Deciphering Region-Level Signatures from Latency Measurements in LEO Satellite Internet

2026-06-28

AI Summary

This study addresses the lack of understanding of regional-scale latency mechanisms in low Earth orbit satellite internet, which hinders the identification of region-specific latency signatures under dynamic network conditions. Leveraging round-trip time (RTT) measurements from Starlink’s public LENS dataset, the authors develop a multi-scale hierarchical analysis framework that systematically reveals strong correlations between deployment factors—such as infrastructure availability and terminal-to-access-point distance—and latency variations. They identify minimum RTT as the most discriminative feature for regional signatures. By integrating mutual information analysis, XGBoost-based feature importance evaluation, and multi-scale statistical feature extraction, the approach achieves 83% regional identification accuracy on short-term data; however, performance degrades over longer durations, underscoring the need for adaptive models to enhance temporal generalization capabilities.

Abstract

Low-Earth orbit (LEO) satellite Internet has become an indispensable infrastructure that provide growing coverage for global users. Despite extensive measurement efforts, the principles underlying region-level performance characteristics remain insufficiently understood, limiting the ability to identify region-specific latency signatures under dynamic network conditions. In this paper, we formulate the problem of region-level latency characterization using Starlink round-trip time (RTT) measurements from the public LENS dataset. We then propose a hierarchical analytical framework that transforms raw RTT sequences into multi-scale statistical features for cross-region comparison. Using data from five geographically representative regions, we demonstrate that latency differences are strongly associated with deployment factors, particularly infrastructure availability and Starlink dish-to-Point-of-Presence distance. Mutual information analysis identifies minimum RTT as the most discriminative feature, which is further supported by XGBoost-based feature importance. The proposed model well achieves 83% accuracy on short-term data. However, its performance degrades over longer periods, indicating limited temporal generalization and motivating the need for adaptive models and feature representations for long-term performance in the future.

Problem

• LEO satellite Internet
• region-level latency
• latency signatures
• Starlink RTT
• network performance characterization

Innovation

• LEO satellite Internet
• region-level latency
• multi-scale statistical features
• RTT characterization
• adaptive modeling