Author

Jaesung Yoo

Publication Date

Fall 2024

Degree Type

Master's Project

Degree Name

Master of Science in Computer Science (MSCS)

Department

Computer Science

First Advisor

Navrati Saxena

Second Advisor

Genya Ishigaki

Third Advisor

Yash Bhamare

Keywords

Satellite Networks, Routing, Long Short Term Memory (LSTM), Congestion Control, Load Balancing, Multi-Path Routing

Abstract

Satellite networks play a crucial role in global connectivity today and making efficient routing algorithms is crucial for optimal performance. While existing routing algorithms have made significant progress using machine learning techniques, they often overlook network congestion and multiple path availability. This report introduces an enhanced routing framework that builds upon LSTM-based predictive routing using dynamic congestion modeling and multi-path selection. Our approach introduces a busy state metric that tracks satellite memory utilization, allowing for adaptive path selection based on both distance and current network load. Through simulations using a constellation of 20 satellites, our enhanced algorithm demonstrates significant improvements over baseline LSTM-based routing. Our goal was to reduce the end-to-end delay under high network load conditions and improve network throughput through better load distribution. The results show that considering both congestion and multiple path availability provides more resilient and efficient routing in satellite networks, particularly in scenarios with high traffic volumes.

Available for download on Wednesday, December 31, 2025

Share

COinS