Joint Optimization of Handoff and Video Rate in LEO Satellite Networks

TL;DR

This work tackles video streaming in LEO satellite networks, where frequent handoffs and multi-user throughput contention degrade QoE. It introduces a joint optimization framework that simultaneously selects satellites and adapts video bitrate using model predictive control (MPC) and reinforcement learning (RL), including centralized training with distributed inference for multi-user settings. Through trace-driven simulations and testbed experiments on simulated Starlink trajectories, NOAA-derived traces, and real Starlink throughput, the authors show that joint satellite selection and bitrate adaptation improves QoE by up to 68% compared to separate strategies, with RL-based methods delivering robust performance under obstructions and multi-user contention. The results demonstrate the practical viability of video-aware mobility management in LEO networks and offer scalable policies for real deployments.

Abstract

Low Earth Orbit (LEO) satellite communication presents a promising solution for delivering Internet access to users in remote regions. Given that video content is expected to dominate network traffic in LEO satellite systems, this study presents a new video-aware mobility management framework specifically designed for such networks. By combining simulation models with real-world datasets, we highlight the critical role of handoff strategies and throughput prediction algorithms in both single-user and multi-user video streaming scenarios. Building on these insights, we introduce a suite of innovative algorithms that jointly determine satellite selection and video bitrate to enhance users' quality of experience (QoE). Initially, we design model predictive control (MPC) and reinforcement learning (RL) based methods for individual users, then extend the approach to manage multiple users sharing a satellite. Notably, we incorporate centralized training with distributed inference in our RL design to develop distributed policies informed by a global view. The effectiveness of our approach is validated through trace-driven simulations and testbed experiments.

Figures (12)

• Figure 1: The relationship between the SNR, altitude, and azimuth angles measured from NOAA satellites in (a). (b) depicts a cumulative distribution function (CDF) plot of the SNR prediction based on the ML model.
• Figure 2: The video QoE in the Starlink network at two locations: one is free from obstructions and the other has several obstructions around it. The figures show the visibility map generated by the Starlink APP. The red portion is the detected obstruction.
• Figure 3: Throughput measurement for Starlink network at different settings: (i) A single dish, (ii) Two dishes facing the same direction, and (iii) Two dishes facing different directions.
• Figure 4: The PPO-based RL algorithm generates joint optimization policies.
• Figure 5: The PPO-based RL algorithm generates joint optimization policies with centralized training and distributed inference.