A Centralized–Distributed Joint Routing Algorithm for LEO Satellite Constellations Based on Multi-Agent Reinforcement Learning

Designing routing algorithms for Low Earth Orbit (LEO) satellite networks poses a significant challenge due to their high dynamics, frequent link failures, and unevenly distributed traffic. Existing studies predominantly focus on shortest-path solutions, which compute minimum-delay paths using globa...

Full description

Saved in:
Bibliographic Details
Main Authors: Licheng Xia, Baojun Lin, Shuai Zhao, Yanchun Zhao
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/9/4664
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850155756582600704
author Licheng Xia
Baojun Lin
Shuai Zhao
Yanchun Zhao
author_facet Licheng Xia
Baojun Lin
Shuai Zhao
Yanchun Zhao
author_sort Licheng Xia
collection DOAJ
description Designing routing algorithms for Low Earth Orbit (LEO) satellite networks poses a significant challenge due to their high dynamics, frequent link failures, and unevenly distributed traffic. Existing studies predominantly focus on shortest-path solutions, which compute minimum-delay paths using global topology information but often neglect the impact of traffic load on routing performance and struggle to adapt to rapid link-state variations. In this regard, we propose a Multi-Agent Reinforcement Learning-Based Joint Routing (MARL-JR) algorithm, which integrates centralized and distributed routing algorithms. MARL-JR combines the accuracy of centralized methods with the responsiveness of distributed approaches in handling dynamic disruptions. In MARL-JR, ground stations initialize Q-tables and upload them to satellites, reducing onboard computational overhead while enhancing routing performance. Compared to traditional centralized algorithms, MARL-JR achieves faster link-state awareness and adaptation; compared to distributed algorithms, it delivers superior initial performance due to optimized pre-training. Experimental results demonstrate that MARL-JR outperforms both Q-Routing (QR) and DR-BM algorithms in average delay, packet loss rate, and load-balancing efficiency.
format Article
id doaj-art-1f731b258a194c07b311b0cd9433f643
institution OA Journals
issn 2076-3417
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-1f731b258a194c07b311b0cd9433f6432025-08-20T02:24:47ZengMDPI AGApplied Sciences2076-34172025-04-01159466410.3390/app15094664A Centralized–Distributed Joint Routing Algorithm for LEO Satellite Constellations Based on Multi-Agent Reinforcement LearningLicheng Xia0Baojun Lin1Shuai Zhao2Yanchun Zhao3School of Information Science and Technology, ShanghaiTech University, Shanghai 201210, ChinaInnovation Academy for Microsatellites of CAS, Shanghai 201304, ChinaInnovation Academy for Microsatellites of CAS, Shanghai 201304, ChinaInnovation Academy for Microsatellites of CAS, Shanghai 201304, ChinaDesigning routing algorithms for Low Earth Orbit (LEO) satellite networks poses a significant challenge due to their high dynamics, frequent link failures, and unevenly distributed traffic. Existing studies predominantly focus on shortest-path solutions, which compute minimum-delay paths using global topology information but often neglect the impact of traffic load on routing performance and struggle to adapt to rapid link-state variations. In this regard, we propose a Multi-Agent Reinforcement Learning-Based Joint Routing (MARL-JR) algorithm, which integrates centralized and distributed routing algorithms. MARL-JR combines the accuracy of centralized methods with the responsiveness of distributed approaches in handling dynamic disruptions. In MARL-JR, ground stations initialize Q-tables and upload them to satellites, reducing onboard computational overhead while enhancing routing performance. Compared to traditional centralized algorithms, MARL-JR achieves faster link-state awareness and adaptation; compared to distributed algorithms, it delivers superior initial performance due to optimized pre-training. Experimental results demonstrate that MARL-JR outperforms both Q-Routing (QR) and DR-BM algorithms in average delay, packet loss rate, and load-balancing efficiency.https://www.mdpi.com/2076-3417/15/9/4664satellite networklow earth orbitreinforcement learningdistributed routing
spellingShingle Licheng Xia
Baojun Lin
Shuai Zhao
Yanchun Zhao
A Centralized–Distributed Joint Routing Algorithm for LEO Satellite Constellations Based on Multi-Agent Reinforcement Learning
Applied Sciences
satellite network
low earth orbit
reinforcement learning
distributed routing
title A Centralized–Distributed Joint Routing Algorithm for LEO Satellite Constellations Based on Multi-Agent Reinforcement Learning
title_full A Centralized–Distributed Joint Routing Algorithm for LEO Satellite Constellations Based on Multi-Agent Reinforcement Learning
title_fullStr A Centralized–Distributed Joint Routing Algorithm for LEO Satellite Constellations Based on Multi-Agent Reinforcement Learning
title_full_unstemmed A Centralized–Distributed Joint Routing Algorithm for LEO Satellite Constellations Based on Multi-Agent Reinforcement Learning
title_short A Centralized–Distributed Joint Routing Algorithm for LEO Satellite Constellations Based on Multi-Agent Reinforcement Learning
title_sort centralized distributed joint routing algorithm for leo satellite constellations based on multi agent reinforcement learning
topic satellite network
low earth orbit
reinforcement learning
distributed routing
url https://www.mdpi.com/2076-3417/15/9/4664
work_keys_str_mv AT lichengxia acentralizeddistributedjointroutingalgorithmforleosatelliteconstellationsbasedonmultiagentreinforcementlearning
AT baojunlin acentralizeddistributedjointroutingalgorithmforleosatelliteconstellationsbasedonmultiagentreinforcementlearning
AT shuaizhao acentralizeddistributedjointroutingalgorithmforleosatelliteconstellationsbasedonmultiagentreinforcementlearning
AT yanchunzhao acentralizeddistributedjointroutingalgorithmforleosatelliteconstellationsbasedonmultiagentreinforcementlearning
AT lichengxia centralizeddistributedjointroutingalgorithmforleosatelliteconstellationsbasedonmultiagentreinforcementlearning
AT baojunlin centralizeddistributedjointroutingalgorithmforleosatelliteconstellationsbasedonmultiagentreinforcementlearning
AT shuaizhao centralizeddistributedjointroutingalgorithmforleosatelliteconstellationsbasedonmultiagentreinforcementlearning
AT yanchunzhao centralizeddistributedjointroutingalgorithmforleosatelliteconstellationsbasedonmultiagentreinforcementlearning