电子学报2025，Vol.53Issue(9)：3078-3088,11.DOI:10.12263/DZXB.20250463
基于大语言模型的SDN网络自动化配置研究
Research on SDN Network Automated Configuration Based on Large Language Models
摘要
Abstract
Traditional networks,which depend on manual configuration,are inefficient and expensive in the face of today's rapidly expanding scales,increasingly complex demands,and the growing need for real-time responsiveness.Large language models(LLM),known for their exceptional ability to understand natural language,show immense promise for au-tomating network configurations.This paper introduces a streamlined approach to automated configuration for software de-fined networking(SDN),leveraging LLM.For the data plane,we present RetroP4,a code generation method that uses re-trieval-augmented generation(RAG)technology,enabling the creation of P4 code tailored to users'intentions.In the con-trol plane,we propose CtrlSynth,a method for automatically generating flow tables by breaking down tasks,aligning the configurations with users'intentions and the P4 code from the data plane.Compared with general-purpose large models,the syntactic correctness of P4 code generated by RetroP4 is improved by 25%,and the semantic correctness is enhanced by 87.5%.CtrlSynth accurately produces flow table information that corresponds to the P4 code,achieving a 100%accuracy rate when dealing with up to 300 traffic-related intentions.关键词
大语言模型(LLM)/网络配置/软件定义网络(SDN)/可编程协议无关报文处理/检索增强生成(RAG)Key words
large language models(LLM)/network configuration/software defined network(SDN)/programming protocol-independent packet processors(P4)/retrieval-augmented generation(RAG)分类
信息技术与安全科学引用本文复制引用
杨兴源,田乐,姚莹,潘璠,胡宇翔..基于大语言模型的SDN网络自动化配置研究[J].电子学报,2025,53(9):3078-3088,11.基金项目
国家重点研发计划(No.2022YFB2901501) （No.2022YFB2901501）
中原科技创新领军人才项目(No.244200510038) （No.244200510038）
河南省重大科技专项项目(No.221100210900-02) National Key Research and Development Program(No.2022YFB2901501) （No.221100210900-02）
Zhongyuan Sci-ence and Technology Innovation Leading Researcher Project(No.244200510038) （No.244200510038）
Major Science and Technology Special Project of Henan Province(No.221100210900-02) （No.221100210900-02）
