Deep Reinforcement Learning-Based Routing Method for Low Earth Orbit Mega-Constellation Satellite Networks with Service Function Constraints

Low-orbit satellite communication networks have gradually become the research focus of fifth-generation (5G) beyond and sixth generation (6G) networks due to their advantages of wide coverage, large communication capacity, and low terrain influence. However, the low earth orbit mega satellite networ...

Full description

Saved in:
Bibliographic Details
Main Authors: Yan Chen, Huan Cao, Longhe Wang, Daojin Chen, Zifan Liu, Yiqing Zhou, Jinglin Shi
Format: Article
Language:English
Published: MDPI AG 2025-02-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/4/1232
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849719643510407168
author Yan Chen
Huan Cao
Longhe Wang
Daojin Chen
Zifan Liu
Yiqing Zhou
Jinglin Shi
author_facet Yan Chen
Huan Cao
Longhe Wang
Daojin Chen
Zifan Liu
Yiqing Zhou
Jinglin Shi
author_sort Yan Chen
collection DOAJ
description Low-orbit satellite communication networks have gradually become the research focus of fifth-generation (5G) beyond and sixth generation (6G) networks due to their advantages of wide coverage, large communication capacity, and low terrain influence. However, the low earth orbit mega satellite network (LEO-MSN) also has difficulty in constructing stable traffic transmission paths, network load imbalance and congestion due to the large scale of network nodes, a highly complex topology, and uneven distribution of traffic flow in time and space. In the service-based architecture proposed by 3GPP, the introduction of service function chain (SFC) constraints exacerbates these challenges. Therefore, in this paper, we propose GDRL-SFCR, an end-to-end routing decision method based on graph neural network (GNN) and deep reinforcement learning (DRL) which jointly optimize the end-to-end transmission delay and network load balancing under SFC constraints. Specifically, this method constructs the system model based on the latest NTN low-orbit satellite network end-to-end transmission architecture, taking into account the SFC constraints, transmission delays, and network node loads in the end-to-end traffic transmission, uses a GNN to extract node attributes and dynamic topology features, and uses the DRL method to design specific reward functions to train the model to learn routing policies that satisfy the SFC constraints. The simulation results demonstrate that, compared with graph theory-based methods and reinforcement learning-based methods, GDRL-SFCR can reduce the end-to-end traffic transmission delay by more than 11.3%, reduce the average network load by more than 14.1%, and increase the traffic access success rate and network capacity by more than 19.1% and two times, respectively.
format Article
id doaj-art-c6a7f6c5664f44a287e83cb6b78f3148
institution DOAJ
issn 1424-8220
language English
publishDate 2025-02-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-c6a7f6c5664f44a287e83cb6b78f31482025-08-20T03:12:07ZengMDPI AGSensors1424-82202025-02-01254123210.3390/s25041232Deep Reinforcement Learning-Based Routing Method for Low Earth Orbit Mega-Constellation Satellite Networks with Service Function ConstraintsYan Chen0Huan Cao1Longhe Wang2Daojin Chen3Zifan Liu4Yiqing Zhou5Jinglin Shi6University of Chinese Academy of Sciences, Beijing 100049, ChinaState Key Laboratory of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, ChinaState Key Laboratory of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, ChinaState Key Laboratory of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, ChinaState Key Laboratory of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, ChinaUniversity of Chinese Academy of Sciences, Beijing 100049, ChinaUniversity of Chinese Academy of Sciences, Beijing 100049, ChinaLow-orbit satellite communication networks have gradually become the research focus of fifth-generation (5G) beyond and sixth generation (6G) networks due to their advantages of wide coverage, large communication capacity, and low terrain influence. However, the low earth orbit mega satellite network (LEO-MSN) also has difficulty in constructing stable traffic transmission paths, network load imbalance and congestion due to the large scale of network nodes, a highly complex topology, and uneven distribution of traffic flow in time and space. In the service-based architecture proposed by 3GPP, the introduction of service function chain (SFC) constraints exacerbates these challenges. Therefore, in this paper, we propose GDRL-SFCR, an end-to-end routing decision method based on graph neural network (GNN) and deep reinforcement learning (DRL) which jointly optimize the end-to-end transmission delay and network load balancing under SFC constraints. Specifically, this method constructs the system model based on the latest NTN low-orbit satellite network end-to-end transmission architecture, taking into account the SFC constraints, transmission delays, and network node loads in the end-to-end traffic transmission, uses a GNN to extract node attributes and dynamic topology features, and uses the DRL method to design specific reward functions to train the model to learn routing policies that satisfy the SFC constraints. The simulation results demonstrate that, compared with graph theory-based methods and reinforcement learning-based methods, GDRL-SFCR can reduce the end-to-end traffic transmission delay by more than 11.3%, reduce the average network load by more than 14.1%, and increase the traffic access success rate and network capacity by more than 19.1% and two times, respectively.https://www.mdpi.com/1424-8220/25/4/1232LEO satellite networkroutingservice function constraintsgraph convolution networkdeep reinforcement learning
spellingShingle Yan Chen
Huan Cao
Longhe Wang
Daojin Chen
Zifan Liu
Yiqing Zhou
Jinglin Shi
Deep Reinforcement Learning-Based Routing Method for Low Earth Orbit Mega-Constellation Satellite Networks with Service Function Constraints
Sensors
LEO satellite network
routing
service function constraints
graph convolution network
deep reinforcement learning
title Deep Reinforcement Learning-Based Routing Method for Low Earth Orbit Mega-Constellation Satellite Networks with Service Function Constraints
title_full Deep Reinforcement Learning-Based Routing Method for Low Earth Orbit Mega-Constellation Satellite Networks with Service Function Constraints
title_fullStr Deep Reinforcement Learning-Based Routing Method for Low Earth Orbit Mega-Constellation Satellite Networks with Service Function Constraints
title_full_unstemmed Deep Reinforcement Learning-Based Routing Method for Low Earth Orbit Mega-Constellation Satellite Networks with Service Function Constraints
title_short Deep Reinforcement Learning-Based Routing Method for Low Earth Orbit Mega-Constellation Satellite Networks with Service Function Constraints
title_sort deep reinforcement learning based routing method for low earth orbit mega constellation satellite networks with service function constraints
topic LEO satellite network
routing
service function constraints
graph convolution network
deep reinforcement learning
url https://www.mdpi.com/1424-8220/25/4/1232
work_keys_str_mv AT yanchen deepreinforcementlearningbasedroutingmethodforlowearthorbitmegaconstellationsatellitenetworkswithservicefunctionconstraints
AT huancao deepreinforcementlearningbasedroutingmethodforlowearthorbitmegaconstellationsatellitenetworkswithservicefunctionconstraints
AT longhewang deepreinforcementlearningbasedroutingmethodforlowearthorbitmegaconstellationsatellitenetworkswithservicefunctionconstraints
AT daojinchen deepreinforcementlearningbasedroutingmethodforlowearthorbitmegaconstellationsatellitenetworkswithservicefunctionconstraints
AT zifanliu deepreinforcementlearningbasedroutingmethodforlowearthorbitmegaconstellationsatellitenetworkswithservicefunctionconstraints
AT yiqingzhou deepreinforcementlearningbasedroutingmethodforlowearthorbitmegaconstellationsatellitenetworkswithservicefunctionconstraints
AT jinglinshi deepreinforcementlearningbasedroutingmethodforlowearthorbitmegaconstellationsatellitenetworkswithservicefunctionconstraints