Saved in:
Bibliographic Details
Main Authors: Xie, Hongjun, Zhang, Chao, Luo, Pengcheng, Zhang, Zenghui, Yang, Genke, Zhang, Xiaojuan, Soong, Boon-Hee
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.09508
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917478222790656
author Xie, Hongjun
Zhang, Chao
Luo, Pengcheng
Zhang, Zenghui
Yang, Genke
Zhang, Xiaojuan
Soong, Boon-Hee
author_facet Xie, Hongjun
Zhang, Chao
Luo, Pengcheng
Zhang, Zenghui
Yang, Genke
Zhang, Xiaojuan
Soong, Boon-Hee
contents As a representative low Earth orbit (LEO) broadband system, Starlink exhibits highly variable access throughput, making short-term forecasting essential for network resource management. Existing forecasting methods mainly optimize symmetric point-prediction metrics such as MAE and RMSE, but they do not explicitly control the asymmetric risk of overestimating future throughput, which can cause over-admission, bandwidth overbooking, and service violations. This paper formulates Starlink throughput prediction as a risk-budgeted safe forecasting problem, where the predictor must satisfy a prescribed overestimation budget while maintaining competitive accuracy. We propose Budget-Guided Coarse-to-Fine Quantile Selection (BG-CFQS), a data-driven framework that trains a family of lower-quantile predictors, locates the quantile boundary satisfying the risk budget, and refines the boundary region to select the most accurate feasible predictor. Experiments on three real-world Starlink throughput datasets show that BG-CFQS satisfies the risk budget on all datasets and achieves the lowest average MAE, mean positive error, and tail positive error among budget-feasible methods. In high-risk and severe-risk low-throughput regimes, BG-CFQS reduces harmful positive errors by 11.0% and 12.6%, respectively. An admission-control evaluation further shows that the proposed safe forecasts reduce dropped sessions, demonstrating that risk-aware forecasting can translate prediction safety into application-level benefits.
format Preprint
id arxiv_https___arxiv_org_abs_2605_09508
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Risk-Aware Safe Throughput Forecasting for Starlink Networks
Xie, Hongjun
Zhang, Chao
Luo, Pengcheng
Zhang, Zenghui
Yang, Genke
Zhang, Xiaojuan
Soong, Boon-Hee
Systems and Control
As a representative low Earth orbit (LEO) broadband system, Starlink exhibits highly variable access throughput, making short-term forecasting essential for network resource management. Existing forecasting methods mainly optimize symmetric point-prediction metrics such as MAE and RMSE, but they do not explicitly control the asymmetric risk of overestimating future throughput, which can cause over-admission, bandwidth overbooking, and service violations. This paper formulates Starlink throughput prediction as a risk-budgeted safe forecasting problem, where the predictor must satisfy a prescribed overestimation budget while maintaining competitive accuracy. We propose Budget-Guided Coarse-to-Fine Quantile Selection (BG-CFQS), a data-driven framework that trains a family of lower-quantile predictors, locates the quantile boundary satisfying the risk budget, and refines the boundary region to select the most accurate feasible predictor. Experiments on three real-world Starlink throughput datasets show that BG-CFQS satisfies the risk budget on all datasets and achieves the lowest average MAE, mean positive error, and tail positive error among budget-feasible methods. In high-risk and severe-risk low-throughput regimes, BG-CFQS reduces harmful positive errors by 11.0% and 12.6%, respectively. An admission-control evaluation further shows that the proposed safe forecasts reduce dropped sessions, demonstrating that risk-aware forecasting can translate prediction safety into application-level benefits.
title Risk-Aware Safe Throughput Forecasting for Starlink Networks
topic Systems and Control
url https://arxiv.org/abs/2605.09508