Deep reinforcement learning based task offloading and resource allocation strategy across multiple edge servers
In the mobile edge computing environment, multiple edge servers are often deployed in task-dense areas, however, the service coverage of these edge servers may overlap with each other. In such scenarios, users within the overlapping areas need to determine which server is chosen to offload the task....
Gespeichert in:
| Veröffentlicht in: | Service oriented computing and applications Jg. 19; H. 3; S. 263 - 276 |
|---|---|
| Hauptverfasser: | , , |
| Format: | Journal Article |
| Sprache: | Englisch |
| Veröffentlicht: |
London
Springer London
01.09.2025
Springer Nature B.V |
| Schlagworte: | |
| ISSN: | 1863-2386, 1863-2394 |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| Abstract | In the mobile edge computing environment, multiple edge servers are often deployed in task-dense areas, however, the service coverage of these edge servers may overlap with each other. In such scenarios, users within the overlapping areas need to determine which server is chosen to offload the task. However, unreasonable decision of task offloading may result in imbalanced loads, thereby affecting the number of served users and the latency and energy consumption of user task offloading. Furthermore, the complexity of task offloading and resource allocation is further heightened by the dynamic arrival of user tasks. Therefore, it is crucial to design an effective task offloading and resource allocation strategy in an environment with multiple edge servers. In this paper, we propose a task offloading and resource allocation strategy aimed at meeting task latency requirements while maximizing the number of served users and minimizing the average energy consumption of all completed tasks. To timely obtain information about user tasks and the status of edge servers, we adopt a central controller to manage multiple edge servers. Then, we model the problem as a parameterized action Markov decision process and utilize the parameterized deep Q-network algorithm, a deep reinforcement learning algorithm, to solve it. Additionally, we conducted experiments to evaluate the performance of our proposed strategy against five benchmark strategies. The results demonstrate the superiority of our strategy in terms of the number of served users and the average energy consumption per task while meeting task latency constraints. |
|---|---|
| AbstractList | In the mobile edge computing environment, multiple edge servers are often deployed in task-dense areas, however, the service coverage of these edge servers may overlap with each other. In such scenarios, users within the overlapping areas need to determine which server is chosen to offload the task. However, unreasonable decision of task offloading may result in imbalanced loads, thereby affecting the number of served users and the latency and energy consumption of user task offloading. Furthermore, the complexity of task offloading and resource allocation is further heightened by the dynamic arrival of user tasks. Therefore, it is crucial to design an effective task offloading and resource allocation strategy in an environment with multiple edge servers. In this paper, we propose a task offloading and resource allocation strategy aimed at meeting task latency requirements while maximizing the number of served users and minimizing the average energy consumption of all completed tasks. To timely obtain information about user tasks and the status of edge servers, we adopt a central controller to manage multiple edge servers. Then, we model the problem as a parameterized action Markov decision process and utilize the parameterized deep Q-network algorithm, a deep reinforcement learning algorithm, to solve it. Additionally, we conducted experiments to evaluate the performance of our proposed strategy against five benchmark strategies. The results demonstrate the superiority of our strategy in terms of the number of served users and the average energy consumption per task while meeting task latency constraints. |
| Author | Shi, Bing Huang, Lianzhen Pan, Yuting |
| Author_xml | – sequence: 1 givenname: Bing orcidid: 0000-0002-2382-4104 surname: Shi fullname: Shi, Bing email: bingshi@whut.edu.cn organization: School of Computer Science and Artificial Intelligence, Wuhan University of Technology, Shenzhen Research Institute of Wuhan University of Technology – sequence: 2 givenname: Yuting surname: Pan fullname: Pan, Yuting organization: School of Computer Science and Artificial Intelligence, Wuhan University of Technology – sequence: 3 givenname: Lianzhen surname: Huang fullname: Huang, Lianzhen organization: School of Computer Science and Artificial Intelligence, Wuhan University of Technology |
| BookMark | eNp9kElLBDEQhYMouP4BTwHPrdlMuo_iDoIXPYcslaHHnmRMMoL_3syMKHgwl0qK91VevUO0G1MEhE4pOaeEqItCqZK0I0x0hAg6dHIHHdBe8o7xQez-3Hu5j05KmZN2OFO9VAco3QAscYYxhpQdLCBWPIHJcYwzbE0Bj6spbziFMCXj110TfQNKWjU9NtOUnKljirjUbCrMPrFxOZWCF6upjssJMPgZ4AL5A3I5RnvBTAVOvusRer27fbl-6J6e7x-vr546x-lQOyfN4IV1sr3Aeg4cvFROBscskYEz7qmy3vjgZc8Gq7y1VgQrjSK9UIYfobPt3GVO7ysoVc-b4di-1JxdKiaEHERT9VvVxnGGoN1YN9u0XcZJU6LXCettwrolrDcJa9lQ9gdd5nFh8uf_EN9CpYnjDPKvq3-oL7tRk08 |
| CitedBy_id | crossref_primary_10_1109_TMC_2025_3573278 |
| Cites_doi | 10.1109/TVT.2016.2593486 10.1109/TWC.2021.3085319 10.1109/JIOT.2017.2750180 10.1109/TVT.2018.2881191 10.1109/JIOT.2018.2805263 10.1109/JIOT.2018.2868616 10.1109/TWC.2020.2993071 10.1109/TVT.2020.3013990 10.1109/TCOMM.2021.3058964 10.1109/TETC.2019.2902661 10.1109/MC.2017.3641638 10.1109/ICWS.2019.00041 10.1109/TCC.2019.2898657 10.1007/b102605 10.1109/MNET.2018.1700268 10.1109/TVT.2020.3003898 10.1609/aaai.v30i1.10226 10.1109/TWC.2021.3076201 10.1109/TII.2020.3001355 10.48550/arXiv.1810.06394 10.48550/arXiv.1511.04143 10.1109/TII.2022.3211622 10.1109/ICWS.2019.00035 10.1109/ICWS53863.2021.00052 10.1109/JIOT.2021.3084509 10.1145/3391198 10.1109/TCOMM.2018.2799937 10.1109/wcnc.2018.8377343 |
| ContentType | Journal Article |
| Copyright | The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024 Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024. |
| Copyright_xml | – notice: The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024 Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. – notice: The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024. |
| DBID | AAYXX CITATION JQ2 |
| DOI | 10.1007/s11761-024-00419-6 |
| DatabaseName | CrossRef ProQuest Computer Science Collection |
| DatabaseTitle | CrossRef ProQuest Computer Science Collection |
| DatabaseTitleList | ProQuest Computer Science Collection |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science |
| EISSN | 1863-2394 |
| EndPage | 276 |
| ExternalDocumentID | 10_1007_s11761_024_00419_6 |
| GroupedDBID | -Y2 .VR 06D 0R~ 123 203 2J2 2JN 2JY 2KG 2KM 2LR 2VQ 2~H 30V 4.4 406 408 409 40E 5VS 67Z 6NX 875 8TC 8UJ 95- 95. 95~ AAAVM AABHQ AACDK AAHNG AAIAL AAJBT AAJKR AANZL AAPKM AARHV AARTL AASML AATNV AATVU AAUYE AAWCG AAYIU AAYQN AAYTO AAYZH ABAKF ABBRH ABBXA ABDBE ABDZT ABECU ABFSG ABFTD ABFTV ABHQN ABJNI ABJOX ABKCH ABMNI ABMQK ABNWP ABQBU ABRTQ ABSXP ABTEG ABTHY ABTKH ABTMW ABULA ABWNU ABXPI ACAOD ACBXY ACDTI ACGFS ACHSB ACHXU ACKNC ACMDZ ACMLO ACOKC ACOMO ACPIV ACSNA ACSTC ACZOJ ADHHG ADHIR ADKNI ADKPE ADRFC ADTPH ADURQ ADYFF ADZKW AEBTG AEFQL AEGAL AEGNC AEJHL AEJRE AEMSY AEOHA AEPYU AESKC AETLH AEVLU AEXYK AEZWR AFBBN AFDZB AFGCZ AFHIU AFLOW AFOHR AFQWF AFWTZ AFZKB AGAYW AGDGC AGJBK AGMZJ AGQEE AGQMX AGRTI AGWIL AGWZB AGYKE AHAVH AHBYD AHPBZ AHSBF AHWEU AHYZX AIAKS AIGIU AIIXL AILAN AITGF AIXLP AJBLW AJRNO AJZVZ ALMA_UNASSIGNED_HOLDINGS ALWAN AMKLP AMXSW AMYLF AMYQR AOCGG ARMRJ ATHPR AXYYD AYFIA AYJHY B-. BA0 BDATZ BGNMA CAG COF CS3 CSCUP DDRTE DNIVK DPUIP EBLON EBS EIOEI EJD ESBYG FERAY FFXSO FIGPU FINBP FNLPD FRRFC FSGXE FWDCC GGCAI GGRSB GJIRD GNWQR GQ7 GQ8 GXS H13 HF~ HG5 HG6 HLICF HMJXF HQYDN HRMNR HZ~ IJ- IKXTQ IWAJR IXC IXD IXE IZIGR IZQ I~X J-C J0Z JBSCW JCJTX JZLTJ KDC KOV LLZTM M4Y MA- NPVJJ NQJWS NU0 O9- O93 O9J OAM P2P P9O PF0 PT4 QOS R89 R9I ROL RPX RSV S16 S1Z S27 S3B SAP SCO SDH SHX SISQX SJYHP SNE SNPRN SNX SOHCF SOJ SPISZ SRMVM SSLCW STPWE SZN T13 TSG TSK TSV TUC U2A UG4 UOJIU UTJUX UZXMN VC2 VFIZW W48 YLTOR Z45 ZMTXR ~A9 AAYXX ABJCF AFFHD AFKRA ARAPS BENPR BGLVJ CCPQU CITATION HCIFZ K7- M7S PHGZM PHGZT PQGLB PTHSS JQ2 |
| ID | FETCH-LOGICAL-c319t-c6a9d4bc6319ebd3e3ed67c6fc2b06f323d17bdadfd6829b7dbbb4fb6a70847a3 |
| IEDL.DBID | RSV |
| ISICitedReferencesCount | 1 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001270454200001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1863-2386 |
| IngestDate | Sat Nov 29 03:16:55 EST 2025 Tue Nov 18 22:13:14 EST 2025 Sat Nov 29 07:32:54 EST 2025 Sat Sep 13 01:10:29 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 3 |
| Keywords | Multiple edge servers Deep reinforcement learning Task offloading Resource allocation |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c319t-c6a9d4bc6319ebd3e3ed67c6fc2b06f323d17bdadfd6829b7dbbb4fb6a70847a3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 |
| ORCID | 0000-0002-2382-4104 |
| PQID | 3257244694 |
| PQPubID | 2044172 |
| PageCount | 14 |
| ParticipantIDs | proquest_journals_3257244694 crossref_citationtrail_10_1007_s11761_024_00419_6 crossref_primary_10_1007_s11761_024_00419_6 springer_journals_10_1007_s11761_024_00419_6 |
| PublicationCentury | 2000 |
| PublicationDate | 2025-09-01 |
| PublicationDateYYYYMMDD | 2025-09-01 |
| PublicationDate_xml | – month: 09 year: 2025 text: 2025-09-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationPlace | London |
| PublicationPlace_xml | – name: London – name: Heidelberg |
| PublicationTitle | Service oriented computing and applications |
| PublicationTitleAbbrev | SOCA |
| PublicationYear | 2025 |
| Publisher | Springer London Springer Nature B.V |
| Publisher_xml | – name: Springer London – name: Springer Nature B.V |
| References | MS Elbamby (419_CR2) 2018; 32 L Qian (419_CR17) 2020; 17 J Yan (419_CR11) 2020; 19 Y Chen (419_CR9) 2019; 9 419_CR29 419_CR28 H Li (419_CR14) 2020; 69 419_CR25 X Ma (419_CR24) 2022; 19 419_CR26 419_CR21 X Lyu (419_CR8) 2016; 66 419_CR20 J Wang (419_CR5) 2019; 9 419_CR22 Y Dai (419_CR27) 2020; 69 N Abbas (419_CR4) 2017; 5 S Xia (419_CR16) 2021; 20 G Ananthanarayanan (419_CR1) 2017; 50 Z Ning (419_CR10) 2018; 6 Y Deng (419_CR15) 2021; 9 419_CR18 TX Tran (419_CR6) 2018; 68 H Gao (419_CR23) 2021; 21 G Premsankar (419_CR3) 2018; 5 F Fang (419_CR7) 2021; 69 S Bi (419_CR13) 2021; 20 X Lyu (419_CR19) 2018; 66 419_CR12 |
| References_xml | – volume: 66 start-page: 3435 issue: 4 year: 2016 ident: 419_CR8 publication-title: IEEE Trans Veh Technol doi: 10.1109/TVT.2016.2593486 – volume: 20 start-page: 7519 issue: 11 year: 2021 ident: 419_CR13 publication-title: IEEE Trans Wirel Commun doi: 10.1109/TWC.2021.3085319 – volume: 5 start-page: 450 issue: 1 year: 2017 ident: 419_CR4 publication-title: IEEE Internet Things J doi: 10.1109/JIOT.2017.2750180 – volume: 68 start-page: 856 issue: 1 year: 2018 ident: 419_CR6 publication-title: IEEE Trans Veh Technol doi: 10.1109/TVT.2018.2881191 – volume: 5 start-page: 1275 issue: 2 year: 2018 ident: 419_CR3 publication-title: IEEE Internet Things J doi: 10.1109/JIOT.2018.2805263 – volume: 6 start-page: 4804 issue: 3 year: 2018 ident: 419_CR10 publication-title: IEEE Internet Things J doi: 10.1109/JIOT.2018.2868616 – volume: 19 start-page: 5404 issue: 8 year: 2020 ident: 419_CR11 publication-title: IEEE Trans Wirel Commun doi: 10.1109/TWC.2020.2993071 – volume: 69 start-page: 12175 issue: 10 year: 2020 ident: 419_CR27 publication-title: IEEE Trans Veh Technol doi: 10.1109/TVT.2020.3013990 – volume: 69 start-page: 3436 issue: 5 year: 2021 ident: 419_CR7 publication-title: IEEE Trans Commun doi: 10.1109/TCOMM.2021.3058964 – volume: 9 start-page: 1529 issue: 3 year: 2019 ident: 419_CR5 publication-title: IEEE Trans Emerg Top Comput doi: 10.1109/TETC.2019.2902661 – volume: 50 start-page: 58 issue: 10 year: 2017 ident: 419_CR1 publication-title: Computer doi: 10.1109/MC.2017.3641638 – ident: 419_CR20 doi: 10.1109/ICWS.2019.00041 – volume: 9 start-page: 1050 issue: 3 year: 2019 ident: 419_CR9 publication-title: IEEE Trans Cloud Comput doi: 10.1109/TCC.2019.2898657 – ident: 419_CR26 doi: 10.1007/b102605 – volume: 32 start-page: 78 issue: 2 year: 2018 ident: 419_CR2 publication-title: IEEE Netw doi: 10.1109/MNET.2018.1700268 – volume: 69 start-page: 10214 issue: 9 year: 2020 ident: 419_CR14 publication-title: IEEE Trans Veh Technol doi: 10.1109/TVT.2020.3003898 – ident: 419_CR22 doi: 10.1609/aaai.v30i1.10226 – volume: 20 start-page: 6743 issue: 10 year: 2021 ident: 419_CR16 publication-title: IEEE Trans Wirel Commun doi: 10.1109/TWC.2021.3076201 – volume: 17 start-page: 5688 issue: 8 year: 2020 ident: 419_CR17 publication-title: IEEE Trans Ind Inform doi: 10.1109/TII.2020.3001355 – ident: 419_CR25 doi: 10.48550/arXiv.1810.06394 – ident: 419_CR28 doi: 10.48550/arXiv.1511.04143 – volume: 19 start-page: 2129 issue: 2 year: 2022 ident: 419_CR24 publication-title: IEEE Trans Ind Inform doi: 10.1109/TII.2022.3211622 – ident: 419_CR21 doi: 10.1109/ICWS.2019.00035 – ident: 419_CR18 doi: 10.1109/ICWS53863.2021.00052 – volume: 9 start-page: 68 issue: 1 year: 2021 ident: 419_CR15 publication-title: IEEE Internet Things J doi: 10.1109/JIOT.2021.3084509 – volume: 21 start-page: 1 issue: 1 year: 2021 ident: 419_CR23 publication-title: ACM Trans Internet Technol TOIT doi: 10.1145/3391198 – volume: 66 start-page: 2603 issue: 6 year: 2018 ident: 419_CR19 publication-title: IEEE Trans Commun doi: 10.1109/TCOMM.2018.2799937 – ident: 419_CR12 doi: 10.1109/wcnc.2018.8377343 – ident: 419_CR29 doi: 10.1109/JIOT.2018.2868616 |
| SSID | ssj0000327867 |
| Score | 2.3514097 |
| Snippet | In the mobile edge computing environment, multiple edge servers are often deployed in task-dense areas, however, the service coverage of these edge servers may... |
| SourceID | proquest crossref springer |
| SourceType | Aggregation Database Enrichment Source Index Database Publisher |
| StartPage | 263 |
| SubjectTerms | Algorithms Computation offloading Computer Appl. in Administrative Data Processing Computer Science Computer Systems Organization and Communication Networks Deep learning e-Commerce/e-business Edge computing Energy consumption Game theory Heuristic Internet of Things IT in Business Machine learning Management of Computing and Information Systems Markov processes Mobile computing Original Research Paper Parameterization Resource allocation Servers Software Engineering/Programming and Operating Systems |
| Title | Deep reinforcement learning based task offloading and resource allocation strategy across multiple edge servers |
| URI | https://link.springer.com/article/10.1007/s11761-024-00419-6 https://www.proquest.com/docview/3257244694 |
| Volume | 19 |
| WOSCitedRecordID | wos001270454200001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVAVX databaseName: SpringerLINK Contemporary 1997-Present customDbUrl: eissn: 1863-2394 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000327867 issn: 1863-2386 databaseCode: RSV dateStart: 20070401 isFulltext: true titleUrlDefault: https://link.springer.com/search?facet-content-type=%22Journal%22 providerName: Springer Nature |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3NS8MwFA86PXhxfuJ0Sg7eNNA1XdIcRR0eZIgfY7eSTxGlHWsV_O9N0nRFUUFvLU1CmuTl9_Ley-8BcOwISGQihohpTFBCCbdPqUA6JnY9GWO095hOrul4nE6n7CZcCiubaPfGJel36vay28AeuZHFFORIohgiy2DFwl3qxPH2brKwrEQ4pqlPHTtICUYWk0i4LfN9M58RqVUzv3hGPeCMuv_r6gZYDwomPKtXxCZY0vkW6DbJG2CQ5W1QXGg9g3PtmVOlNxLCkELiETpsU7Di5TMsjHkpfKA95LmyFWpzP3QO-9rcB8ua4fYdcv-HsAlShM5WB53Z1-qYO-BhdHl_foVC9gUkrVhWSBLOVCIksW9aKKyxVoRKYmQsImJwjNWACsWVUSSNmaBKCJEYQTiNLORxvAs6eZHrPQANE9hwRofUZVtXOmVUYSHioTEJSaKkBwbNDGQyUJO7DBkvWUuq7EY0syOa-RHNSA-cLOrMamKOX0v3m4nNgpCWGbbbldVuCLMdOG0msv38c2v7fyt-ANZilzXYR6b1Qaeav-pDsCrfqqdyfuQX7wdU_eqC |
| linkProvider | Springer Nature |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1bS8MwFA46BX1xXnE6NQ--aaBruqR5FHUoziE6x95KriKOdaxV8N-bpO2GooK-tTQJbW7f6Tkn3wfAsSMgkZFoI6YxQREl3F7FAumQ2PlkjNE-Yjro0l4vHg7ZXXkoLKuy3auQpN-p54fdWvaXG1lMQY4kiiGyCJYii1guke_-YTDzrAQ4pLGXjm3FBCOLSaQ8LfN9M58RaW5mfomMesDp1P_3qutgrTQw4VkxIzbAgh5vgnol3gDLtbwF0gutJ3CqPXOq9E5CWEpIPEGHbQrmPHuBqTGj1CfaQz5WtkLh7ocuYF-4-2BWMNy-Q-6_EFZJitD56qBz-1obcxs8di7751eoVF9A0i7LHEnCmYqEJPZOC4U11opQSYwMRUAMDrFqUaG4MorEIRNUCSEiIwingYU8jndAbZyO9S6AhglsOKNt6tTWlY4ZVViIsG1MRKIgaoBWNQKJLKnJnULGKJmTKrseTWyPJr5HE9IAJ7M6k4KY49fSzWpgk3KRZgm225W1bgizL3BaDeT88c-t7f2t-BFYuerfdpPude9mH6yGTkHYZ6k1QS2fvuoDsCzf8udseugn8gda3e1m |
| linkToPdf | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1bS8MwFA46RXxxXnE6NQ--adjWdEnzKM6hOMZAHXsruYo4urFWwX9vkrabigriW0uTkGvPybl8HwCnDoBEhqKNmMYEhZRw-xQJpANi95MxRnuP6bBH-_1oNGKDD1n8Ptq9dEnmOQ0OpSnJGlNlGovEt5a9fiMrX5ADjGKILIOV0JEGufv63XBuZWnigEaeRrYVEYysfCJF5sz3zXyWTguV84uX1AufbvX_3d4EG4XiCS_ynbIFlnSyDaolqQMszvgOmHS0nsKZ9oiq0hsPYUEt8QidzFMw4-kznBgznvgAfMgTZSvkbgDoHPm5GRCmOfLtG-R-tLAMXoTOhgedOdjqnrvgoXt1f3mNClYGJO1xzZAknKlQSGLftFBYY60IlcTIQDSJwQFWLSoUV0aRKGCCKiFEaAThtGlFIcd7oJJMEr0PoGECG85omzoWdqUjRhUWImgbE5KwGdZAq1yNWBaQ5Y45YxwvwJbdjMZ2RmM_ozGpgbN5nWkO2PFr6Xq5yHFxeNMY29-Y1XoIsx04Lxd18fnn1g7-VvwErA063bh30789BOuBIxb2wWt1UMlmL_oIrMrX7CmdHfs9_Q7qZ_ZK |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Deep+reinforcement+learning+based+task+offloading+and+resource+allocation+strategy+across+multiple+edge+servers&rft.jtitle=Service+oriented+computing+and+applications&rft.au=Shi%2C+Bing&rft.au=Pan%2C+Yuting&rft.au=Huang%2C+Lianzhen&rft.date=2025-09-01&rft.pub=Springer+London&rft.issn=1863-2386&rft.eissn=1863-2394&rft.volume=19&rft.issue=3&rft.spage=263&rft.epage=276&rft_id=info:doi/10.1007%2Fs11761-024-00419-6&rft.externalDocID=10_1007_s11761_024_00419_6 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1863-2386&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1863-2386&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1863-2386&client=summon |