{"created":"2024-12-12T08:16:44.293432+00:00","id":2010537,"links":{},"metadata":{"_buckets":{"deposit":"4655d552-6cab-4391-a4b8-c2f93ec47512"},"_deposit":{"created_by":7,"id":"2010537","owners":[7],"pid":{"revision_id":0,"type":"depid","value":"2010537"},"status":"published"},"_oai":{"id":"oai:tokushima-u.repo.nii.ac.jp:02010537","sets":["1713853213384:1713853295607"]},"author_link":["401"],"control_number":"2010537","item_10001_biblio_info_7":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicIssueDates":{"bibliographicIssueDate":"2018-07-01","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"7","bibliographicPageStart":"60","bibliographicVolumeNumber":"10","bibliographic_titles":[{"bibliographic_title":"Future Internet","bibliographic_titleLang":"en"}]}]},"item_10001_description_5":{"attribute_name":"抄録","attribute_value_mlt":[{"subitem_description":"Mobile devices could augment their ability via cloud resources in mobile cloud computing environments. This paper developed a novel two-layered reinforcement learning (TLRL) algorithm to consider task offloading for resource-constrained mobile devices. As opposed to existing literature, the utilization rate of the physical machine and the delay for offloaded tasks are taken into account simultaneously by introducing a weighted reward. The high dimensionality of the state space and action space might affect the speed of convergence. Therefore, a novel reinforcement learning algorithm with a two-layered structure is presented to address this problem. First, k clusters of the physical machines are generated based on the k-nearest neighbors algorithm (k-NN). The first layer of TLRL is implemented by a deep reinforcement learning to determine the cluster to be assigned for the offloaded tasks. On this basis, the second layer intends to further specify a physical machine for task execution. Finally, simulation examples are carried out to verify that the proposed TLRL algorithm is able to speed up the optimal policy learning and can deal with the tradeoff between physical machine utilization rate and delay.","subitem_description_language":"en","subitem_description_type":"Abstract"}]},"item_10001_publisher_8":{"attribute_name":"出版者","attribute_value_mlt":[{"subitem_publisher":"MDPI","subitem_publisher_language":"en"}]},"item_10001_rights_15":{"attribute_name":"権利情報","attribute_value_mlt":[{"subitem_rights":"This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).","subitem_rights_language":"en"}]},"item_10001_source_id_9":{"attribute_name":"収録物ID","attribute_value_mlt":[{"subitem_source_identifier":"19995903","subitem_source_identifier_type":"ISSN"}]},"item_10001_version_type_20":{"attribute_name":"出版タイプ","attribute_value_mlt":[{"subitem_version_resource":"http://purl.org/coar/version/c_970fb48d4fbd8a85","subitem_version_type":"VoR"}]},"item_1715043197608":{"attribute_name":"アクセス権","attribute_value_mlt":[{"subitem_access_right":"open access"}]},"item_1722929371688":{"attribute_name":"出版社版DOI","attribute_value_mlt":[{"subitem_relation_name":[{"subitem_relation_name_language":"ja","subitem_relation_name_text":"10.3390/fi10070060"}],"subitem_relation_type_id":{"subitem_relation_type_id_text":"https://doi.org/10.3390/fi10070060","subitem_relation_type_select":"DOI"}}]},"item_1723180141928":{"attribute_name":"EID","attribute_value_mlt":[{"subitem_identifier_type":"URI","subitem_identifier_uri":"350475"}]},"item_creator":{"attribute_name":"著者","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Quan, Li","creatorNameLang":"en"}]},{"creatorNames":[{"creatorName":"Wang, Zhiliang","creatorNameLang":"en"}]},{"creatorAffiliations":[{"affiliationNameIdentifiers":[{"affiliationNameIdentifier":"","affiliationNameIdentifierScheme":"ISNI","affiliationNameIdentifierURI":"http://www.isni.org/isni/"}],"affiliationNames":[{"affiliationName":"","affiliationNameLang":"ja"}]}],"creatorNames":[{"creatorName":"任, 福継","creatorNameLang":"ja"},{"creatorName":"ニン, フジ","creatorNameLang":"ja-Kana"},{"creatorName":"Ren, Fuji","creatorNameLang":"en"}],"familyNames":[{"familyName":"任","familyNameLang":"ja"},{"familyName":"ニン","familyNameLang":"ja-Kana"},{"familyName":"Ren","familyNameLang":"en"}],"givenNames":[{"givenName":"福継","givenNameLang":"ja"},{"givenName":"フジ","givenNameLang":"ja-Kana"},{"givenName":"Fuji","givenNameLang":"en"}],"nameIdentifiers":[{"nameIdentifier":"401","nameIdentifierScheme":"WEKO"},{"nameIdentifier":"19966/profile-ja.html","nameIdentifierScheme":"徳島大学 教育研究者総覧","nameIdentifierURI":"http://pub2.db.tokushima-u.ac.jp/ERD/person/19966/profile-ja.html"},{"nameIdentifier":"20264947","nameIdentifierScheme":"e-Rad","nameIdentifierURI":"https://nrid.nii.ac.jp/ja/search/?qm=20264947"}]}]},"item_files":{"attribute_name":"ファイル情報","attribute_type":"file","attribute_value_mlt":[{"accessrole":"open_access","date":[{"dateType":"Available","dateValue":"2022-12-07"}],"displaytype":"detail","filename":"futint_10_7_60.pdf","filesize":[{"value":"2.53 MB"}],"format":"application/pdf","licensetype":"license_0","mimetype":"application/pdf","url":{"objectType":"fulltext","url":"https://tokushima-u.repo.nii.ac.jp/record/2010537/files/futint_10_7_60.pdf"},"version_id":"05ea636f-e9e0-4fdf-b065-ba764a47e2e4"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"mobile device","subitem_subject_language":"en","subitem_subject_scheme":"Other"},{"subitem_subject":"task offloading","subitem_subject_language":"en","subitem_subject_scheme":"Other"},{"subitem_subject":"tradeoff","subitem_subject_language":"en","subitem_subject_scheme":"Other"},{"subitem_subject":"mobile cloud computing","subitem_subject_language":"en","subitem_subject_scheme":"Other"},{"subitem_subject":"two layered reinforcement learning","subitem_subject_language":"en","subitem_subject_scheme":"Other"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"eng"}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourcetype":"journal article","resourceuri":"http://purl.org/coar/resource_type/c_6501"}]},"item_title":"A Novel Two-Layered Reinforcement Learning for Task Offloading with Tradeoff between Physical Machine Utilization Rate and Delay","item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"A Novel Two-Layered Reinforcement Learning for Task Offloading with Tradeoff between Physical Machine Utilization Rate and Delay","subitem_title_language":"en"}]},"item_type_id":"40001","owner":"7","path":["1713853295607"],"pubdate":{"attribute_name":"PubDate","attribute_value":"2022-12-07"},"publish_date":"2022-12-07","publish_status":"0","recid":"2010537","relation_version_is_last":true,"title":["A Novel Two-Layered Reinforcement Learning for Task Offloading with Tradeoff between Physical Machine Utilization Rate and Delay"],"weko_creator_id":"7","weko_shared_id":-1},"updated":"2025-02-13T05:58:31.904687+00:00"}