Risk-Aware Safe Throughput Forecasting for Starlink Networks

TL;DR

This paper introduces a risk-aware forecasting method for Starlink throughput that explicitly controls overestimation risk, improving accuracy and reducing service violations in variable LEO networks.

Contribution

It formulates throughput prediction as a risk-budgeted problem and proposes BG-CFQS, a novel framework for safe, accurate forecasting under risk constraints.

Findings

BG-CFQS satisfies the overestimation risk budget across datasets.

It achieves the lowest MAE and positive errors among risk-feasible methods.

Reduces harmful positive errors by over 11% in high-risk regimes.

Abstract

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.