Starlink satellite networks gain real-time round-trip time prediction
StarRTT: An End-to-End Real-Time Framework for Blind Zone-Free RTT Prediction in Starlink LEO Satellite Networks
Information TheoryArtificial Intelligence
Summary
Satellites like Starlink move very fast, which causes delays that change a lot when your internet connection switches between satellites. This makes internet speed unpredictable. The authors designed a system called StarRTT that predicts these delays in real time, avoiding times when the system can't tell which satellite is serving you. Their model uses recent observations and predicted satellite positions to make better delay predictions, improving accuracy compared to earlier methods.
What this means in practice
- •For network schedulers: Improve handover decisions in LEO satellite networks by predicting communication delays continuously without blind zones.
- •For internet service providers: Optimize customer experiences on low Earth orbit satellite broadband by reducing fluctuations in network latency through real-time RTT prediction.$Commercial implications: Enables more stable and responsive satellite internet products by anticipating delay variations and dynamically managing connectivity.
Authors
Jaeyong Lee, Seongjin Jeong, Yusang Park, Hyunho Hwang, Sangmin Han, Wonjae Shin
Abstract
Low Earth Orbit (LEO) satellite mega-constellations such as Starlink require frequent handovers due to high orbital velocities, resulting in substantial Round-Trip Time (RTT) fluctuations. Accurate RTT prediction can mitigate these fluctuations, yet it fundamentally relies on continuously updated serving- satellite information. Existing serving-satellite identification methods typically complete identification only at the end of each scheduling cycle, creating an identification blind zone that limits real-time prediction. To overcome this limitation, we develop StarRTT, an end-to-end real-time framework that eliminates the blind zone by integrating per-second serving-satellite identification with RTT prediction. Within this framework, we propose Real-Time Long Short-Term Memory (RT-LSTM), an LSTM-based RTT prediction model designed to capture both non-stationary RTT evolution and time-varying geometric relationships among the serving satellite, user terminal, and gateways. Specifically, a historical LSTM encodes historical RTT observations and real-time serving-satellite and gateway-relative features, while a future LSTM processes Two-Line Element (TLE)-propagated future features of the identified serving satellite up to the next scheduling instant. Under strict real-time back-testing, RT-LSTM achieves a Mean Absolute Error (MAE) of 1.405 ms averaged over all 15 prediction horizons and 15 reference time-slot indices, reducing the error by 4.3 %, 11.6 %, and 22.1 % compared with the existing baseline models, LSTM, StarNet, and Attention-based Spatiotemporal Model (ASTM), respectively. Notably, the reduction over LSTM reaches 12.5 % at the scheduling instant, highlighting the benefit of real-time serving-satellite information when recent RTT observations are limited.