Cargando…

Deep Reinforcement Learning-Based Resource Allocation for Satellite Internet of Things with Diverse QoS Guarantee

Large-scale terminals’ various QoS requirements are key challenges confronting the resource allocation of Satellite Internet of Things (S-IoT). This paper presents a deep reinforcement learning-based online channel allocation and power control algorithm in an S-IoT uplink scenario. The intelligent a...

Descripción completa

Detalles Bibliográficos
Autores principales: Tang, Siqi, Pan, Zhisong, Hu, Guyu, Wu, Yang, Li, Yunbo
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9024869/
https://www.ncbi.nlm.nih.gov/pubmed/35458964
http://dx.doi.org/10.3390/s22082979
_version_ 1784690717091692544
author Tang, Siqi
Pan, Zhisong
Hu, Guyu
Wu, Yang
Li, Yunbo
author_facet Tang, Siqi
Pan, Zhisong
Hu, Guyu
Wu, Yang
Li, Yunbo
author_sort Tang, Siqi
collection PubMed
description Large-scale terminals’ various QoS requirements are key challenges confronting the resource allocation of Satellite Internet of Things (S-IoT). This paper presents a deep reinforcement learning-based online channel allocation and power control algorithm in an S-IoT uplink scenario. The intelligent agent determines the transmission channel and power simultaneously based on contextual information. Furthermore, the weighted normalized reward concerning success rate, power efficiency, and QoS requirement is adopted to balance the performance between increasing resource efficiency and meeting QoS requirements. Finally, a practical deployment mechanism based on transfer learning is proposed to promote onboard training efficiency and to reduce computation consumption of the training process. The simulation demonstrates that the proposed method can balance the success rate and power efficiency with QoS requirement guaranteed. For S-IoT’s normal operation condition, the proposed method can improve the power efficiency by 60.91% and 144.44% compared with GA and DRL_RA, while its power efficiency is only 4.55% lower than that of DRL-EERA. In addition, this method can be transferred and deployed to a space environment by merely 100 onboard training steps.
format Online
Article
Text
id pubmed-9024869
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-90248692022-04-23 Deep Reinforcement Learning-Based Resource Allocation for Satellite Internet of Things with Diverse QoS Guarantee Tang, Siqi Pan, Zhisong Hu, Guyu Wu, Yang Li, Yunbo Sensors (Basel) Article Large-scale terminals’ various QoS requirements are key challenges confronting the resource allocation of Satellite Internet of Things (S-IoT). This paper presents a deep reinforcement learning-based online channel allocation and power control algorithm in an S-IoT uplink scenario. The intelligent agent determines the transmission channel and power simultaneously based on contextual information. Furthermore, the weighted normalized reward concerning success rate, power efficiency, and QoS requirement is adopted to balance the performance between increasing resource efficiency and meeting QoS requirements. Finally, a practical deployment mechanism based on transfer learning is proposed to promote onboard training efficiency and to reduce computation consumption of the training process. The simulation demonstrates that the proposed method can balance the success rate and power efficiency with QoS requirement guaranteed. For S-IoT’s normal operation condition, the proposed method can improve the power efficiency by 60.91% and 144.44% compared with GA and DRL_RA, while its power efficiency is only 4.55% lower than that of DRL-EERA. In addition, this method can be transferred and deployed to a space environment by merely 100 onboard training steps. MDPI 2022-04-13 /pmc/articles/PMC9024869/ /pubmed/35458964 http://dx.doi.org/10.3390/s22082979 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Tang, Siqi
Pan, Zhisong
Hu, Guyu
Wu, Yang
Li, Yunbo
Deep Reinforcement Learning-Based Resource Allocation for Satellite Internet of Things with Diverse QoS Guarantee
title Deep Reinforcement Learning-Based Resource Allocation for Satellite Internet of Things with Diverse QoS Guarantee
title_full Deep Reinforcement Learning-Based Resource Allocation for Satellite Internet of Things with Diverse QoS Guarantee
title_fullStr Deep Reinforcement Learning-Based Resource Allocation for Satellite Internet of Things with Diverse QoS Guarantee
title_full_unstemmed Deep Reinforcement Learning-Based Resource Allocation for Satellite Internet of Things with Diverse QoS Guarantee
title_short Deep Reinforcement Learning-Based Resource Allocation for Satellite Internet of Things with Diverse QoS Guarantee
title_sort deep reinforcement learning-based resource allocation for satellite internet of things with diverse qos guarantee
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9024869/
https://www.ncbi.nlm.nih.gov/pubmed/35458964
http://dx.doi.org/10.3390/s22082979
work_keys_str_mv AT tangsiqi deepreinforcementlearningbasedresourceallocationforsatelliteinternetofthingswithdiverseqosguarantee
AT panzhisong deepreinforcementlearningbasedresourceallocationforsatelliteinternetofthingswithdiverseqosguarantee
AT huguyu deepreinforcementlearningbasedresourceallocationforsatelliteinternetofthingswithdiverseqosguarantee
AT wuyang deepreinforcementlearningbasedresourceallocationforsatelliteinternetofthingswithdiverseqosguarantee
AT liyunbo deepreinforcementlearningbasedresourceallocationforsatelliteinternetofthingswithdiverseqosguarantee