Deep Graph-based Reinforcement Learning for Joint Cruise Control and Task Offloading for Aerial Edge Internet-of-Things (EdgeIoT)

Detalhes bibliográficos
Autor(a) principal: Li, Kai
Data de Publicação: 2022
Outros Autores: Ni, Wei, Yuan, Xin, Noor, Alam, Jamalipour, Abbas
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
Texto Completo: http://hdl.handle.net/10400.22/21637
Resumo: This paper puts forth an aerial edge Internet-of-Things (EdgeIoT) system, where an unmanned aerial vehicle (UAV) is employed as a mobile edge server to process mission-critical computation tasks of ground Internet-of-Things (IoT) devices. When the UAV schedules an IoT device to offload its computation task, the tasks buffered at the other unselected devices could be outdated and have to be cancelled. We investigate a new joint optimization of UAV cruise control and task offloading allocation, which maximizes tasks offloaded to the UAV, subject to the IoT device’s computation capacity and battery budget, and the UAV’s speed limit. Since the optimization contains a large solution space while the instantaneous network states are unknown to the UAV, we propose a new deep graph-based reinforcement learning framework. An advantage actor-critic (A2C) structure is developed to train the real-time continuous actions of the UAV in terms of the flight speed, heading, and the offloading schedule of the IoT device. By exploring hidden representations resulting from the network feature correlation, our framework takes advantage of graph neural networks (GNN) to supervise the training of UAV’s actions in A2C. The proposed GNN-A2C framework is implemented with Google Tensorflow. The performance analysis shows that GNN-A2C achieves fast convergence and reduces considerably the task missing rate in aerial EdgeIoT.
id RCAP_1ae5ef98523f3d19610f7cc585efc1ac
oai_identifier_str oai:recipp.ipp.pt:10400.22/21637
network_acronym_str RCAP
network_name_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository_id_str 7160
spelling Deep Graph-based Reinforcement Learning for Joint Cruise Control and Task Offloading for Aerial Edge Internet-of-Things (EdgeIoT)220602Unmanned aerial vehicleAerial EdgeIoTGraph neural networkDeep reinforcement learningCruise controlTask offloadingThis paper puts forth an aerial edge Internet-of-Things (EdgeIoT) system, where an unmanned aerial vehicle (UAV) is employed as a mobile edge server to process mission-critical computation tasks of ground Internet-of-Things (IoT) devices. When the UAV schedules an IoT device to offload its computation task, the tasks buffered at the other unselected devices could be outdated and have to be cancelled. We investigate a new joint optimization of UAV cruise control and task offloading allocation, which maximizes tasks offloaded to the UAV, subject to the IoT device’s computation capacity and battery budget, and the UAV’s speed limit. Since the optimization contains a large solution space while the instantaneous network states are unknown to the UAV, we propose a new deep graph-based reinforcement learning framework. An advantage actor-critic (A2C) structure is developed to train the real-time continuous actions of the UAV in terms of the flight speed, heading, and the offloading schedule of the IoT device. By exploring hidden representations resulting from the network feature correlation, our framework takes advantage of graph neural networks (GNN) to supervise the training of UAV’s actions in A2C. The proposed GNN-A2C framework is implemented with Google Tensorflow. The performance analysis shows that GNN-A2C achieves fast convergence and reduces considerably the task missing rate in aerial EdgeIoT.This work was supported in part by the National Funds through FCT/MCTES (Portuguese Foundation for Science and Technology), within the CISTER Research Unit under Grant UIDP/UIDB/04234/2020, and in part by national funds through FCT, within project PTDC/EEICOM/3362/2021 (ADANET).IEEERepositório Científico do Instituto Politécnico do PortoLi, KaiNi, WeiYuan, XinNoor, AlamJamalipour, Abbas2022-12-302035-01-01T00:00:00Z2022-12-30T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfhttp://hdl.handle.net/10400.22/21637eng10.1109/JIOT.2022.3182119metadata only accessinfo:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2023-03-13T13:16:08Zoai:recipp.ipp.pt:10400.22/21637Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T17:40:40.300258Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse
dc.title.none.fl_str_mv Deep Graph-based Reinforcement Learning for Joint Cruise Control and Task Offloading for Aerial Edge Internet-of-Things (EdgeIoT)
220602
title Deep Graph-based Reinforcement Learning for Joint Cruise Control and Task Offloading for Aerial Edge Internet-of-Things (EdgeIoT)
spellingShingle Deep Graph-based Reinforcement Learning for Joint Cruise Control and Task Offloading for Aerial Edge Internet-of-Things (EdgeIoT)
Li, Kai
Unmanned aerial vehicle
Aerial EdgeIoT
Graph neural network
Deep reinforcement learning
Cruise control
Task offloading
title_short Deep Graph-based Reinforcement Learning for Joint Cruise Control and Task Offloading for Aerial Edge Internet-of-Things (EdgeIoT)
title_full Deep Graph-based Reinforcement Learning for Joint Cruise Control and Task Offloading for Aerial Edge Internet-of-Things (EdgeIoT)
title_fullStr Deep Graph-based Reinforcement Learning for Joint Cruise Control and Task Offloading for Aerial Edge Internet-of-Things (EdgeIoT)
title_full_unstemmed Deep Graph-based Reinforcement Learning for Joint Cruise Control and Task Offloading for Aerial Edge Internet-of-Things (EdgeIoT)
title_sort Deep Graph-based Reinforcement Learning for Joint Cruise Control and Task Offloading for Aerial Edge Internet-of-Things (EdgeIoT)
author Li, Kai
author_facet Li, Kai
Ni, Wei
Yuan, Xin
Noor, Alam
Jamalipour, Abbas
author_role author
author2 Ni, Wei
Yuan, Xin
Noor, Alam
Jamalipour, Abbas
author2_role author
author
author
author
dc.contributor.none.fl_str_mv Repositório Científico do Instituto Politécnico do Porto
dc.contributor.author.fl_str_mv Li, Kai
Ni, Wei
Yuan, Xin
Noor, Alam
Jamalipour, Abbas
dc.subject.por.fl_str_mv Unmanned aerial vehicle
Aerial EdgeIoT
Graph neural network
Deep reinforcement learning
Cruise control
Task offloading
topic Unmanned aerial vehicle
Aerial EdgeIoT
Graph neural network
Deep reinforcement learning
Cruise control
Task offloading
description This paper puts forth an aerial edge Internet-of-Things (EdgeIoT) system, where an unmanned aerial vehicle (UAV) is employed as a mobile edge server to process mission-critical computation tasks of ground Internet-of-Things (IoT) devices. When the UAV schedules an IoT device to offload its computation task, the tasks buffered at the other unselected devices could be outdated and have to be cancelled. We investigate a new joint optimization of UAV cruise control and task offloading allocation, which maximizes tasks offloaded to the UAV, subject to the IoT device’s computation capacity and battery budget, and the UAV’s speed limit. Since the optimization contains a large solution space while the instantaneous network states are unknown to the UAV, we propose a new deep graph-based reinforcement learning framework. An advantage actor-critic (A2C) structure is developed to train the real-time continuous actions of the UAV in terms of the flight speed, heading, and the offloading schedule of the IoT device. By exploring hidden representations resulting from the network feature correlation, our framework takes advantage of graph neural networks (GNN) to supervise the training of UAV’s actions in A2C. The proposed GNN-A2C framework is implemented with Google Tensorflow. The performance analysis shows that GNN-A2C achieves fast convergence and reduces considerably the task missing rate in aerial EdgeIoT.
publishDate 2022
dc.date.none.fl_str_mv 2022-12-30
2022-12-30T00:00:00Z
2035-01-01T00:00:00Z
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/article
format article
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://hdl.handle.net/10400.22/21637
url http://hdl.handle.net/10400.22/21637
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv 10.1109/JIOT.2022.3182119
dc.rights.driver.fl_str_mv metadata only access
info:eu-repo/semantics/openAccess
rights_invalid_str_mv metadata only access
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv IEEE
publisher.none.fl_str_mv IEEE
dc.source.none.fl_str_mv reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron:RCAAP
instname_str Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron_str RCAAP
institution RCAAP
reponame_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
collection Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository.name.fl_str_mv Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
repository.mail.fl_str_mv
_version_ 1799131495531544576