Dependent Task Offloading for Edge Computing based on Deep Reinforcement Learning
Edge computing is an emerging promising computing paradigm that brings computation and storage resources to the network edge, hence significantly reducing the service latency and network traffic. In edge computing, many applications are composed of dependent tasks where the outputs of some are the i...
Saved in:
| Published in: | IEEE transactions on computers Vol. 71; no. 10; pp. 2449 - 2461 |
|---|---|
| Main Authors: | , , , , , |
| Format: | Journal Article |
| Language: | English |
| Published: |
New York
IEEE
01.10.2022
The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Subjects: | |
| ISSN: | 0018-9340, 1557-9956 |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | Edge computing is an emerging promising computing paradigm that brings computation and storage resources to the network edge, hence significantly reducing the service latency and network traffic. In edge computing, many applications are composed of dependent tasks where the outputs of some are the inputs of others. How to offload these tasks to the network edge is a vital and challenging problem which aims to determine the placement of each running task in order to maximize the Quality-of-Service (QoS). Most of the existing studies either design heuristic algorithms that lack strong adaptivity or learning-based methods but without considering the intrinsic task dependency. Different from the existing work, we propose an intelligent task offloading scheme leveraging off-policy reinforcement learning empowered by a Sequence-to-Sequence (S2S) neural network, where the dependent tasks are represented by a Directed Acyclic Graph (DAG). To improve the training efficiency, we combine a specific off-policy policy gradient algorithm with a clipped surrogate objective. We then conduct extensive simulation experiments using heterogeneous applications modelled by synthetic DAGs. The results demonstrate that: 1) our method converges fast and steadily in training; 2) it outperforms the existing methods and approximates the optimal solution in latency and energy consumption under various scenarios. |
|---|---|
| AbstractList | Edge computing is an emerging promising computing paradigm that brings computation and storage resources to the network edge, hence significantly reducing the service latency and network traffic. In edge computing, many applications are composed of dependent tasks where the outputs of some are the inputs of others. How to offload these tasks to the network edge is a vital and challenging problem which aims to determine the placement of each running task in order to maximize the Quality-of-Service (QoS). Most of the existing studies either design heuristic algorithms that lack strong adaptivity or learning-based methods but without considering the intrinsic task dependency. Different from the existing work, we propose an intelligent task offloading scheme leveraging off-policy reinforcement learning empowered by a Sequence-to-Sequence (S2S) neural network, where the dependent tasks are represented by a Directed Acyclic Graph (DAG). To improve the training efficiency, we combine a specific off-policy policy gradient algorithm with a clipped surrogate objective. We then conduct extensive simulation experiments using heterogeneous applications modelled by synthetic DAGs. The results demonstrate that: 1) our method converges fast and steadily in training; 2) it outperforms the existing methods and approximates the optimal solution in latency and energy consumption under various scenarios. |
| Author | Wang, Jin Hu, Jia Georgalas, Nektarios Zomaya, Albert Y. Min, Geyong Zhan, Wenhan |
| Author_xml | – sequence: 1 givenname: Jin orcidid: 0000-0003-2487-2148 surname: Wang fullname: Wang, Jin email: jw855@exeter.ac.uk organization: Department of Computer Science, University of Exeter, Exeter, U.K – sequence: 2 givenname: Jia orcidid: 0000-0001-5406-8420 surname: Hu fullname: Hu, Jia email: j.hu@exeter.ac.uk organization: Department of Computer Science, University of Exeter, Exeter, U.K – sequence: 3 givenname: Geyong orcidid: 0000-0003-1395-7314 surname: Min fullname: Min, Geyong email: g.min@exeter.ac.uk organization: Department of Computer Science, University of Exeter, Exeter, U.K – sequence: 4 givenname: Wenhan orcidid: 0000-0002-1851-7185 surname: Zhan fullname: Zhan, Wenhan email: zhanwenhan@uestc.edu.cn organization: School of Computer Science and Engeeneering, University of Electronic Science and Technology of China, Chengdu, Sichuan, China – sequence: 5 givenname: Albert Y. orcidid: 0000-0002-3090-1059 surname: Zomaya fullname: Zomaya, Albert Y. email: albert.zomaya@sydney.edu.au organization: School of Information Technologies, The University of Sydney, Camperdown, NSW, Australia – sequence: 6 givenname: Nektarios orcidid: 0000-0001-9746-3236 surname: Georgalas fullname: Georgalas, Nektarios email: nektarios.georgalas@bt.com organization: Applied Research Department, British Telecom, London, U.K |
| BookMark | eNp9kD1rwzAQQEVJoWnauUMXQWcnJ8mWrLE46QcEQos7C9k-B6eJ5MrO0H9fm4QOHTodHO_dwbsmE-cdEnLHYM4Y6EWezTlwNhdMMIjhgkxZkqhI60ROyBSApZEWMVyR667bAYDkoKfkbYktugpdT3PbfdJNXe-9rRq3pbUPdFVtkWb-0B77cVXYDivqHV0itvQdGzdAJR5GfY02uAG6IZe13Xd4e54z8vG0yrOXaL15fs0e11EpBPRRodNS17IQhQWlE6FQYQVWxqyEVNRWFrXmFWcxk0IrJaysoEyxsJrbqgQtZuThdLcN_uuIXW92_hjc8NJwNRSRAsRILU5UGXzXBaxNG5qDDd-GgRm7mTwzYzdz7jYYyR-jbHrbN971wTb7f7z7k9cg4u8XLblSUogfGBR61Q |
| CODEN | ITCOB4 |
| CitedBy_id | crossref_primary_10_1109_ACCESS_2025_3568848 crossref_primary_10_1109_TSC_2025_3552338 crossref_primary_10_3390_electronics13122387 crossref_primary_10_3390_electronics14163184 crossref_primary_10_1002_cpe_8315 crossref_primary_10_1109_TCC_2023_3290777 crossref_primary_10_1109_ACCESS_2024_3452190 crossref_primary_10_1109_TNSM_2024_3391664 crossref_primary_10_1145_3544836 crossref_primary_10_1088_1742_6596_2670_1_012021 crossref_primary_10_1186_s13677_022_00365_8 crossref_primary_10_1109_JIOT_2024_3516838 crossref_primary_10_1109_JSAC_2022_3233532 crossref_primary_10_1007_s41870_025_02725_4 crossref_primary_10_1109_TGCN_2024_3514578 crossref_primary_10_1109_TC_2025_3587620 crossref_primary_10_1109_JIOT_2025_3586685 crossref_primary_10_1109_COMST_2022_3212586 crossref_primary_10_1109_TVT_2024_3389951 crossref_primary_10_1109_JIOT_2025_3542574 crossref_primary_10_1109_TII_2025_3563531 crossref_primary_10_1016_j_jnca_2025_104211 crossref_primary_10_3390_fi16060181 crossref_primary_10_1016_j_eswa_2024_124657 crossref_primary_10_1109_TII_2022_3217477 crossref_primary_10_1109_TSC_2024_3478826 crossref_primary_10_1016_j_sysarc_2025_103447 crossref_primary_10_1109_JIOT_2024_3447036 crossref_primary_10_1109_JIOT_2023_3288379 crossref_primary_10_3390_electronics12061304 crossref_primary_10_1016_j_adhoc_2025_103754 crossref_primary_10_1109_TMC_2024_3406721 crossref_primary_10_1109_TMC_2024_3506221 crossref_primary_10_3390_app131810027 crossref_primary_10_1109_TNSM_2024_3491432 crossref_primary_10_1016_j_future_2024_04_034 crossref_primary_10_1109_TMC_2024_3362912 crossref_primary_10_1109_JIOT_2024_3520954 crossref_primary_10_1109_TNSM_2024_3375839 crossref_primary_10_1109_TNSM_2023_3295653 crossref_primary_10_3390_electronics12122599 crossref_primary_10_1109_TMC_2023_3264901 crossref_primary_10_7717_peerj_cs_893 crossref_primary_10_1002_cpe_8050 crossref_primary_10_1109_TNSM_2024_3428496 crossref_primary_10_3390_fi15120395 crossref_primary_10_1016_j_dcan_2024_08_015 crossref_primary_10_1109_ACCESS_2024_3494775 crossref_primary_10_1007_s00607_024_01327_5 crossref_primary_10_1109_TMC_2025_3531887 crossref_primary_10_1007_s40747_023_01322_x crossref_primary_10_1109_TKDE_2025_3555328 crossref_primary_10_1007_s00607_025_01449_4 crossref_primary_10_1109_JIOT_2024_3397296 crossref_primary_10_1016_j_future_2024_04_028 crossref_primary_10_1109_TWC_2024_3429510 crossref_primary_10_1109_TMC_2022_3219983 crossref_primary_10_1109_TCE_2024_3357459 crossref_primary_10_1109_JIOT_2024_3506159 crossref_primary_10_1016_j_simpat_2025_103168 crossref_primary_10_1109_TC_2023_3337317 crossref_primary_10_1007_s10586_025_05468_w crossref_primary_10_1109_JIOT_2024_3510805 crossref_primary_10_1109_TMC_2023_3289611 crossref_primary_10_1109_TC_2023_3321938 crossref_primary_10_1016_j_future_2024_107588 crossref_primary_10_1109_TCCN_2024_3508784 crossref_primary_10_1109_TSC_2025_3556614 crossref_primary_10_1109_TSC_2024_3495510 crossref_primary_10_1109_JIOT_2022_3233667 crossref_primary_10_1109_TCC_2024_3381646 crossref_primary_10_1016_j_asoc_2025_113105 crossref_primary_10_1007_s11235_025_01310_1 crossref_primary_10_1109_TMC_2025_3573379 crossref_primary_10_3389_fdata_2024_1422546 crossref_primary_10_1038_s41598_025_93731_w crossref_primary_10_1007_s11276_023_03283_y crossref_primary_10_1109_JIOT_2024_3439332 crossref_primary_10_1007_s10586_024_04732_9 crossref_primary_10_1109_TC_2025_3585630 crossref_primary_10_1109_TVT_2025_3546914 crossref_primary_10_1109_JIOT_2025_3526984 crossref_primary_10_1109_TC_2024_3355767 crossref_primary_10_1109_TCCN_2024_3520961 crossref_primary_10_1145_3603703 crossref_primary_10_1109_TVT_2023_3328845 crossref_primary_10_1109_TMC_2023_3320104 crossref_primary_10_1109_TC_2024_3354033 crossref_primary_10_1109_JIOT_2025_3549441 crossref_primary_10_1007_s10586_024_04893_7 crossref_primary_10_1109_JIOT_2024_3461853 crossref_primary_10_1109_JIOT_2024_3517342 crossref_primary_10_1109_TNET_2023_3323514 crossref_primary_10_1109_TCE_2024_3419098 crossref_primary_10_3390_electronics13132528 crossref_primary_10_1109_TSC_2025_3589122 crossref_primary_10_1109_TPDS_2024_3468892 crossref_primary_10_1109_TMC_2024_3355868 crossref_primary_10_1109_JIOT_2024_3374969 crossref_primary_10_7717_peerj_cs_851 crossref_primary_10_1109_TVT_2024_3523376 crossref_primary_10_1007_s42452_024_06396_x crossref_primary_10_1109_ACCESS_2023_3302528 crossref_primary_10_1109_MNET_2024_3383242 crossref_primary_10_1109_JIOT_2025_3534737 crossref_primary_10_1109_TC_2025_3558020 crossref_primary_10_1016_j_jnca_2023_103785 crossref_primary_10_1109_TCC_2023_3328614 crossref_primary_10_1016_j_iot_2023_100868 crossref_primary_10_1016_j_comnet_2025_111445 crossref_primary_10_1109_JIOT_2022_3150419 |
| Cites_doi | 10.1145/1999995.2000000 10.1109/TCC.2017.2701794 10.1126/science.aar6404 10.1109/TCOMM.2017.2699660 10.1109/TMC.2018.2815015 10.1109/TC.2020.2987567 10.1109/TC.2020.2976996 10.1109/TVT.2017.2740724 10.1109/JSAC.2018.2815360 10.1109/TC.2020.2969148 10.1109/TC.2016.2536019 10.1109/TCOMM.2018.2866572 10.1109/JIOT.2018.2876279 10.1109/TPDS.2013.57 10.1109/MCOM.2019.1800971 10.1007/978-1-4615-3618-5_2 10.1109/COMST.2017.2682318 10.1038/nature14236 10.1109/WCNC.2018.8377343 10.1109/MobileCloud.2015.22 10.1145/344588.344618 10.1109/TVT.2020.2966500 10.1038/s41586-019-1724-z 10.1109/TMC.2020.3036871 10.1109/TSC.2014.2381227 10.1109/71.993206 |
| ContentType | Journal Article |
| Copyright | Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022 |
| Copyright_xml | – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022 |
| DBID | 97E RIA RIE AAYXX CITATION 7SC 7SP 8FD JQ2 L7M L~C L~D |
| DOI | 10.1109/TC.2021.3131040 |
| DatabaseName | IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE/IET Electronic Library (IEL) (UW System Shared) CrossRef Computer and Information Systems Abstracts Electronics & Communications Abstracts Technology Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional |
| DatabaseTitle | CrossRef Technology Research Database Computer and Information Systems Abstracts – Academic Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Professional |
| DatabaseTitleList | Technology Research Database |
| Database_xml | – sequence: 1 dbid: RIE name: IEEE Xplore Digital Library url: https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering Computer Science |
| EISSN | 1557-9956 |
| EndPage | 2461 |
| ExternalDocumentID | 10_1109_TC_2021_3131040 9627763 |
| Genre | orig-research |
| GrantInformation_xml | – fundername: EU Horizon 2020 INITIATE Project grantid: 101008297 |
| GroupedDBID | --Z -DZ -~X .DC 0R~ 29I 4.4 5GY 6IK 85S 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACIWK ACNCT AENEX AETEA AGQYO AHBIQ AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ASUFR ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS EJD HZ~ IEDLZ IFIPE IPLJI JAVBF LAI M43 MS~ O9- OCL P2P PQQKQ RIA RIE RNS RXW TAE TN5 TWZ UHB UPT XZL YZZ AAYXX ABUFD CITATION 7SC 7SP 8FD JQ2 L7M L~C L~D |
| ID | FETCH-LOGICAL-c330t-b98c9f6b3ba079537e7ed0a641c083fa6bf92d2141639773a6d0c8eba92adc093 |
| IEDL.DBID | RIE |
| ISICitedReferencesCount | 148 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000850876700008&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0018-9340 |
| IngestDate | Sun Nov 30 04:34:31 EST 2025 Sat Nov 29 01:35:43 EST 2025 Tue Nov 18 22:18:33 EST 2025 Wed Aug 27 02:14:29 EDT 2025 |
| IsDoiOpenAccess | false |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 10 |
| Language | English |
| License | https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html https://doi.org/10.15223/policy-029 https://doi.org/10.15223/policy-037 |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c330t-b98c9f6b3ba079537e7ed0a641c083fa6bf92d2141639773a6d0c8eba92adc093 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 |
| ORCID | 0000-0001-5406-8420 0000-0003-1395-7314 0000-0002-1851-7185 0000-0001-9746-3236 0000-0003-2487-2148 0000-0002-3090-1059 |
| OpenAccessLink | https://ore.exeter.ac.uk/repository/bitstream/10871/127931/1/rl-taskoffloading.pdf |
| PQID | 2711063039 |
| PQPubID | 85452 |
| PageCount | 13 |
| ParticipantIDs | crossref_citationtrail_10_1109_TC_2021_3131040 crossref_primary_10_1109_TC_2021_3131040 ieee_primary_9627763 proquest_journals_2711063039 |
| PublicationCentury | 2000 |
| PublicationDate | 2022-10-01 |
| PublicationDateYYYYMMDD | 2022-10-01 |
| PublicationDate_xml | – month: 10 year: 2022 text: 2022-10-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationPlace | New York |
| PublicationPlace_xml | – name: New York |
| PublicationTitle | IEEE transactions on computers |
| PublicationTitleAbbrev | TC |
| PublicationYear | 2022 |
| Publisher | IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Publisher_xml | – name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| References | ref35 ref13 ref34 ref12 ref37 ref15 ref36 ref14 ref31 ref33 ref11 ref32 ref10 dai (ref38) 2017 ref2 mnih (ref20) 2016 ref39 ref17 ref16 abbas (ref6) 0; 8 mnih (ref19) 2015; 518 ref18 sabell (ref1) 2019; 20 ba (ref30) 2016 schulman (ref23) 2017 bahdanau (ref26) 2015 ref21 sutskever (ref25) 2014 doerr (ref22) 2019 ref29 ref7 schulman (ref24) 2016 ref9 ref4 ref3 ref5 lillicrap (ref8) 2016 kool (ref28) 2019 vinyals (ref27) 2015 |
| References_xml | – ident: ref13 doi: 10.1145/1999995.2000000 – ident: ref14 doi: 10.1109/TCC.2017.2701794 – ident: ref7 doi: 10.1126/science.aar6404 – year: 2016 ident: ref30 article-title: Layer normalization publication-title: Proc Adv Neural Inf Process Syst – ident: ref3 doi: 10.1109/TCOMM.2017.2699660 – ident: ref34 doi: 10.1109/TMC.2018.2815015 – ident: ref12 doi: 10.1109/TC.2020.2987567 – ident: ref5 doi: 10.1109/TC.2020.2976996 – year: 2017 ident: ref23 article-title: Proximal policy optimization algorithms – ident: ref17 doi: 10.1109/TVT.2017.2740724 – ident: ref4 doi: 10.1109/JSAC.2018.2815360 – ident: ref9 doi: 10.1109/TC.2020.2969148 – ident: ref33 doi: 10.1109/TC.2016.2536019 – start-page: 2692 year: 2015 ident: ref27 article-title: Pointer networks publication-title: Proc 28th Int Conf Neural Inf Process Syst – year: 2019 ident: ref28 article-title: Attention, learn to solve routing problems! publication-title: Proc Int Conf Learn Representations – ident: ref37 doi: 10.1109/TCOMM.2018.2866572 – ident: ref36 doi: 10.1109/JIOT.2018.2876279 – ident: ref29 doi: 10.1109/TPDS.2013.57 – year: 2016 ident: ref8 article-title: Continuous control with deep reinforcement learning publication-title: Proc Int Conf Learn Representations – start-page: 3104 year: 2014 ident: ref25 article-title: Sequence to sequence learning with neural networks publication-title: Proc 27th Int Conf Adv Neural Inf Process Syst – ident: ref11 doi: 10.1109/MCOM.2019.1800971 – start-page: 6348 year: 2017 ident: ref38 article-title: Learning combinatorial optimization algorithms over graphs publication-title: Proc Adv Neural Inf Process Syst – year: 2016 ident: ref24 article-title: High-dimensional continuous control using generalized advantage estimation publication-title: Proc Int Conf Learn Representations – ident: ref21 doi: 10.1007/978-1-4615-3618-5_2 – ident: ref32 doi: 10.1109/COMST.2017.2682318 – year: 2015 ident: ref26 article-title: Neural machine translation by jointly learning to align and translate publication-title: Proc Int Conf Learn Representations – volume: 518 start-page: 529 year: 2015 ident: ref19 article-title: Human-level control through deep reinforcement learning publication-title: Nature doi: 10.1038/nature14236 – volume: 8 year: 0 ident: ref6 article-title: Reward-oriented task offloading under limited edge server power for multi-access edge computing publication-title: IEEE Internet of Things J – ident: ref35 doi: 10.1109/WCNC.2018.8377343 – ident: ref15 doi: 10.1109/MobileCloud.2015.22 – start-page: 1928 year: 2016 ident: ref20 article-title: Asynchronous methods for deep reinforcement learning publication-title: Proc Int Conf Mach Learn – ident: ref18 doi: 10.1145/344588.344618 – ident: ref16 doi: 10.1109/TVT.2020.2966500 – start-page: 1636 year: 2019 ident: ref22 article-title: Trajectory-based off-policy deep reinforcement learning publication-title: Proc Int Conf Mach Learn – ident: ref39 doi: 10.1038/s41586-019-1724-z – volume: 20 year: 2019 ident: ref1 article-title: Developing software for multi-access edge computing publication-title: ETSI White Paper – ident: ref10 doi: 10.1109/TMC.2020.3036871 – ident: ref2 doi: 10.1109/TSC.2014.2381227 – ident: ref31 doi: 10.1109/71.993206 |
| SSID | ssj0006209 |
| Score | 2.680576 |
| Snippet | Edge computing is an emerging promising computing paradigm that brings computation and storage resources to the network edge, hence significantly reducing the... |
| SourceID | proquest crossref ieee |
| SourceType | Aggregation Database Enrichment Source Index Database Publisher |
| StartPage | 2449 |
| SubjectTerms | Algorithms Communications traffic Computation offloading Deep learning deep reinforcement learning Edge computing Energy consumption Graphical representations Heuristic methods Machine learning Multi-access edge computing Neural networks Reinforcement learning sequence to sequence neural networks Solid modeling Task analysis task offloading Training Wireless communication |
| Title | Dependent Task Offloading for Edge Computing based on Deep Reinforcement Learning |
| URI | https://ieeexplore.ieee.org/document/9627763 https://www.proquest.com/docview/2711063039 |
| Volume | 71 |
| WOSCitedRecordID | wos000850876700008&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: PRVIEE databaseName: IEEE Xplore Digital Library customDbUrl: eissn: 1557-9956 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0006209 issn: 0018-9340 databaseCode: RIE dateStart: 19680101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LTwIxEJ4A8aAHUdCIounBgwcXutt99WgQ4gkfwYTbpk9iJCzh4e-3LYWQqAdPu9m0zWa_TmemO_0-gFtOSCgwjwMzG3AQU5EEjIc6kArnUicZoTp2YhPZcJiPx_SlAve7szBKKVd8pjr21v3Ll6VY262yrhWKMfZQhaq5bM5q7VbddFvOERoDJjH2ND4hpt1Rz-SBUWjSUxPL2F2OPQ_kJFV-rMPOuQzq_3utEzj2QSR62KB-ChU1a0B9K9CAvL024GiPbbAJr49e8HaFRmz5iZ61npauhB6ZyBX15UShzRj2kXVvEpUz9KjUHL0px7Aq3GYi8qSskzN4H_RHvafAKyoEghC8CjjNBdUpJ5zhjCYkU5mSmKWxwSsnmqVc00hGoY3STGBIWCqxyBVnNGJSYErOoTYrZ-oCkAkMNctjymOCLQEONwObjFQkCWGRSbpa0Nl-5UJ4unGrejEtXNqBaTHqFRaWwsPSgrtdh_mGaePvpk2Lwq6ZB6AF7S2MhbfEZRFlZoTUOGp6-XuvKziM7JEGV6DXhtpqsVbXcCC-Vh_LxY2bZN8y2c1O |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1JSwMxFH7UBdSDWxXrmoMHD06bmWSWHKUqFbUujOBtyCqitKWt_n6TNC2CevA2DEkY5svLey95-T6AY0FILLGgkZ0NOKJMphEXsYmUxoUyaU6YoV5sIu92i-dndl-D09ldGK21Lz7TTffoz_JVX364rbKWE4qx9jAHCymlCZ7c1pqtu9m0oCO2JkwoDkQ-MWatsm0zwSS2CaqNZtw-xzcf5EVVfqzE3r1crv3vw9ZhNYSR6GyC-wbUdG8T1qYSDShY7CasfOMbrMPDeZC8HaOSj97QnTHvfV9Ej2zsii7Ui0aTMdwr5-AU6vfQudYD9Kg9x6r024ko0LK-bMHT5UXZ7kRBUyGShOBxJFghmckEERznLCW5zrXCPKMWsYIYngnDEpXELk6zoSHhmcKy0IKzhCuJGdmG-V6_p3cA2dDQ8IIyQQl2FDjCDmxzUpmmhCc27WpAc_qXKxkIx53uxXvlEw_MqrJdOViqAEsDTmYdBhOujb-b1h0Ks2YBgAbsT2Gsgi2OqiS3I2TWVbPd33sdwVKnvL2pbq6613uwnLgLDr5cbx_mx8MPfQCL8nP8Ohoe-gn3BQxl0JU |
| 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=Dependent+Task+Offloading+for+Edge+Computing+based+on+Deep+Reinforcement+Learning&rft.jtitle=IEEE+transactions+on+computers&rft.au=Wang%2C+Jin&rft.au=Hu%2C+Jia&rft.au=Min%2C+Geyong&rft.au=Zhan%2C+Wenhan&rft.date=2022-10-01&rft.pub=The+Institute+of+Electrical+and+Electronics+Engineers%2C+Inc.+%28IEEE%29&rft.issn=0018-9340&rft.eissn=1557-9956&rft.volume=71&rft.issue=10&rft.spage=2449&rft_id=info:doi/10.1109%2FTC.2021.3131040&rft.externalDBID=NO_FULL_TEXT |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0018-9340&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0018-9340&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0018-9340&client=summon |