Backend
Hierarchical Traffic Engineering for Scalable Software-Defined Satellite Networks
arXiv cs.SY0 views
arXiv:2611.24777v1 Announce Type: new Abstract: Future satellite systems are shifting toward regenerative payloads that interconnect many modem banks into a reconfigurable on-board network. However, conventional constellation-level routing overlooks intra-payload congestion and load imbalance, which can limit the traffic each satellite can accommodate. This paper proposes a hierarchical software-defined networking (SDN)framework for traffic engineering (TE) across both the constellation and payload levels. The system is represented by a two-level graph, where each satellite node in the constellation graph is expanded into an internal network of interconnected modem banks. The proposed hierarchical payload-aware allocation (HPAA) algorithm coordinates the two levels through the exchange of assigned traffic demand and advertised capacity budgets. Simulation results show that, under heavy load, HPAA delivers about 9 times the throughput of shortest-path routing, with 17% lower end-to-end delay and no packet loss. These findings highlight that hierarchical control accounting for the on-board network constraints of regenerative payloads is a key lever to improve the performance of satellite constellations.
Source:https://arxiv.org/abs/2611.24777PreviousCross-Vehicle Transferability of Lateral Velocity Estimation on Production Vehicles through Input Selection and Data AugmentationNextAMISS: An Integrity Framework for Magnetic Navigation
Related posts

The Transaction Only Covers Your Database. The Provider Key Is What Saves You
0dev.to Database

Go 1.28 will flag the error your rows.Next() loop forgets
0dev.to Database
How zkDatabase Works: From Data Sampling to Verifiable Query Results
0dev.to Database
LogTreeDB: Building a Crash-Safe, Zero-Dependency Document Database from Scratch in C++17
0dev.to Database
CratesBump: A Version-Bump Dataset for the Rust Ecosystem
0arXiv cs.SE
Integrating AI Coding Agents Into Scientific Research
0arXiv cs.SE