Large language model-based optical network log analysis using LLaMA2 with instruction tuning
Journal of Optical Communications and Networking · 01.11.2024 · 16 (11) · 1116
DOI: 10.1364/jocn.527874 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Optical Communications and Networking, online erschienen am 22.10.2024. Verfasst von Yue Pang und 8 weiteren Autor:innen. Die Arbeit wurde bisher 36-mal zitiert (Crossref) und nennt 48 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Beijing Nova Program, BUPT Excellent Ph.D. Students Foundation.
Abstract (Originalsprache)
The optical network encompasses numerous devices and links, generating a significant volume of logs. Analyzing these logs is significant for network optimization, failure diagnosis, and health monitoring. However, the large-scale and diverse formats of optical network logs present several challenges, including the high cost and difficulty of manual processing, insufficient semantic understanding in existing analysis methods, and the strict requirements for data security and privacy. Generative artificial intelligence (GAI) with powerful language understanding and generation capabilities has the potential to address these challenges. Large language models (LLMs) as a concrete realization of GAI are well-suited for analyzing DCI logs, replacing human experts and enhancing accuracy. Additionally, LLMs enable intelligent interactions with network administrators, automating tasks and improving operational efficiency. Moreover, fine-tuning with open-source LLMs protects data privacy and enhances log analysis accuracy. Therefore, we introduce LLMs and propose a log analysis method with instruction tuning using LLaMA2 for log parsing, anomaly detection and classification, anomaly analysis, and report generation. Real log data extracted from the field-deployed network was used to design and construct instruction tuning datasets. We utilized the dataset for instruction tuning and demonstrated and evaluated the effectiveness of the proposed scheme. The results indicate that this scheme improves the performance of log analysis tasks, especially a 14% improvement in exact match rate for log parsing, a 13% improvement in F1-score for anomaly detection and classification, and a 23% improvement in usability for anomaly analysis, compared with the best baselines.
Förderung
- National Natural Science Foundation of China
- Beijing Nova Program
- BUPT Excellent Ph.D. Students Foundation
Zitieren
APA
Pang, Y., Zhang, M., Liu, Y., Li, X., Wang, Y., Huan, Y., Liu, Z., Li, J., & Wang, D. (2024). Large language model-based optical network log analysis using LLaMA2 with instruction tuning. Journal of Optical Communications and Networking, 16(11), 1116. https://doi.org/10.1364/jocn.527874
Vancouver
Pang Y, Zhang M, Liu Y, Li X, Wang Y, Huan Y, et al. Large language model-based optical network log analysis using LLaMA2 with instruction tuning. Journal of Optical Communications and Networking. 2024;16(11):1116. doi:10.1364/jocn.527874
BibTeX
@article{Pang2024,
author = {Pang, Yue and Zhang, Min and Liu, Yanli and Li, Xiangbin and Wang, Yidi and Huan, Yahang and Liu, Zhuo and Li, Jin and Wang, Danshi},
title = {Large language model-based optical network log analysis using LLaMA2 with instruction tuning},
journal = {Journal of Optical Communications and Networking},
year = {2024},
volume = {16},
number = {11},
pages = {1116},
doi = {10.1364/jocn.527874}
}
EUVIMED