Multi objective reinforcement learning driven task offloading algorithm for satellite edge computing networks

Abstract Satellite edge computing (SEC) has become a revolutionary paradigm to improve the quality of service, reduce the pressure on satellite-terrestrial backhaul bandwidth and reduce the average response delay of task requests. In this paper, we propose a task offloading algorithm based on K-D3QN...

Full description

Saved in:
Bibliographic Details
Main Authors: Sai Xu, Jun Liu, Jiawei Tang, Xiangjun Liu, Zhi Li
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-10553-6
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849334994341724160
author Sai Xu
Jun Liu
Jiawei Tang
Xiangjun Liu
Zhi Li
author_facet Sai Xu
Jun Liu
Jiawei Tang
Xiangjun Liu
Zhi Li
author_sort Sai Xu
collection DOAJ
description Abstract Satellite edge computing (SEC) has become a revolutionary paradigm to improve the quality of service, reduce the pressure on satellite-terrestrial backhaul bandwidth and reduce the average response delay of task requests. In this paper, we propose a task offloading algorithm based on K-D3QN to meet the rapidly growing demand of ground users. This algorithm improves the DQN algorithm by incorporating a satellite resource clustering module, a DDQN algorithm, and a competitive network mechanism module. The offloading decision-making process comprehensively considers three optimization objectives: task latency, resource utilization, and load-balancing degree, to achieve dynamic multi-objective optimization. Experimental results shown that the algorithm significantly reduces task latency, improves resource utilization and load-balancing degree.
format Article
id doaj-art-44d34a01a2c34451aff35347a07fc36a
institution Kabale University
issn 2045-2322
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-44d34a01a2c34451aff35347a07fc36a2025-08-20T03:45:26ZengNature PortfolioScientific Reports2045-23222025-07-0115111310.1038/s41598-025-10553-6Multi objective reinforcement learning driven task offloading algorithm for satellite edge computing networksSai Xu0Jun Liu1Jiawei Tang2Xiangjun Liu3Zhi Li4School of Computer Science and Engineering, Northeastern UniversitySchool of Computer Science and Engineering, Northeastern UniversitySchool of Computer Science and Engineering, Northeastern UniversityCS&S Information System Engineering Co.,Ltd School of Information Science and Engineering, Shenyang Ligong UniversityAbstract Satellite edge computing (SEC) has become a revolutionary paradigm to improve the quality of service, reduce the pressure on satellite-terrestrial backhaul bandwidth and reduce the average response delay of task requests. In this paper, we propose a task offloading algorithm based on K-D3QN to meet the rapidly growing demand of ground users. This algorithm improves the DQN algorithm by incorporating a satellite resource clustering module, a DDQN algorithm, and a competitive network mechanism module. The offloading decision-making process comprehensively considers three optimization objectives: task latency, resource utilization, and load-balancing degree, to achieve dynamic multi-objective optimization. Experimental results shown that the algorithm significantly reduces task latency, improves resource utilization and load-balancing degree.https://doi.org/10.1038/s41598-025-10553-6Space-based information networkSatellite edge computingTask offloadingReinforcement learningDQN
spellingShingle Sai Xu
Jun Liu
Jiawei Tang
Xiangjun Liu
Zhi Li
Multi objective reinforcement learning driven task offloading algorithm for satellite edge computing networks
Scientific Reports
Space-based information network
Satellite edge computing
Task offloading
Reinforcement learning
DQN
title Multi objective reinforcement learning driven task offloading algorithm for satellite edge computing networks
title_full Multi objective reinforcement learning driven task offloading algorithm for satellite edge computing networks
title_fullStr Multi objective reinforcement learning driven task offloading algorithm for satellite edge computing networks
title_full_unstemmed Multi objective reinforcement learning driven task offloading algorithm for satellite edge computing networks
title_short Multi objective reinforcement learning driven task offloading algorithm for satellite edge computing networks
title_sort multi objective reinforcement learning driven task offloading algorithm for satellite edge computing networks
topic Space-based information network
Satellite edge computing
Task offloading
Reinforcement learning
DQN
url https://doi.org/10.1038/s41598-025-10553-6
work_keys_str_mv AT saixu multiobjectivereinforcementlearningdriventaskoffloadingalgorithmforsatelliteedgecomputingnetworks
AT junliu multiobjectivereinforcementlearningdriventaskoffloadingalgorithmforsatelliteedgecomputingnetworks
AT jiaweitang multiobjectivereinforcementlearningdriventaskoffloadingalgorithmforsatelliteedgecomputingnetworks
AT xiangjunliu multiobjectivereinforcementlearningdriventaskoffloadingalgorithmforsatelliteedgecomputingnetworks
AT zhili multiobjectivereinforcementlearningdriventaskoffloadingalgorithmforsatelliteedgecomputingnetworks