Shaping Rewards, Shaping Routes: On Multi-Agent Deep Q-Networks for Routing in Satellite Constellation Networks

TL;DR

This paper explores multi-agent deep Q-networks for satellite network routing, focusing on reward shaping and convergence, proposing a hybrid centralized-decentralized approach to optimize latency and load balancing.

Contribution

It introduces a novel hybrid learning framework combining centralized training with decentralized control for satellite network routing.

Findings

Reward shaping improves training convergence.

Hybrid approach enhances adaptability in dynamic scenarios.

Joint optimization of latency and load balancing achieved.

Abstract

Effective routing in satellite mega-constellations has become crucial to facilitate the handling of increasing traffic loads, more complex network architectures, as well as the integration into 6G networks. To enhance adaptability as well as robustness to unpredictable traffic demands, and to solve dynamic routing environments efficiently, machine learning-based solutions are being considered. For network control problems, such as optimizing packet forwarding decisions according to Quality of Service requirements and maintaining network stability, deep reinforcement learning techniques have demonstrated promising results. For this reason, we investigate the viability of multi-agent deep Q-networks for routing in satellite constellation networks. We focus specifically on reward shaping and quantifying training convergence for joint optimization of latency and load balancing in static and dynamic scenarios. To address identified drawbacks, we propose a novel hybrid solution based on centralized learning and decentralized control.