# APEX：用于无线边缘运维的网络原生时间序列基础模型

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-06-10 09:23
- AIHOT 分数：61
- AIHOT 链接：https://aihot.virxact.com/items/cmq9sy2cm0ezgslld5yjit16d
- 原文链接：https://arxiv.org/abs/2606.11553

## AI 摘要

APEX 是一个网络原生、仅解码器的 Transformer 模型，专用于企业无线接入点（AP）遥测的预测与异常检测。它在约 4,500 个生产无线网络的 10 通道多元遥测数据上预训练，涵盖约 10 万条 AP 时间序列、每 AP 34 个指标。提供两个版本：APEX-Large（269M 参数，云部署）和 APEX-Edge（10.5M 参数，边缘部署）。在 192 步（4 天）的 DHCP 退化基准上，APEX-Large 比最强基础模型基线 Toto 降低 MAE 18%，比 SARIMA 降低 38%，异常检测 F1 达 0.93；APEX-Edge 可在 AP 级边缘硬件上实现亚秒级、保护隐私的推理。结果表明网络原生预训练是主动无线运维的实用基础。

## 正文

Generic time-series foundation models transfer poorly to wireless network telemetry whose signals are bursty, zero-inflated, and coupled across protocol layers. We present APEX, a network-native, decoder-only transformer for forecasting enterprise AP telemetry, and evaluate it on DHCP degradation as a representative network task. APEX is pre-trained on 10-channel multivariate telemetry from ~4,500 production wireless networks (~100K AP time series, 34 metrics per AP), and is available as APEX-Large (269M, cloud) and APEX-Edge (10.5M, edge). On a 192-step (4-day) DHCP degradation benchmark, APEX-Large reduces MAE by 18% over the strongest foundation-model baseline (Toto) and 38% over SARIMA, with anomaly-detection F1 = 0.93, while APEX-Edge enables sub-second, privacy-preserving inference on AP-class edge hardware. These results suggest network-native pre-training is a practical foundation for proactive wireless operations.