PreConfig: A Pretrained Model for Automating Network Configuration (2403.09369v1)
Abstract: Manual network configuration automation (NCA) tools face significant challenges in versatility and flexibility due to their reliance on extensive domain expertise and manual design, limiting their adaptability to diverse scenarios and complex application needs. This paper introduces PreConfig, an innovative NCA tool that leverages a pretrained LLM for automating network configuration tasks. PreConfig is designed to address the complexity and variety of NCA tasks by framing them as text-to-text transformation problems, thus unifying the tasks of configuration generation, translation, and analysis under a single, versatile model. Our approach overcomes existing tools' limitations by utilizing advances in natural language processing to automatically comprehend and generate network configurations without extensive manual re-engineering. We confront the challenges of integrating domain-specific knowledge into pretrained models and the scarcity of supervision data in the network configuration field. Our solution involves constructing a specialized corpus and further pretraining on network configuration data, coupled with a novel data mining technique for generating task supervision data. The proposed model demonstrates robustness in configuration generation, translation, and analysis, outperforming conventional tools in handling complex networking environments. The experimental results validate the effectiveness of PreConfig, establishing a new direction for automating network configuration tasks with pretrained LLMs.
- Aed: Incrementally synthesizing policy-compliant and manageable configurations. In Proceedings of the 16th International Conference on emerging Networking EXperiments and Technologies. 482–495.
- Unified pre-training for program understanding and generation. arXiv preprint arXiv:2103.06333 (2021).
- A general approach to network configuration verification. In Proceedings of the Conference of the ACM Special Interest Group on Data Communication.
- A general approach to network configuration verification. In Proceedings of the Conference of the ACM Special Interest Group on Data Communication. 155–168.
- Don’t mind the gap: Bridging network-wide objectives and device-level configurations. In Proceedings of the 2016 ACM SIGCOMM Conference.
- Config2Spec: Mining network specifications from network configurations. In 17th USENIX Symposium on Networked Systems Design and Implementation (NSDI 20). 969–984.
- Longbing Cao and Chengqi Zhang. 2008. Domain driven data mining. In Data Mining and Knowledge Discovery Technologies. IGI Global, 196–223.
- Software-defined network assimilation: bridging the last mile towards centralized network configuration management with NAssim. In Proceedings of the ACM SIGCOMM 2022 Conference. 281–297.
- NetComplete: Practical Network-Wide configuration synthesis with autocompletion. In 15th USENIX Symposium on Networked Systems Design and Implementation (NSDI 18).
- Codebert: A pre-trained model for programming and natural languages. arXiv preprint arXiv:2002.08155 (2020).
- Variational pretraining for semi-supervised text classification. arXiv preprint arXiv:1906.02242 (2019).
- Don’t stop pretraining: Adapt language models to domains and tasks. arXiv preprint arXiv:2004.10964 (2020).
- Metagpt: Meta programming for multi-agent collaborative framework. arXiv preprint arXiv:2308.00352 (2023).
- Huawei. 2017. eDesk Configuration Translation Tool. https://info.support.huawei.com/network/ptmngsys/Web/OnlineCourse_WLAN/en/mooc/tools/index_en_3.html. (2017).
- AI-enabled next-generation communication networks: Intelligent agent and AI router. IEEE Wireless Communications 27, 6 (2020), 129–133.
- Juniper. 2009. IOS-to-JUNOS Conversion Tool. [Online]. (2009). https://supportportal.juniper.net/s/article/Archive-IOS-to-JUNOS-I2J-Conversion-Tool-Tool-Fact-Sheet?language=en_US.
- Aris Leivadeas and Matthias Falkner. 2022. A survey on intent based networking. IEEE Communications Surveys & Tutorials (2022).
- Codexglue: A machine learning benchmark dataset for code understanding and generation. arXiv preprint arXiv:2102.04664 (2021).
- Knowledge-defined networking. ACM SIGCOMM Computer Communication Review 47, 3 (2017), 2–10.
- What do LLMs need to Synthesize Correct Router Configurations?. In Proceedings of the 22nd ACM Workshop on Hot Topics in Networks. 189–195.
- Communicative agents for software development. arXiv preprint arXiv:2307.07924 (2023).
- Exploring the limits of transfer learning with a unified text-to-text transformer. The Journal of Machine Learning Research 21, 1 (2020), 5485–5551.
- Practical Intent-driven Routing Configuration Synthesis. In 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23).
- Campion: debugging router configuration differences. In Proceedings of the 2021 ACM SIGCOMM 2021 Conference. 748–761.
- Biglog: Unsupervised large-scale pre-training for a unified log representation. In 2023 IEEE/ACM 31st International Symposium on Quality of Service (IWQoS). IEEE, 1–11.
- Safely and automatically updating in-network ACL configurations with intent language. In Proceedings of the ACM Special Interest Group on Data Communication. 214–226.
- Codet5: Identifier-aware unified pre-trained encoder-decoder models for code understanding and generation. arXiv preprint arXiv:2109.00859 (2021).
- Magicoder: Source Code Is All You Need. arXiv preprint arXiv:2312.02120 (2023).
- A prompt pattern catalog to enhance prompt engineering with chatgpt. arXiv preprint arXiv:2302.11382 (2023).
- Wizardlm: Empowering large language models to follow complex instructions. arXiv preprint arXiv:2304.12244 (2023).
- Test Coverage for Network Configurations. In 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23). 1717–1732.
- Accuracy, scalability, coverage: A practical configuration verifier on a global WAN. In Proceedings of the Annual conference of the ACM Special Interest Group on Data Communication on the applications, technologies, architectures, and protocols for computer communication. 599–614.
- Towards better chain-of-thought prompting strategies: A survey. arXiv preprint arXiv:2310.04959 (2023).
Sponsor
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.