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

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.

Distortions Characterization for Dynamic Carrier Allocation in Ultra High-Throughput Satellites

A novel analytical formula for the characterization of linear and nonlinear distortions in future ultra high-throughput communication payloads is proposed in this work. In this context, the carrier-to-interference ratio related to single-carrier and multicarrier signals is derived. Through the analysis of its behavior valuable insights are created, especially regarding the interaction between linear and nonlinear intersymbol interference. Furthermore, the principle of dynamic carrier allocation optimization is highlighted in a realistic scenario. Within the presented framework, it is proven that a significant gain can be achieved even with a limited number of carriers. Finally, a complexity and accuracy analysis emphasizes the practicality of the proposed approach.