Federated Deep Reinforcement Learning for Internet of Things with Decentralized Cooperative Edge Caching

Simple item page
dc.contributorAalto-yliopistofi
dc.contributorAalto Universityen
dc.contributor.authorWang, Xiaofeien_US
dc.contributor.authorWang, Chenyangen_US
dc.contributor.authorLi, Xiuhuaen_US
dc.contributor.authorLeung, Victor C.M.en_US
dc.contributor.authorTaleb, Tariken_US
dc.contributor.departmentDepartment of Communications and Networkingen
dc.contributor.groupauthorMobile Network Softwarization and Service Customizationen
dc.contributor.organizationTianjin Universityen_US
dc.contributor.organizationChongqing Universityen_US
dc.contributor.organizationShenzhen Universityen_US
dc.date.accessioned2020-11-06T11:39:20Z
dc.date.available2020-11-06T11:39:20Z
dc.date.issued2020-10en_US
dc.description| openaire: EC/H2020/871780/EU//MonB5G
dc.description.abstractEdge caching is an emerging technology for addressing massive content access in mobile networks to support rapidly growing Internet-of-Things (IoT) services and applications. However, most current optimization-based methods lack a self-adaptive ability in dynamic environments. To tackle these challenges, current learning-based approaches are generally proposed in a centralized way. However, network resources may be overconsumed during the training and data transmission process. To address the complex and dynamic control issues, we propose a federated deep-reinforcement-learning-based cooperative edge caching (FADE) framework. FADE enables base stations (BSs) to cooperatively learn a shared predictive model by considering the first-round training parameters of the BSs as the initial input of the local training, and then uploads near-optimal local parameters to the BSs to participate in the next round of global training. Furthermore, we prove the expectation convergence of FADE. Trace-driven simulation results demonstrate the effectiveness of the proposed FADE framework on reducing the performance loss and average delay, offloading backhaul traffic, and improving the hit rate.en
dc.description.versionPeer revieweden
dc.format.extent15
dc.format.extent9441-9455
dc.format.mimetypeapplication/pdfen_US
dc.identifier.citationWang, X, Wang, C, Li, X, Leung, V C M & Taleb, T 2020, ' Federated Deep Reinforcement Learning for Internet of Things with Decentralized Cooperative Edge Caching ', IEEE Internet of Things Journal, vol. 7, no. 10, 9062302, pp. 9441-9455 . https://doi.org/10.1109/JIOT.2020.2986803en
dc.identifier.doi10.1109/JIOT.2020.2986803en_US
dc.identifier.issn2327-4662
dc.identifier.otherPURE UUID: 9275f8aa-8abf-452b-a5a4-754a627d18f8en_US
dc.identifier.otherPURE ITEMURL: https://research.aalto.fi/en/publications/9275f8aa-8abf-452b-a5a4-754a627d18f8en_US
dc.identifier.otherPURE LINK: http://www.scopus.com/inward/record.url?scp=85087622595&partnerID=8YFLogxKen_US
dc.identifier.otherPURE FILEURL: https://research.aalto.fi/files/52538818/Federated_deep_reinforcement_learning.pdfen_US
dc.identifier.urihttps://aaltodoc.aalto.fi/handle/123456789/47462
dc.identifier.urnURN:NBN:fi:aalto-202011066354
dc.language.isoenen
dc.publisherIEEE
dc.relationinfo:eu-repo/grantAgreement/EC/H2020/871780/EU//MonB5Gen_US
dc.relation.ispartofseriesIEEE Internet of Things Journalen
dc.relation.ispartofseriesVolume 7, issue 10en
dc.rightsopenAccessen
dc.subject.keywordCooperative cachingen_US
dc.subject.keyworddeep reinforcement learning (DRL)en_US
dc.subject.keywordedge cachingen_US
dc.subject.keywordfederated learningen_US
dc.subject.keywordhit rateen_US
dc.subject.keywordInternet of Things (IoT)en_US
dc.titleFederated Deep Reinforcement Learning for Internet of Things with Decentralized Cooperative Edge Cachingen
dc.typeA1 Alkuperäisartikkeli tieteellisessä aikakauslehdessäfi
dc.type.versionacceptedVersion
Files
Collections
[article-cris] Sähkötekniikan korkeakoulu / ELEC