APEX：一种面向无线边缘运营预测与异常检测的网络原生时序基础模型

摘要

通用时间序列基础模型在无线网络遥测中迁移效果不佳，因为此类信号具有突发性、零膨胀性，且跨协议层存在耦合。我们提出APEX——一个面向网络的、仅解码器变换器，用于预测企业级接入点（AP）遥测数据，并以DHCP降级作为代表性网络任务进行评测。APEX在约4,500个生产无线网络的10通道多变量遥测数据（约10万条AP时间序列，每个AP包含34个指标）上进行预训练，提供APEX-Large（269M参数，云端）和APEX-Edge（10.5M参数，边缘端）两种版本。在192步（4天）的DHCP降级基准测试中，APEX-Large的平均绝对误差（MAE）比最强基础模型基线（Toto）降低18%，比SARIMA降低38%，异常检测F1得分达0.93；而APEX-Edge可在AP级边缘硬件上实现亚秒级、保护隐私的推理。这些结果表明，网络原生预训练是主动无线网络运维的实用基础。

English

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.