Decision-aware traffic forecasting for backbone capacity planning. Asymmetric losses and conformal calibration to minimize operator cost rather than RMSE. Evaluated on Abilene, GÉANT, and CESNET-TimeSeries24 with 20-seed paired-bootstrap CIs.
capacity-planning service-level-agreement pytorch lstm network-management quantile-regression time-series-forecasting conformal-prediction backbone-networks traffic-forecasting asymmetric-loss network-traffic-prediction decision-focused-learning cesnet-timeseries24 abilene-dataset geant-dataset
-
Updated
May 31, 2026 - Python