APEX：一個用於無線邊緣運作之預測與異常檢測的網路原生時間序列基礎模型

摘要

通用時間序列基礎模型在無線網路遙測數據上的遷移效果不佳，此類數據具有突發性、零膨脹及跨協定層耦合等特性。本文提出APEX－一個網路原生、僅解碼器架構的Transformer模型，用於預測企業級AP遙測數據，並以DHCP效能衰退作為代表性網路任務進行評估。APEX透過來自約4,500個生產環境無線網路（約10萬條AP時間序列，每AP含34項指標）的10通道多變量遙測數據進行預訓練，並提供APEX-Large（2.69億參數，雲端部署）與APEX-Edge（1050萬參數，邊緣部署）兩種版本。在192步（4天）的DHCP效能衰退基準測試中，APEX-Large的MAE較最強基礎模型基線（Toto）降低18%，較SARIMA降低38%，異常檢測F1值達0.93；而APEX-Edge則可在AP級邊緣硬體上實現次秒級、隱私保護的推論。結果表明，網路原生的預訓練方式可作為主動式無線網路運維的實用基礎。

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.