@article{10.1145/3768971,
author = {Liu, Zikun and Reidys, Fan-Xue Gabriella and Tanveer, Sarah and Vasisht, Deepak},
title = {Vivisecting Starlink Throughput: Measurement and Prediction},
year = {2025},
issue_date = {December 2025},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
volume = {3},
number = {CoNEXT4},
url = {https://doi.org/10.1145/3768971},
doi = {10.1145/3768971},
abstract = {Internet connectivity using low earth orbit (LEO) satellites is gaining significant traction, with nearly 3 million users worldwide. While these networks promise to provide universal broadband connectivity, they suffer from large throughput fluctuations over short time scales. We conduct an extensive evaluation of Starlink's throughput across three devices in different countries, with measurement durations ranging from one to six months. We identify various factors that cause throughput variations at varying timescales. Given our analysis, we design StarNet, a new learning-based throughput prediction system. StarNet incorporates satellite network-specific insights and accurately predicts future throughput for end users. We demonstrate that StarNet's accurate predictions can improve the experience of end user applications like video streaming.},
journal = {Proc. ACM Netw.},
month = nov,
articleno = {24},
numpages = {23},
keywords = {machine learning, network measurement, neural networks, satellite network, time series prediction}
}