Reinforcement Learning for Opportunistic Routing in Software-Defined LEO–Terrestrial Systems

2026-01-20

IEEE Wireless Communications Letters

AI Summary

This work addresses the high latency and low reliability in low Earth orbit (LEO) satellite networks caused by highly dynamic inter-satellite links and intermittent visibility of ground gateways. To tackle these challenges, the authors propose an opportunistic routing scheme orchestrated by a geostationary Earth orbit (GEO)-based software-defined networking (SDN) controller. The approach uniquely integrates residual reinforcement learning into a constrained stochastic optimization framework, enabling dynamic decisions to forward packets to any currently available gateway—thereby overcoming the limitations of conventional routing strategies that rely on fixed destinations. Extensive simulations across multi-day orbital scenarios demonstrate that the proposed method significantly outperforms classical scheduling policies such as backpressure algorithms, achieving substantial reductions in end-to-end delay and improved queue-length management.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Search and Optimization: Learning to Search
• Reasoning under Uncertainty: Stochastic Optimization

Application Category

• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments

Abstract

The proliferation of large-scale low Earth orbit (LEO) satellite constellations is driving the need for intelligent routing strategies that can effectively deliver data to terrestrial networks under rapidly time-varying topologies and intermittent gateway visibility. Leveraging the global control capabilities of a geostationary (GEO)-resident software-defined networking (SDN) controller, we introduce opportunistic routing, which aims to minimize delivery delay by forwarding packets to any currently available ground gateways rather than fixed destinations. This makes it a promising approach for achieving low-latency and robust data delivery in highly dynamic LEO networks. Specifically, we formulate a constrained stochastic optimization problem and employ a residual reinforcement learning framework to optimize opportunistic routing for reducing transmission delay. Simulation results over multiple days of orbital data demonstrate that our method achieves significant improvements in queue length reduction compared to classical backpressure and other well-known queueing algorithms.

Problem

• opportunistic routing
• LEO-terrestrial systems
• time-varying topology
• intermittent gateway visibility
• low-latency data delivery

Innovation

• opportunistic routing
• reinforcement learning
• software-defined networking
• LEO-terrestrial systems
• stochastic optimization