arXiv cs.AI· Geon Kim, Dara Ron, Sukhdeep Singh, Suyog Moogi, Pranshav Gajjar, V V N K Someswara Rao Koduri, Een Kee Hong, Vijay K. Shah·· 6 天前AI 评分24
TelcoAgent：可扩展的 5G 多 KPM 预测框架，具备 3GPP 可解释性
TelcoAgent: A Scalable 5G Multi-KPM Forecasting With 3GPP-Grounded Explainability
AI 导读
TelcoAgent 是一个基于基础模型的框架，无需站点特定训练即可对多个 KPM 进行准确、可扩展且可解释的预测。它由三部分组成：从 3GPP 规范文档自动构建知识图谱的三智能体流水线、基于时间序列基础模型（TSFM）的零样本预测流水线，以及提供领域诊断的推理与解释流水线。在美国某运营商 3 个月城市级 5G 数据集上，该框架对 200 个小区每小区的全部 7 个 KPM 均实现高预测精度。
正文 · 原文
Abstract:Key Performance Measurement (KPM) forecasting is essential for proactive network management of 5G and next-generation telecom networks. However, existing machine learning (ML) approaches face significant limitations in scalability and explainability, restricting their effectiveness in real-world deployments. We propose TelcoAgent, a foundation model-based framework that enables accurate, scalable, and explainable forecasting of multiple KPMs across diverse network cells without the need for site-specific training. Specifically, the framework comprises three key components: (i) an automated three-agent pipeline that constructs a 3rd Generation Partnership Project (3GPP) knowledge graph directly from specification documents, (ii) a scalable, time-series foundation model (TSFM)-based prediction pipeline to deliver accurate, zero-shot forecasting, and finally (iii) a reasoning and explanation pipeline that provides actionable, domain-grounded diagnostics. Evaluated using a 3-month, real-world, city-scale 5G KPM dataset from a U.S.-based network operator, TelcoAgent demonstrates high forecasting accuracy for all 7 considered KPMs per cell across 200 cells, while delivering explainable insights and actionable instructions to address network degradations.
| Comments: | 6 pages, 6 figures. Accepted to IEEE GLOBECOM 2026 |
| Subjects: | Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2606.19821 [cs.AI] |
| (or arXiv:2606.19821v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2606.19821 arXiv-issued DOI via DataCite |
Submission history
From: Geon Kim [view email]
[v1]
Thu, 18 Jun 2026 05:55:29 UTC (497 KB)
[v2]
Fri, 9 Oct 2026 14:55:19 UTC (424 KB)
来源：arXiv cs.AI · arxiv.org