复现研究：LEO 卫星链路风险可控吞吐量预测何时才能真正控住风险？
When Does Risk-Controlled Throughput Forecasting Actually Control Risk? A Reproduction Study on LEO Satellite Link
AI 导读
一项复现研究在三条 Starlink 轨迹及一个独立第四数据集上检验了 BG-CFQS 风险预算吞吐量预测方法。随机划分下能复现全部已发表结果（3/3 数据集通过风险检验），但连续时间划分下仅在 1/3 数据集成立；且该方法无法服务低于 0.15 的风险预算，最紧预算下超限 1.4x 至 3.7x。
正文 · 原文
Abstract:Risk-budgeted throughput forecasting converts a point forecast of LEO satellite capacity into a conservative bound whose overestimation rate is held at a user-specified budget, so that admission control can act on it safely. We reproduce the state of the art, BG-CFQS, on the three Starlink traces its authors used and on an independent fourth dataset, and report four findings. First, its risk guarantee is reproducible but conditional on the calibration split: under a random split we recover every published quantity, including risk-pass on 3 of 3 datasets, but under a contiguous temporal split, which is what a deployed terminal faces, it holds on 1 of 3. Second, independent of any split, the method cannot serve a risk budget below 0.15, the low end of its candidate quantile set. On all four datasets the achieved rate is identical at budgets of 0.05, 0.10 and 0.15, overshooting by 1.4x to 3.7x at the tightest. Third, static conformal calibration cannot improve a ranking, only shift an operating point; we confirm this exactly on latency spike detection, where online calibration improves AUPRC by up to 51%. Fourth, group-conditional online recalibration splits into two mechanisms. The online part replicates: it tracks the budget within 1% from 0.05 to 0.35, where static calibration is 16 to 21% off. The group-conditional part does not: on three of four datasets, conditioning on any available covariate, including measured serving-satellite geometry, is worse than not conditioning, and our attempt to predict which datasets benefit failed. What is new here is empirical, not algorithmic: we claim the findings, not the methods.
| Comments: | Code: this https URL |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Networking and Internet Architecture (cs.NI) |
| Cite as: | arXiv:2611.06307 [cs.LG] |
| (or arXiv:2611.06307v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2611.06307 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Mayan Sharma [view email]
[v1]
Wed, 4 Nov 2026 10:42:15 UTC (79 KB)
来源：arXiv cs.AI · arxiv.org