Network configuration translation methods under low-resource scenarios

SHI Hongwei; SHI Jingwen; HUANG Tao

doi:10.11959/j.issn.1000-0801.DXKX260165

Chinese

您当前的位置：

首页 >

文章列表页 >

Network configuration translation methods under low-resource scenarios

更新时间：2026-07-08

- Network configuration translation methods under low-resource scenarios
- Telecommunications Science (2026)
- 作者机构：
  
  1.东南大学网络空间安全学院，江苏南京 211189
  2.紫金山实验室未来网络研究中心，江苏南京 211111
  3.北京邮电大学网络与交换技术国家重点实验室，北京 100876
- 作者简介：
- 基金信息：
  
  The Industrial Internet Innovation and Development Project of Ministry of Industry and Information Technology(TC240AAKM-137);The National Engineering Research Center for Next Generation Internet Broadband Service Applications Project of China United Network Communications Group Co., Ltd(2025-STHZ-ZJSSYS-001)
- DOI：10.11959/j.issn.1000-0801.DXKX260165
  CLC： TP393
- Received：11 March 2026，
  
  Revised：2026-06-02，
  
  Accepted：08 July 2026，
- 稿件说明：
移动端阅览
SHI Hongwei, SHI Jingwen, HUANG Tao. Network configuration translation methods under low-resource scenarios[J/OL]. Telecommunications Science, 2026.
DOI：

SHI Hongwei, SHI Jingwen, HUANG Tao. Network configuration translation methods under low-resource scenarios[J/OL]. Telecommunications Science, 2026. DOI： 10.11959/j.issn.1000-0801.DXKX260165.

摘要

针对跨厂商网络设备配置转换场景中低语料条件下转换准确性与稳定性不足的问题，提出了一种基于Transformer架构的网络配置转换模型（network configuration translation model，NetConfigTM）。该方法融合网络配置领域特性，构建面向配置语义的训练机制，通过对有限配置语料进行扩展与建模，在低标注条件下实现有效特征学习。进一步引入掩码语言建模、去噪自编码与有监督微调相结合的多阶段训练策略，增强模型对跨厂商配置语法结构与语义映射关系的建模能力。基于脱敏网络配置数据开展实验验证，结果表明，该方法在多类典型配置场景下能够保持稳定、可靠的转换准确性，并可将人工方式下天级的配置转换过程缩短至分钟级，验证了其在跨厂商网络环境中开展自动化配置转换的工程可行性。

Abstract

To address the insufficient accuracy and stability of network configuration translation under low-resource scenarios in cross-vendor environments

a Transformer-based network configuration translation model (NetConfigTM) was proposed. The model integrated domain characteristics of network configurations and constructed a configuration-semantic-oriented training mechanism. By expanding and modeling limited configuration corpora

effective feature learning was realized under low-label conditions. Furthermore

a multi-stage training strategy combining masked language modeling

denoising autoencoding

and supervised fine-tuning was introduced to enhance the modeling capability of cross-vendor configuration syntax structures and semantic mapping relationships. Experiments conducted on desensitized network configuration data demonstrated that the proposed method maintained stable and reliable translation accuracy in multiple typical configuration scenarios and reduced the configuration translation time from days of manual operation to minutes

verifying its engineering feasibility for automated configuration translation in cross-vendor network environments.

关键词

Keywords

references

PATRI S K , GRIGOREVA E , KELLERER W , et al . Rational agent-based decision algorithm for strategic converged network migration planning [J ] . Journal of Optical Communications and Networking , 2019 , 11 ( 7 ): 371 - 382 .

ZHANG Z , PENG Z , YU H , et al . Digital network twins for next-generation wireless: Creation, optimization, and challenges [J ] . IEEE Network , 2025 : 1 - 9 .

TRAYNOR P , ENCK W , MCDANIEL P , et al . Exploiting open functionality in SMS-capable cellular networks [J ] . Journal of Computer Security , 2008 , 16 ( 6 ): 713 - 742 .

DING W , LI J , NIU Z , et al . Automating network configuration with natural language intents [C ] // Proceedings of the ACM SIGCOMM 2024 Conference: Posters and Demos . Sydney : ACM , 2024 : 19 - 21 .

SEEGER J , BRÖRING A , PAHL M O , et al . Rule-based translation of application-level QoS constraints into SDN configurations for the IoT [C ] // 2019 European Conference on Networks and Communications . Valencia : IEEE , 2019 : 432 - 437 .

NI D , YANG Y , SHEN Y , et al . Configuration tree-based network device parameter generation and deployment framework [C ] // 2025 International Conference on Electrical Automation and Artificial Intelligence . Xiamen : IEEE , 2025 : 434 - 438 .

LI P , LI L , ZHANG M , et al . Universal conditional masked language pre-training for neural machine translation [C ] // Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics . Dublin : ACL , 2022 : 6379 - 6391 .

CHEN H , MIAO Y , CHEN L , et al . Software-defined network assimilation: Bridging the last mile towards centralized network configuration management with NAssim [C ] // Proceedings of the ACM SIGCOMM 2022 Conference . Amsterdam : ACM , 2022 : 281 - 297 .

CONNEAU A , LAMPLE G . Cross-lingual language model pretraining [C ] // Proceedings of the 33rd International Conference on Neural Information Processing Systems . Vancouver : NIPS , 2019 : 7059 - 7069 .

LI F , ZHANG J , LI M , et al . Opportunities and implementation of neural machine translation for network configuration [J ] . IEEE Network , 2023 , 37 ( 4 ): 82 - 89 .

LI F , LIANG B , LANG H , et al . Preconfig: A unified language model framework for network configuration automation [J ] . IEEE Transactions on Cognitive Communications and Networking , 2026 , 12 : 6320 - 6330 .

WEI Y , XIE X , HU T , et al . Inta: Intent-based translation for network configuration with llm agents [C ] // 2025 IEEE 33rd International Conference on Network Protocols (ICNP) , 2025 : 1 - 16 .

VASWANI A , SHAZEER N , PARMAR N , et al . Attention is all you need [C ] // Proceedings of the 31st International Conference on Neural Information Processing Systems . Long Beach : NIPS , 2017 : 6000 - 6010 .

NAKAMURA K , SUZUKI H , OGATA S , et al . A Method to Automatically Extract a Network Device Configuration Model by Parsing Network Device Configurations [EB/OL ] . ( 2025-11-01 )[ 2026-03-09 ] . https://arxiv.org/abs/2511.17948 https://arxiv.org/abs/2511.17948 .

FENG Z , GUO D , TANG D , et al . CodeBERT: A pre-trained model for programming and natural languages [C ] // Findings of the Association for Computational Linguistics: EMNLP 2020 . Online : ACL , 2020 : 1536 - 1547 .

DONG L , YANG N , WANG W , et al . Unified language model pre-training for natural language understanding and generation [C ] // Proceedings of the 33rd International Conference on Neural Information Processing Systems . Vancouver : NIPS , 2019 : 13063 - 13075 .

FADAEE M , BISAZZA A , MONZ C . Data augmentation for low-resource neural machine translation [C ] // Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics . Vancouver : ACL , 2017 : 567 - 573 .

SHUTTLEWORTH R , ANDREAS J , TORRALBA A , SHARMA P . LoRA vs Full Fine-tuning: An Illusion of Equivalence [EB/OL ] . ( 2024-10-28 )[ 2026-06-02 ] . https://arxiv.org/abs/2410.21228 https://arxiv.org/abs/2410.21228 .

ZHANG B , CHENG Y , SHAKERI S , et al . Encoder-Decoder or Decoder-Only? Revisiting Encoder-Decoder Large Language Model[EB/OL ] . ( 2025-10-17 )[ 2026-03-09 ] . https://arxiv.org/abs/2510.26622 https://arxiv.org/abs/2510.26622 .

PAPINENI K , ROUKOS S , WARD T , et al . Bleu: A method for automatic evaluation of machine translation [C ] // Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics (ACL) . Philadelphia, Pennsylvania, USA , 2002 : 311 - 318 .

RAFFEL C , SHAZEER N , ROBERTS A , et al . Exploring the limits of transfer learning with a unified text-to-text transformer [J ] . Journal of Machine Learning Research , 2020 , 21 ( 1 ): 5485 - 5551 .

ZHANG J , ZHAO Y , SALEH M , et al . PEGASUS: Pre-training with extracted gap-sentences for abstractive summarization [C ] // Proceedings of the 37th International Conference on Machine Learning . Vienna : ICML , 2020 : 11328 - 11339 .

石鸿伟 , 苏琛 , 倪中阳 , 等 . 面向IP承载网的数模双驱动孪生网络系统架构研究 [J ] . 电信科学 , 2025 , 41 ( 09 ): 1 - 15

SHI Hongwei , SU Chen , NI Zhongyang , et al . Research on hybrid-driven digital twin network system architecture for IP-based carrier network [J ] . Telecommunications Science , 2025 , 41 ( 09 ): 1 - 15

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Off-grid hybrid-field channel estimation algorithm for extremely large-scale MIMO systems

GhostMamba-SAN: an efficient DDoS attack detection model

Three revolutions of communication networks and key technologies for AI-driven revolution

Research on intelligent integrated collaborative scheduling of computing network brain and edge computing

Interference analysis and research on 5G private networks and V2X direct communication

Related Author

No data

Related Institution

No data

AI问答

Postal code：100079
Tel：（010）53879206 Email：tmw@bjxintong.com.cn
Technical support is provided by Beijing Founder electronics co., LTD 京ICP备09082226号-64 京公网安备11010602201714号
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰