG J H,YU L,et al.How to define the propagation environment semantics and its application in scatterer-based beam prediction[J].IEEE wireless communications letters,2023,12(4):649-653.DOI:10.1109/LWC.2023.3237827
[24]ZHANG Z,ZHANG J H,ZHANG Y X,et al.Deep reinforcement learning based dynamic beam selection in dual-band communication systems[J].IEEE transactions on wireless communications,2024,23(4):2591-2606.DOI:10.1109/TWC.2023.3300830
[25]WANG J L,ZHANG J H,ZHANG Y X,et al.Radio environment knowledge pool for 6G digital twin channel[J].IEEEcommunications magazine,2025,63(5):158-164.DOI:10.1109/MCOM.003.2400168
[26]GUAN Y C,ZHANG J H,TIAN L,et al.A comparative study for indoor factory environments at 4.9 and 28 GHz[C]//Proceedings of 14th European Conference on Antennas and Propagation(EuCAP).IEEE,2020:1-5.DOI:10.23919/EuCAP48036.2020.9135294
[27]ZHANG X,QIU G,ZHANG J H,et al.Analysis of millimeterwave channel characteristics based on channel measurements in indoor environments at 39 GHz[C]//2019 11th International conference on wireless Communications and Signal Processing(WCSP).IEEE,2019:1-6.DOI:10.1109/WCSP.2019.8928017
[28]WANG F Y,ZHANG Y X,TANG P,et al.Effects of inaccuracies of indoor environment databases on ray tracing results[C]//Proceedings of IEEE 93rd Vehicular Technology Conference(VTC2021-Spring).IEEE,2021:1-7.DOI:10.1109/vtc2021-spring51267.2021.9448968
[29]ZHANG J H,CAI Y C,YU L,et al.Wireless environment information sensing,feature,semantic,and knowledge:four steps towards 6G AI-enabled air interface[EB/OL].(2024-09-28)[2025-03-21].https://arxiv.org/abs/2409.19331
[30]ZHANG J H,YU L,LIU S Y,et al.Wireless environmental information theory:a new paradigm towards 6G online and proactive environment intelligence communication[EB/OL].(2024-12-16)[2025-03-21].https://arxiv.org/abs/2412.11479
[31]WANG J L,ZHANG J H,SUN Y T,et al.Electromagnetic wave property inspired radio environment knowledge construction and artificial intelligence based verification for 6G digital twin channel[J].Frontiers of information technology&electronic engineering, 2025,26(2):260-277.DOI:10.1631/fitee.2400464
[32]张兆灵,于力,张宇翔,等.无线环境知识表示方法研究--工业互联网场景的应用[J].移动通信,2025,49(5):63-66.DOI:10.13982/j.cnki.mtc.2025.05063
[33]HU E J,SHEN Y,WALLIS P,et al.LoRA:low-rank adaptation of large language models[EB/OL].(2021-06-17)[2025-06-20].https://arxiv.org/abs/2106.09685
[34]RADFORD A,WU J,CHILD R,et al.Language models are unsupervised multitask learners[EB/OL].(2019-02-14)[2025-06-20].https://openai.com/blog/better-language-models/
[35]YU L,SHI L Z,ZHANG J H,et al.ChannelGPT:a large model to generate digital twin channel for 6G environment intelligence[EB/OL].(2025-06-06)[2025-06-20].https://arxiv.org/abs/2410.13379
[36]张建华,史廉正,于力,等.信道通用预训练大模型赋能数字孪生信道:原理与实践[J].无线电工程,2025,55(4):679-686.DOI:10.1360/SSI-2023-0355
[37]ZHAO Y Z,YU L,SHI L Z,et al.Multi-modal large models based beam prediction:an example empowered by DeepSeek[EB/OL].(2025-06-06)[2025-06-20].https://arxiv.org/abs/2506.05921
[38]ALKHATEEB A,CHARAN G,OSMAN T,et al.DeepSense 6G:a large-scale real-world multi-modal sensing and communication dataset[J].IEEE communications magazine,2023,61(9):122-128.DOI:10.1109/MCOM.006.2200730
基本信息:
DOI：
中图分类号:TN929.5
引用信息:
[1]于力,张建华,蔡逸辰.6G数字孪生信道的三个使能技术多模态感知、环境知识和大模型[J].中兴通讯技术,2025,31(04):19-28.
基金信息:
国家自然科学基金项目（62401084,62525101）