File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Deep Reinforcement Learning for Intelligent Internet of Vehicles: An Energy-Efficient Computational Offloading Scheme

TitleDeep Reinforcement Learning for Intelligent Internet of Vehicles: An Energy-Efficient Computational Offloading Scheme
Authors
KeywordsInternet of vehicles
Deep reinforcement learning
Computation offloading
Energy efficiency
Issue Date2019
PublisherInstitute of Electrical and Electronics Engineers. The Journal's web site is located at https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=6687307
Citation
IEEE Transactions on Cognitive Communications and Networking, 2019 How to Cite?
AbstractThe emerging vehicular services call for updated communication and computing platforms. Fog computing, whose infrastructure is deployed in close proximity to terminals, extends the facilities of cloud computing. However, due to the limitation of vehicular fog nodes, it is challenging to satisfy the quality of experiences of users, calling for intelligent networks with updated computing abilities. This paper constructs a three-layer offloading framework in intelligent Internet of Vehicles (IoV) to minimize the overall energy consumption while satisfying the delay constraint of users. Due to its high computational complexity, the formulated problem is decomposed into two parts: flow redirection and offloading decision. After that, a deep reinforcement learning based scheme is put forward to solve the optimization problem. Performance evaluations based on real-world traces of taxis in Shanghai (China) demonstrate the effectiveness of our methods, where average energy consumption can be decreased by around 60 percent compared with the baseline algorithm.
Persistent Identifierhttp://hdl.handle.net/10722/275022
ISSN

 

DC FieldValueLanguage
dc.contributor.authorNing, Z-
dc.contributor.authorDong, P-
dc.contributor.authorWang, X-
dc.contributor.authorGuo, L-
dc.contributor.authorRodrigues, JJPC-
dc.contributor.authorKong, X-
dc.contributor.authorHuang, J-
dc.contributor.authorKwok, RYK-
dc.date.accessioned2019-09-10T02:33:51Z-
dc.date.available2019-09-10T02:33:51Z-
dc.date.issued2019-
dc.identifier.citationIEEE Transactions on Cognitive Communications and Networking, 2019-
dc.identifier.issn2332-7731-
dc.identifier.urihttp://hdl.handle.net/10722/275022-
dc.description.abstractThe emerging vehicular services call for updated communication and computing platforms. Fog computing, whose infrastructure is deployed in close proximity to terminals, extends the facilities of cloud computing. However, due to the limitation of vehicular fog nodes, it is challenging to satisfy the quality of experiences of users, calling for intelligent networks with updated computing abilities. This paper constructs a three-layer offloading framework in intelligent Internet of Vehicles (IoV) to minimize the overall energy consumption while satisfying the delay constraint of users. Due to its high computational complexity, the formulated problem is decomposed into two parts: flow redirection and offloading decision. After that, a deep reinforcement learning based scheme is put forward to solve the optimization problem. Performance evaluations based on real-world traces of taxis in Shanghai (China) demonstrate the effectiveness of our methods, where average energy consumption can be decreased by around 60 percent compared with the baseline algorithm.-
dc.languageeng-
dc.publisherInstitute of Electrical and Electronics Engineers. The Journal's web site is located at https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=6687307-
dc.relation.ispartofIEEE Transactions on Cognitive Communications and Networking-
dc.subjectInternet of vehicles-
dc.subjectDeep reinforcement learning-
dc.subjectComputation offloading-
dc.subjectEnergy efficiency-
dc.titleDeep Reinforcement Learning for Intelligent Internet of Vehicles: An Energy-Efficient Computational Offloading Scheme-
dc.typeArticle-
dc.identifier.emailNing, Z: zning@hku.hk-
dc.identifier.emailKwok, RYK: ykwok@hku.hk-
dc.identifier.authorityKwok, RYK=rp00128-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1109/TCCN.2019.2930521-
dc.identifier.hkuros303924-
dc.publisher.placeUnited States-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats