Cross-domain knowledge-driven meta-intelligent network algorithm framework for 6G

Lin Jiaqi; Qian Qijie; Zhong Xudong; Feng Tao; Gao Xianming; Ge Jiaxin; Peng Mugen; Ren Baoquan

doi:10.11959/j.issn.2096-3750.2026.00503

您当前的位置：

首页 >

文章列表页 >

Cross-domain knowledge-driven meta-intelligent network algorithm framework for 6G

Theory and Technology | 更新时间：2026-04-16

- Cross-domain knowledge-driven meta-intelligent network algorithm framework for 6G
- Chinese Journal on Internet of Things Vol. 10, Issue 1, Pages: 81-98(2026)
- 作者机构：
  
  1.北京邮电大学网络与交换技术全国重点实验室，北京 100876
  2.军事科学院系统工程研究院，北京 100141
  3.南京邮电大学通信与信息工程学院，江苏南京 210003
- 作者简介：
- 基金信息：
  
  the Key Laboratory Fund of National Defense(6142006240401)
- DOI：10.11959/j.issn.2096-3750.2026.00503
  CLC： TN915.5
- Received：14 May 2025，
  
  Revised：2025-07-02，
  
  Accepted：18 July 2025，
  
  Published：30 March 2026
- 稿件说明：
移动端阅览
林佳琦,钱琪杰,钟旭东等.面向6G的跨域知识驱动网络元智能算法框架[J].物联网学报,2026,10(01):81-98.

Lin Jiaqi,Qian Qijie,Zhong Xudong,et al.Cross-domain knowledge-driven meta-intelligent network algorithm framework for 6G[J].Chinese Journal on Internet of Things,2026,10(01):81-98.
林佳琦,钱琪杰,钟旭东等.面向6G的跨域知识驱动网络元智能算法框架[J].物联网学报,2026,10(01):81-98. DOI： 10.11959/j.issn.2096-3750.2026.00503.

Lin Jiaqi,Qian Qijie,Zhong Xudong,et al.Cross-domain knowledge-driven meta-intelligent network algorithm framework for 6G[J].Chinese Journal on Internet of Things,2026,10(01):81-98. DOI： 10.11959/j.issn.2096-3750.2026.00503.

摘要

为应对现有自动化运维模型在6G多场景、实时化智能管理中的能力瓶颈，提出了一种跨域知识驱动的网络元智能算法框架。现有方案多依赖静态规则或单域优化，难以适配6G网络在复杂环境感知、动态策略迁移与多目标调度方面的综合需求。该框架将网络状态建模为环境域、网络域与用户行为域3类知识源，基于轻量化模型与图神经网络实现高层意图解析与跨域知识的在线融合，并通过知识蒸馏机制动态地更新全局知识库。在此基础上构建多层网络元智能体，形成“感知→推理→知识生成→决策下发→验证优化→记忆检索”的闭环控制流程，辅以自监督、强化与元学习，实现策略的快速迁移与持续演进。围绕低空交通管控场景，设计了3类典型任务：跨域组网、意图引导的智能体管理与蜂群路径规划。实验结果表明，所提方法在吞吐量、故障恢复时间、流量预测精度、决策时延、执行成功率、资源公平度、路径效率与任务成功率等关键指标上均取得了显著的提升。

Abstract

A cross-domain knowledge-driven meta-intelligent network algorithm framework was proposed in this paper to address the limitations of existing automated operation and maintenance models in supporting multi-scenario and real-time intelligent management in 6G networks. Traditional approaches often rely on static rules or single-domain optimization

which are insufficient for 6G demands such as heterogeneous perception

dynamic policy adaptation

and multi-objective scheduling. The framework modeled network states across environmental

network

and user behavior domains

leveraging lightweight models and graph neural networks for high-level intent parsing and online knowledge fusion. A global knowledge base was dynamically updated via knowledge distillation. Multi-layer meta-intelligent agents formed a closed-loop control process of perception

reasoning

knowledge generation

decision issuance

validation

and memory retrieval. Self-supervised learning

reinforcement learning

and meta-learning techniques were integrated to support rapid policy adaptation and continual optimization. Centered on a low-altitude traffic control scenario

the framework was evaluated through three tasks: knowledge-driven networking

intent-guided agent management

and swarm path planning. Experimental results show that the proposed method consistently outperforms baseline approaches in throughput

failure recovery time

traffic prediction accuracy

decision latency

execution success rate

resource fairness

path efficiency

and task success rate.

关键词

Keywords

references

Long S F , Tang F X , Li Y F , et al . 6G comprehensive intelligence: network operations and optimization based on large language models [J ] . IEEE Network , 2025 , 39 ( 4 ): 192 - 201 .

Park K , Sung S , Kim H , et al . Technology trends and challenges in SDN and service assurance for end-to-end network slicing [J ] . Computer Networks , 2023 , 234 : 109908 .

Coronado E , Behravesh R , Subramanya T , et al . Zero touch management: a survey of network automation solutions for 5G and 6G networks [J ] . IEEE Communications Surveys & Tutorials , 2022 , 24 ( 4 ): 2535 - 2578 .

Mestres A , Rodriguez-Natal A , Carner J , et al . Knowledge-defined networking [J ] . ACM SIGCOMM Computer Communication Review , 2017 , 47 ( 3 ): 2 - 10 .

Clark D D , Partridge C , Ramming J C , et al . A knowledge plane for the Internet [C ] // Proceedings of the 2003 Conference on Applications, Technologies, Architectures, and Protocols for Computer Communications . New York : ACM Press , 2003 : 3 - 10 .

Dang W S , Huang R , Yu Y J , et al . Autonomous driving network: network architecture in the era of autonomy [M ] . Boca Raton : CRC Press , 2023 .

Yang K Q , He Q , Wang X W , et al . KDN-based adaptive computation offloading and resource allocation strategy optimization: maximizing user satisfaction [J ] . IEEE Transactions on Computers , 2025 , 74 ( 5 ): 1743 - 1757 .

Chaccour C , Saad W , Debbah M , et al . Less data, more knowledge: building next-generation semantic communication networks [J ] . IEEE Communications Surveys & Tutorials , 2025 , 27 ( 1 ): 37 - 76 .

杨静雅 , 唐晓刚 , 周一青 , 等 . 意图抽象与知识联合驱动的6G内生智能网络架构 [J ] . 通信学报 , 2023 , 44 ( 2 ): 12 - 26 .

Yang J Y , Tang X G , Zhou Y Q , et al . 6G native intelligence network architecture enabled by intent abstraction and knowledge [J ] . Journal on Communications , 2023 , 44 ( 2 ): 12 - 26 .

Benoudifa O , Ait Wakrime A , Benaini R . Autonomous solution for controller placement problem of software-defined networking using MuZero based intelligent agents [J ] . Journal of King Saud University - Computer and Information Sciences , 2023 , 35 ( 10 ): 101842 .

Jiang F B , Peng Y B , Dong L , et al . Large language model enhanced multi-agent systems for 6G communications [J ] . IEEE Wireless Communications , 2024 , 31 ( 6 ): 48 - 55 .

Tosounidis V , Pavlidis G , Sakellariou I . Deep Q-learning for load balancing traffic in SDN networks [C ] // Proceedings of the 11th Hellenic Conference on Artificial Intelligence . New York : ACM Press , 2020 : 135 - 143 .

Bi W D , Cheng X Q , Xu B B , et al . Bridged-GNN: knowledge bridge learning for effective knowledge transfer [C ] // Proceedings of the 32nd ACM International Conference on Information and Knowledge Management . New York : ACM Press , 2023 : 99 - 109 .

Abd Elaziz M , Al-qaness M A A , Dahou A , et al . Evolution toward intelligent communications: impact of deep learning applications on the future of 6G technology [J ] . WIREs Data Mining and Knowledge Discovery , 2024 , 14 : e1521 .

Dayaratne T , Vo V , Lai S , et al . Exploiting and securing ML solutions in near-RT RIC: a perspective of an xApp [PP ] . V1. arXiv ( 2024-06-18 )[ 2025-04-20 ] . arXiv: 2406.12299 .

He C , Annavaram M , Avestimehr S . Group knowledge transfer: federated learning of large cnns at the edge [J ] . Advances in Neural Information Processing Systems , 2020 , 33 : 14068 - 14080 .

Yu X , He Z , Sun Y , et al . The effect of personalization in fedProx: A fine-grained analysis on statistical accuracy and communication efficiency [J ] . arXiv , 2024 , preprint arXiv: 2410.08934 .

Vettoruzzo A , Bouguelia M R , Vanschoren J , et al . Advances and challenges in meta-learning: a technical review [J ] . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2024 , 46 ( 7 ): 4763 - 4779 .

Sternberg R J , Glaveanu V , Karami S , et al . Meta-intelligence: understanding, control, and interactivity between creative, analytical, practical, and wisdom-based approaches in problem solving [J ] . Journal of Intelligence , 2021 , 9 ( 2 ): 19 .

尹浩 . 智能信息网络理论与技术 [M ] . 北京 : 人民邮电出版社 , 2024 .

Yin H . Intelligent information network theory and technology [M ] . Beijing : Posts & Telecom Press , 2024 .

Dong N N , Yin H , Ren B Q , et al . Research on network cognition model and mechanism of intelligent information network [J ] . China Communications , 2023 , 20 ( 2 ): 257 - 277 .

Lamberti L , Bellone L , Macan L , et al . Distilling tiny and ultra-fast deep neural networks for autonomous navigation on nano-UAVs [J ] . IEEE Internet of Things Journal , 2024 , 11 ( 20 ): 33269 - 33281 .

Ouyang Y , Yang C , Song Y , et al . A brief survey and implementation on refinement for intent-driven networking [J ] . IEEE Network , 2022 , 35 ( 6 ): 75 - 83 .

Song Y , Yang C , Zhang J , et al . Full-life cycle intent-driven network verification: challenges and approaches [J ] . IEEE Network , 2022 , 37 ( 5 ): 145 - 153 .

Ouyang Y , Li C , Zhang J , et al . Intent-driven 6G end-to-end Network orchestration [C ] // Proceedings of the IEEE INFOCOM 2024-IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS) . Pisataway : IEEE Press , 2024 : 1 - 2 .

Farhan M , Shah N , Wang L , et al . RDG-TE: link reliability-aware DRL-GNN-based traffic engineering in SDN [J ] . Expert Systems with Applications , 2025 , 265 : 125963 .

Ouyang Y , Lin J , Feng T , et al . Intent-driven CoX resource management for space-terrestrial networks [J ] . IEEE Wireless Communications , 2023 , 31 ( 3 ): 339 - 347 .

He Q , Wang Y , Wang X , et al . Routing optimization with deep reinforcement learning in knowledge defined networking [J ] . IEEE Transactions on Mobile Computing , 2023 , 23 ( 2 ): 1444 - 1455 .

Zhou S , Zhao S Z , Ren Z Q . Loosely synchronized rule-based planning for multi-agent path finding with asynchronous actions [J ] . Proceedings of the AAAI Conference on Artificial Intelligence , 2025 , 39 ( 14 ): 14763 - 14770 .

Wu Y L , Lin G Z , Ge J G . Knowledge-powered explainable artificial intelligence for network automation toward 6G [J ] . IEEE Network , 2022 , 36 ( 3 ): 16 - 23 .

Hart P E , Nilsson N J , Raphael B . A formal basis for the heuristic determination of minimum cost paths [J ] . IEEE Transactions on Systems Science and Cybernetics , 1968 , 4 ( 2 ): 100 - 107 .

Lin J Q , Qian Q J , Ren B Q , et al . A knowledge-driven meta-learning method for ultra-fast path planning in lightweight UAVs [C ] // Proceedings of the ICC 2025 - IEEE International Conference on Communications . Piscataway : IEEE Press , 2025 : 1292 - 1297 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

No data

Related Author

Lin Jiaqi

Peng Mugen

Related Institution

State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications

⁰