Integrating deep reinforcement learning with pointer networks for service request scheduling in edge computing

With the increasing popularity of edge computing, service providers are more likely to deploy services at the edge of the network to reduce the latency of service requests. However, the resources offered by edge servers are extremely limited compared to those in the cloud. Therefore, a challenging i...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Knowledge-based systems Ročník 258; s. 109983
Hlavní autoři: Zhao, Yuqi, Li, Bing, Wang, Jian, Jiang, Delun, Li, Duantengchuan
Médium: Journal Article
Jazyk:angličtina
Vydáno: Elsevier B.V 22.12.2022
Témata:
ISSN:0950-7051, 1872-7409
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract With the increasing popularity of edge computing, service providers are more likely to deploy services at the edge of the network to reduce the latency of service requests. However, the resources offered by edge servers are extremely limited compared to those in the cloud. Therefore, a challenging issue in edge computing is how to sufficiently utilize service resources at the edge to satisfy as many service requests as possible. Existing service request scheduling methods mainly use a single optimization objective, e.g., resource utilization or running time. In this paper, the issue of service request scheduling with multiple requests is modeled as a sequential problem, where multiple optimization objectives, including resource utilization, running time, and waiting time, are involved. A reinforcement learning model with pointer networks is proposed to construct scheduling policies. Experiments conducted on three representative real-world datasets show that our proposed approach outperforms several state-of-the-art methods on the three metrics.
AbstractList With the increasing popularity of edge computing, service providers are more likely to deploy services at the edge of the network to reduce the latency of service requests. However, the resources offered by edge servers are extremely limited compared to those in the cloud. Therefore, a challenging issue in edge computing is how to sufficiently utilize service resources at the edge to satisfy as many service requests as possible. Existing service request scheduling methods mainly use a single optimization objective, e.g., resource utilization or running time. In this paper, the issue of service request scheduling with multiple requests is modeled as a sequential problem, where multiple optimization objectives, including resource utilization, running time, and waiting time, are involved. A reinforcement learning model with pointer networks is proposed to construct scheduling policies. Experiments conducted on three representative real-world datasets show that our proposed approach outperforms several state-of-the-art methods on the three metrics.
ArticleNumber 109983
Author Wang, Jian
Zhao, Yuqi
Jiang, Delun
Li, Bing
Li, Duantengchuan
Author_xml – sequence: 1
  givenname: Yuqi
  surname: Zhao
  fullname: Zhao, Yuqi
  organization: School of Computer Science, Wuhan University, Wuhan, China
– sequence: 2
  givenname: Bing
  surname: Li
  fullname: Li, Bing
  email: bingli@whu.edu.cn
  organization: School of Computer Science, Wuhan University, Wuhan, China
– sequence: 3
  givenname: Jian
  orcidid: 0000-0002-1559-9314
  surname: Wang
  fullname: Wang, Jian
  email: jianwang@whu.edu.cn
  organization: School of Computer Science, Wuhan University, Wuhan, China
– sequence: 4
  givenname: Delun
  surname: Jiang
  fullname: Jiang, Delun
  organization: School of Computer Science, Wuhan University, Wuhan, China
– sequence: 5
  givenname: Duantengchuan
  surname: Li
  fullname: Li, Duantengchuan
  organization: School of Computer Science, Wuhan University, Wuhan, China
BookMark eNqFkE1LAzEQhoNUsK3-Aw_5A1uT3U2TeBCk-AUFL3oOITvbph_JmqQt_fdmWU8e9DAMzLzPDO87QSPnHSB0S8mMEjq_28y2zsdznJWkLPNISlFdoDEVvCx4TeQIjYlkpOCE0Ss0iXFDSFZSMUbuzSVYBZ2sW-EGoMMBrGt9MLAHl_AOdHD97mTTGnfeZnnADtLJh23EWYgjhKM1kMGvA8SEo1lDc9j1kHUYmhVg4_fdoX9xjS5bvYtw89On6PP56WPxWizfX94Wj8vCVGSeCiEazjWXgs0NaerSSABimDCsyqUbYFXLOJXECKg1FQSYZEA4tJCNcl1N0f1w1wQfY4BWGZuySe9S0HanKFF9cmqjhuRUn5wakstw_Qvugt3rcP4PexgwyMaOFoKKxoIz0NgAJqnG278PfANxq5Ax
CitedBy_id crossref_primary_10_3390_app131910689
crossref_primary_10_1145_3709141
crossref_primary_10_1007_s43926_024_00089_y
crossref_primary_10_1016_j_eswa_2024_124606
crossref_primary_10_1007_s10115_024_02167_7
crossref_primary_10_1016_j_knosys_2025_113574
crossref_primary_10_1016_j_rineng_2025_105981
crossref_primary_10_1016_j_jss_2024_112145
crossref_primary_10_1109_TNSE_2024_3521885
crossref_primary_10_1016_j_knosys_2025_113633
crossref_primary_10_1109_TCYB_2025_3594063
crossref_primary_10_1016_j_cja_2025_103567
crossref_primary_10_1016_j_knosys_2024_112018
crossref_primary_10_1038_s41598_024_81684_5
crossref_primary_10_3390_electronics14163327
Cites_doi 10.1109/TII.2022.3155162
10.1016/j.future.2021.10.013
10.1109/DASC-PICom-CBDCom-CyberSciTech52372.2021.00112
10.32604/csse.2022.024021
10.1109/JIOT.2021.3104015
10.1186/s13677-021-00276-0
10.1007/BF00941281
10.1023/A:1022672621406
10.1007/978-3-030-64243-3_27
10.1109/WCSP49889.2020.9299801
10.1016/j.knosys.2021.107099
10.1109/TPDS.2021.3131680
10.1007/s10489-021-02549-2
10.1016/j.ins.2022.05.053
10.1016/j.ins.2021.11.052
10.1016/j.sysarc.2020.101799
10.1109/INFOCOM.2017.8057116
10.1109/Cybermatics_2018.2018.00109
10.1109/ICWS53863.2021.00078
10.1109/TMC.2020.3017079
10.1016/j.asoc.2022.108731
10.1109/TC.2020.2987567
10.1145/3487552.3487815
10.1016/j.energy.2017.02.174
10.1109/JIOT.2021.3107431
10.1137/1034115
10.1109/JSAC.2021.3118419
10.1016/j.energy.2013.10.034
10.1145/3500911
10.1007/978-3-030-03596-9_15
ContentType Journal Article
Copyright 2022 Elsevier B.V.
Copyright_xml – notice: 2022 Elsevier B.V.
DBID AAYXX
CITATION
DOI 10.1016/j.knosys.2022.109983
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
EISSN 1872-7409
ExternalDocumentID 10_1016_j_knosys_2022_109983
S0950705122010760
GroupedDBID --K
--M
.DC
.~1
0R~
1B1
1~.
1~5
4.4
457
4G.
5VS
7-5
71M
77K
8P~
9JN
AACTN
AAEDT
AAEDW
AAIAV
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AAXUO
AAYFN
ABAOU
ABBOA
ABIVO
ABJNI
ABMAC
ABYKQ
ACAZW
ACDAQ
ACGFS
ACRLP
ACZNC
ADBBV
ADEZE
ADGUI
ADTZH
AEBSH
AECPX
AEKER
AENEX
AFKWA
AFTJW
AGHFR
AGUBO
AGYEJ
AHHHB
AHJVU
AHZHX
AIALX
AIEXJ
AIKHN
AITUG
AJOXV
ALMA_UNASSIGNED_HOLDINGS
AMFUW
AMRAJ
AOUOD
ARUGR
AXJTR
BJAXD
BKOJK
BLXMC
CS3
DU5
EBS
EFJIC
EFLBG
EO8
EO9
EP2
EP3
FDB
FIRID
FNPLU
FYGXN
G-Q
GBLVA
GBOLZ
IHE
J1W
JJJVA
KOM
LG9
LY7
M41
MHUIS
MO0
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
PQQKQ
Q38
ROL
RPZ
SDF
SDG
SDP
SES
SPC
SPCBC
SST
SSV
SSW
SSZ
T5K
WH7
XPP
ZMT
~02
~G-
29L
77I
9DU
AAQXK
AATTM
AAXKI
AAYWO
AAYXX
ABDPE
ABWVN
ABXDB
ACLOT
ACNNM
ACRPL
ACVFH
ADCNI
ADJOM
ADMUD
ADNMO
AEIPS
AEUPX
AFJKZ
AFPUW
AGQPQ
AIGII
AIIUN
AKBMS
AKRWK
AKYEP
ANKPU
APXCP
ASPBG
AVWKF
AZFZN
CITATION
EFKBS
EJD
FEDTE
FGOYB
G-2
HLZ
HVGLF
HZ~
R2-
SBC
SET
SEW
UHS
WUQ
~HD
ID FETCH-LOGICAL-c306t-88d77a79856c0d42c9ee0c58c538c5ade53f57190c8e4a180e595e07efe0957a3
ISICitedReferencesCount 16
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000880093300012&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0950-7051
IngestDate Sat Nov 29 07:07:15 EST 2025
Tue Nov 18 21:58:38 EST 2025
Fri Feb 23 02:39:27 EST 2024
IsPeerReviewed true
IsScholarly true
Keywords Deep reinforcement learning
Pointer networks
Scheduling algorithm
Edge computing
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c306t-88d77a79856c0d42c9ee0c58c538c5ade53f57190c8e4a180e595e07efe0957a3
ORCID 0000-0002-1559-9314
ParticipantIDs crossref_citationtrail_10_1016_j_knosys_2022_109983
crossref_primary_10_1016_j_knosys_2022_109983
elsevier_sciencedirect_doi_10_1016_j_knosys_2022_109983
PublicationCentury 2000
PublicationDate 2022-12-22
PublicationDateYYYYMMDD 2022-12-22
PublicationDate_xml – month: 12
  year: 2022
  text: 2022-12-22
  day: 22
PublicationDecade 2020
PublicationTitle Knowledge-based systems
PublicationYear 2022
Publisher Elsevier B.V
Publisher_xml – name: Elsevier B.V
References Stallings (b13) 2011
J. Deng, B. Li, J. Wang, Y. Zhao, Microservice Pre-Deployment Based on Mobility Prediction and Service Composition in Edge, in: 2021 IEEE International Conference on Web Services, ICWS, 2021, pp. 569–578.
Tanenbaum (b12) 2009
Goren, Fogel, Halperin (b17) 2022; 27
Deng, Zhang, Zhou, Liu, Zhou, Chen, Zhao (b19) 2022; 585
Li, Shi, Deng, Hu (b18) 2022; 121
Kong, Duan, Hou, Shen, Wang, Yan, Collotta (b22) 2022; 18
Bello, Pham, Le, Norouzi, Bengio (b32) 2017
X. Zhao, X. Guo, Y. Zhang, W. Li, A Parallel-Batch Multi-Objective Job Scheduling Algorithm in Edge Computing, in: IEEE International Conference on Internet of Things (IThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData), 2018, pp. 510–516.
Zou, Hao, Yu, Jin (b14) 2021; 70
Zhu, Lin, Li, Wang (b21) 2021; 225
Tuli, Ilager, Ramamohanarao, Buyya (b10) 2022; 21
H. Wang, M. Yurochkin, Y. Sun, D.S. Papailiopoulos, Y. Khazaeni, Federated Learning with Matched Averaging, in: 8th International Conference on Learning Representations, ICLR, 2020.
O. Vinyals, M. Fortunato, N. Jaitly, Pointer Networks, in: Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems, 2015, pp. 2692–2700.
I. Sutskever, O. Vinyals, Q.V. Le, Sequence to Sequence Learning with Neural Networks, in: Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems, 2014, pp. 3104–3112.
Hu, Shaloudegi, Zhang, Yu (b26) 2020
L. Zeng, J. Sun, J. Ma, Q. Liu, Task Scheduling Based on Multi-level Hashing and HRRN in cloud computing, in: IEEE Intl Conf on Dependable, Autonomic and Secure Computing, 2021, pp. 667–672.
H. Tan, Z. Han, X. Li, F.C.M. Lau, Online job dispatching and scheduling in edge-clouds, in: 2017 IEEE Conference on Computer Communications, INFOCOM, 2017, pp. 1–9.
Hansen (b36) 1992; 34
Wang, Wang, Jia, Pang (b6) 2022; 42
Liao, Li, Guo, Kang, Li (b7) 2022; 9
Cai, Wang, Wang, Lyu, Xu, Zheng, Vasilakos (b11) 2022; 40
Cui, Geng, Zhu, Han (b29) 2017; 125
M. Xu, Z. Fu, X. Ma, L. Zhang, Y. Li, F. Qian, S. Wang, K. Li, J. Yang, X. Liu, From cloud to edge: a first look at public edge platforms, in: IMC ’21: ACM Internet Measurement Conference, Virtual Event, USA, 2021, pp. 37–53.
Golub, Heath, Wahba (b37) 2007
R. Chen, L. Cui, Y. Zhang, J. Chen, K. Yao, Y. Yang, C. Yao, H. Han, Delay Optimization with FCFS Queuing Model in Mobile Edge Computing-Assisted UAV Swarms: A Game-Theoretic Learning Approach, in: 2020 International Conference on Wireless Communications and Signal Processing (WCSP), 2020, pp. 245–250.
Wang, Li, Huang, Wang, Luo (b20) 2022
Zheng, Wan, Zhang, Jiang (b15) 2022; 11
Engl (b38) 1987; 52
Xia, Qiu, Xu, Zhang (b4) 2022; 606
Song, Xing, Wang, Luo, Dai, Li (b23) 2022; 128
Williams (b33) 1992; 8
Yuan, He, Chen, Zhang, Qi, Xu, Xiang, Yang (b1) 2022; 33
P. Lai, Q. He, M. Abdelrazek, F. Chen, J.G. Hosking, J.C. Grundy, Y. Yang, Optimal Edge User Allocation in Edge Computing with Variable Sized Vector Bin Packing, in: C. Pahl, M. Vukovic, J. Yin, Q. Yu (Eds.), Service-Oriented Computing - 16th International Conference, ICSOC, Vol. 11236, 2018, pp. 230–245.
Song, Ma, Zhao, Yang, Zhai (b5) 2022; 52
J. Lu, X. Guo, X. Zhao, H. Zhou, A Parallel Tasks Scheduling Algorithm with Markov Decision Process in Edge Computing, in: Green, Pervasive, and Cloud Computing - 15th International Conference, GPC, Vol. 12398, 2020, pp. 362–375.
Huang, Li, Bai, Wang, Bai, Wang (b24) 2020
Sun, Yin, Zou, Zhang, Zhang, Zhou (b8) 2020; 108
J. Schaffer, Multiple Objective Optimization with Vector Evaluated Genetic Algorithms, in: G.J.E. Grefensette, J.J.L. Erlbraum (Eds.), Proceedings of the First Int. Conference on Genetic Algortihms, 1985, pp. 93–100.
Peng, Wu, Xia, Ma, Wang, Jiang (b3) 2022; 9
Falsafi, Zakariazadeh, Jadid (b28) 2014; 64
Zou (10.1016/j.knosys.2022.109983_b14) 2021; 70
10.1016/j.knosys.2022.109983_b25
10.1016/j.knosys.2022.109983_b27
Golub (10.1016/j.knosys.2022.109983_b37) 2007
Huang (10.1016/j.knosys.2022.109983_b24) 2020
Song (10.1016/j.knosys.2022.109983_b5) 2022; 52
Wang (10.1016/j.knosys.2022.109983_b6) 2022; 42
Cui (10.1016/j.knosys.2022.109983_b29) 2017; 125
Sun (10.1016/j.knosys.2022.109983_b8) 2020; 108
Hu (10.1016/j.knosys.2022.109983_b26) 2020
Li (10.1016/j.knosys.2022.109983_b18) 2022; 121
Tuli (10.1016/j.knosys.2022.109983_b10) 2022; 21
Williams (10.1016/j.knosys.2022.109983_b33) 1992; 8
Cai (10.1016/j.knosys.2022.109983_b11) 2022; 40
Engl (10.1016/j.knosys.2022.109983_b38) 1987; 52
Deng (10.1016/j.knosys.2022.109983_b19) 2022; 585
Falsafi (10.1016/j.knosys.2022.109983_b28) 2014; 64
10.1016/j.knosys.2022.109983_b30
10.1016/j.knosys.2022.109983_b31
Wang (10.1016/j.knosys.2022.109983_b20) 2022
10.1016/j.knosys.2022.109983_b34
Goren (10.1016/j.knosys.2022.109983_b17) 2022; 27
10.1016/j.knosys.2022.109983_b35
10.1016/j.knosys.2022.109983_b9
10.1016/j.knosys.2022.109983_b16
10.1016/j.knosys.2022.109983_b39
Stallings (10.1016/j.knosys.2022.109983_b13) 2011
10.1016/j.knosys.2022.109983_b2
Tanenbaum (10.1016/j.knosys.2022.109983_b12) 2009
Zhu (10.1016/j.knosys.2022.109983_b21) 2021; 225
Yuan (10.1016/j.knosys.2022.109983_b1) 2022; 33
Xia (10.1016/j.knosys.2022.109983_b4) 2022; 606
Kong (10.1016/j.knosys.2022.109983_b22) 2022; 18
Peng (10.1016/j.knosys.2022.109983_b3) 2022; 9
Zheng (10.1016/j.knosys.2022.109983_b15) 2022; 11
Liao (10.1016/j.knosys.2022.109983_b7) 2022; 9
Song (10.1016/j.knosys.2022.109983_b23) 2022; 128
Hansen (10.1016/j.knosys.2022.109983_b36) 1992; 34
Bello (10.1016/j.knosys.2022.109983_b32) 2017
10.1016/j.knosys.2022.109983_b40
10.1016/j.knosys.2022.109983_b41
References_xml – year: 2020
  ident: b26
  article-title: FedMGDA+: Federated learning meets multi-objective optimization
– reference: J. Schaffer, Multiple Objective Optimization with Vector Evaluated Genetic Algorithms, in: G.J.E. Grefensette, J.J.L. Erlbraum (Eds.), Proceedings of the First Int. Conference on Genetic Algortihms, 1985, pp. 93–100.
– volume: 585
  start-page: 441
  year: 2022
  end-page: 453
  ident: b19
  article-title: An enhanced fast non-dominated solution sorting genetic algorithm for multi-objective problems
  publication-title: Inform. Sci.
– reference: L. Zeng, J. Sun, J. Ma, Q. Liu, Task Scheduling Based on Multi-level Hashing and HRRN in cloud computing, in: IEEE Intl Conf on Dependable, Autonomic and Secure Computing, 2021, pp. 667–672.
– volume: 64
  start-page: 853
  year: 2014
  end-page: 867
  ident: b28
  article-title: The role of demand response in single and multi-objective wind-thermal generation scheduling: A stochastic programming
  publication-title: Energy
– reference: H. Tan, Z. Han, X. Li, F.C.M. Lau, Online job dispatching and scheduling in edge-clouds, in: 2017 IEEE Conference on Computer Communications, INFOCOM, 2017, pp. 1–9.
– reference: J. Deng, B. Li, J. Wang, Y. Zhao, Microservice Pre-Deployment Based on Mobility Prediction and Service Composition in Edge, in: 2021 IEEE International Conference on Web Services, ICWS, 2021, pp. 569–578.
– reference: H. Wang, M. Yurochkin, Y. Sun, D.S. Papailiopoulos, Y. Khazaeni, Federated Learning with Matched Averaging, in: 8th International Conference on Learning Representations, ICLR, 2020.
– volume: 52
  start-page: 4028
  year: 2022
  end-page: 4040
  ident: b5
  article-title: Cost-efficient multi-service task offloading scheduling for mobile edge computing
  publication-title: Appl. Intell.
– volume: 9
  start-page: 4451
  year: 2022
  end-page: 4463
  ident: b7
  article-title: Dependency-aware application assigning and scheduling in edge computing
  publication-title: IEEE Internet Things J.
– reference: R. Chen, L. Cui, Y. Zhang, J. Chen, K. Yao, Y. Yang, C. Yao, H. Han, Delay Optimization with FCFS Queuing Model in Mobile Edge Computing-Assisted UAV Swarms: A Game-Theoretic Learning Approach, in: 2020 International Conference on Wireless Communications and Signal Processing (WCSP), 2020, pp. 245–250.
– volume: 9
  start-page: 4677
  year: 2022
  end-page: 4692
  ident: b3
  article-title: DoSRA: A decentralized approach to online edge task scheduling and resource allocation
  publication-title: IEEE Internet Things J.
– volume: 125
  start-page: 681
  year: 2017
  end-page: 704
  ident: b29
  article-title: Review: Multi-objective optimization methods and application in energy saving
  publication-title: Energy
– volume: 52
  start-page: 209
  year: 1987
  end-page: 215
  ident: b38
  article-title: Discrepancy principles for Tikhonov regularization of ill-posed problems leading to optimal convergence rates
  publication-title: J. Optim. Theory Appl.
– volume: 70
  start-page: 228
  year: 2021
  end-page: 239
  ident: b14
  article-title: A3C-DO: A regional resource scheduling framework based on deep reinforcement learning in edge scenario
  publication-title: IEEE Trans. Comput.
– reference: O. Vinyals, M. Fortunato, N. Jaitly, Pointer Networks, in: Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems, 2015, pp. 2692–2700.
– volume: 18
  start-page: 6308
  year: 2022
  end-page: 6316
  ident: b22
  article-title: Deep reinforcement learning-based energy-efficient edge computing for internet of vehicles
  publication-title: IEEE Trans. Ind. Inform.
– reference: X. Zhao, X. Guo, Y. Zhang, W. Li, A Parallel-Batch Multi-Objective Job Scheduling Algorithm in Edge Computing, in: IEEE International Conference on Internet of Things (IThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData), 2018, pp. 510–516.
– volume: 34
  start-page: 561
  year: 1992
  end-page: 580
  ident: b36
  article-title: Analysis of discrete ill-posed problems by means of the L-curve
  publication-title: SIAM Rev.
– reference: M. Xu, Z. Fu, X. Ma, L. Zhang, Y. Li, F. Qian, S. Wang, K. Li, J. Yang, X. Liu, From cloud to edge: a first look at public edge platforms, in: IMC ’21: ACM Internet Measurement Conference, Virtual Event, USA, 2021, pp. 37–53.
– volume: 40
  start-page: 611
  year: 2022
  end-page: 625
  ident: b11
  article-title: Dynacomm: Accelerating distributed CNN training between edges and clouds through dynamic communication scheduling
  publication-title: IEEE J. Sel. Areas Commun.
– reference: J. Lu, X. Guo, X. Zhao, H. Zhou, A Parallel Tasks Scheduling Algorithm with Markov Decision Process in Edge Computing, in: Green, Pervasive, and Cloud Computing - 15th International Conference, GPC, Vol. 12398, 2020, pp. 362–375.
– start-page: 202
  year: 2007
  end-page: 212
  ident: b37
  article-title: Generalized cross-validation as a method for choosing a good ridge parameter
  publication-title: Milestones in Matrix Computation - Selected Works of Gene H. Golub, with Commentaries
– volume: 121
  year: 2022
  ident: b18
  article-title: Pyramid particle swarm optimization with novel strategies of competition and cooperation
  publication-title: Appl. Soft Comput.
– volume: 128
  start-page: 333
  year: 2022
  end-page: 348
  ident: b23
  article-title: Offloading dependent tasks in multi-access edge computing: A multi-objective reinforcement learning approach
  publication-title: Future Gener. Comput. Syst.
– reference: I. Sutskever, O. Vinyals, Q.V. Le, Sequence to Sequence Learning with Neural Networks, in: Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems, 2014, pp. 3104–3112.
– year: 2022
  ident: b20
  article-title: Smart contract-based caching and data transaction optimization in mobile edge computing
  publication-title: Knowl.-Based Syst.
– reference: P. Lai, Q. He, M. Abdelrazek, F. Chen, J.G. Hosking, J.C. Grundy, Y. Yang, Optimal Edge User Allocation in Edge Computing with Variable Sized Vector Bin Packing, in: C. Pahl, M. Vukovic, J. Yin, Q. Yu (Eds.), Service-Oriented Computing - 16th International Conference, ICSOC, Vol. 11236, 2018, pp. 230–245.
– volume: 606
  start-page: 38
  year: 2022
  end-page: 59
  ident: b4
  article-title: Multi-objective workflow scheduling based on genetic algorithm in cloud environment
  publication-title: Inform. Sci.
– volume: 27
  start-page: 2.3:1
  year: 2022
  end-page: 2.3:17
  ident: b17
  article-title: Area optimal polygonization using simulated annealing
  publication-title: ACM J. Exp. Algorithmics
– year: 2009
  ident: b12
  article-title: Modern Operating Systems
– year: 2017
  ident: b32
  article-title: Neural combinatorial optimization with reinforcement learning
– volume: 21
  start-page: 940
  year: 2022
  end-page: 954
  ident: b10
  article-title: Dynamic scheduling for stochastic edge-cloud computing environments using A3C learning and residual recurrent neural networks
  publication-title: IEEE Trans. Mob. Comput.
– year: 2011
  ident: b13
  article-title: Operating Systems - Internals and Design Principles
– volume: 11
  start-page: 3
  year: 2022
  ident: b15
  article-title: Deep reinforcement learning-based workload scheduling for edge computing
  publication-title: J. Cloud Comput.
– year: 2020
  ident: b24
  article-title: A federated multi-view deep learning framework for privacy-preserving recommendations
– volume: 42
  start-page: 1241
  year: 2022
  end-page: 1255
  ident: b6
  article-title: Flexible task scheduling based on edge computing and cloud collaboration
  publication-title: Comput. Syst. Sci. Eng.
– volume: 33
  start-page: 1873
  year: 2022
  end-page: 1887
  ident: b1
  article-title: CSEdge: Enabling collaborative edge storage for multi-access edge computing based on blockchain
  publication-title: IEEE Trans. Parallel Distrib. Syst.
– volume: 225
  year: 2021
  ident: b21
  article-title: A decomposition-based multi-objective genetic programming hyper-heuristic approach for the multi-skill resource constrained project scheduling problem
  publication-title: Knowl.-Based Syst.
– volume: 108
  year: 2020
  ident: b8
  article-title: Makespan-minimization workflow scheduling for complex networks with social groups in edge computing
  publication-title: J. Syst. Archit.
– volume: 8
  start-page: 229
  year: 1992
  end-page: 256
  ident: b33
  article-title: Simple statistical gradient-following algorithms for connectionist reinforcement learning
  publication-title: Mach. Learn.
– volume: 18
  start-page: 6308
  issue: 9
  year: 2022
  ident: 10.1016/j.knosys.2022.109983_b22
  article-title: Deep reinforcement learning-based energy-efficient edge computing for internet of vehicles
  publication-title: IEEE Trans. Ind. Inform.
  doi: 10.1109/TII.2022.3155162
– volume: 128
  start-page: 333
  year: 2022
  ident: 10.1016/j.knosys.2022.109983_b23
  article-title: Offloading dependent tasks in multi-access edge computing: A multi-objective reinforcement learning approach
  publication-title: Future Gener. Comput. Syst.
  doi: 10.1016/j.future.2021.10.013
– ident: 10.1016/j.knosys.2022.109983_b40
  doi: 10.1109/DASC-PICom-CBDCom-CyberSciTech52372.2021.00112
– volume: 42
  start-page: 1241
  issue: 3
  year: 2022
  ident: 10.1016/j.knosys.2022.109983_b6
  article-title: Flexible task scheduling based on edge computing and cloud collaboration
  publication-title: Comput. Syst. Sci. Eng.
  doi: 10.32604/csse.2022.024021
– volume: 9
  start-page: 4451
  issue: 6
  year: 2022
  ident: 10.1016/j.knosys.2022.109983_b7
  article-title: Dependency-aware application assigning and scheduling in edge computing
  publication-title: IEEE Internet Things J.
  doi: 10.1109/JIOT.2021.3104015
– year: 2020
  ident: 10.1016/j.knosys.2022.109983_b24
– volume: 11
  start-page: 3
  year: 2022
  ident: 10.1016/j.knosys.2022.109983_b15
  article-title: Deep reinforcement learning-based workload scheduling for edge computing
  publication-title: J. Cloud Comput.
  doi: 10.1186/s13677-021-00276-0
– ident: 10.1016/j.knosys.2022.109983_b16
– volume: 52
  start-page: 209
  issue: 2
  year: 1987
  ident: 10.1016/j.knosys.2022.109983_b38
  article-title: Discrepancy principles for Tikhonov regularization of ill-posed problems leading to optimal convergence rates
  publication-title: J. Optim. Theory Appl.
  doi: 10.1007/BF00941281
– ident: 10.1016/j.knosys.2022.109983_b31
– volume: 8
  start-page: 229
  year: 1992
  ident: 10.1016/j.knosys.2022.109983_b33
  article-title: Simple statistical gradient-following algorithms for connectionist reinforcement learning
  publication-title: Mach. Learn.
  doi: 10.1023/A:1022672621406
– ident: 10.1016/j.knosys.2022.109983_b34
  doi: 10.1007/978-3-030-64243-3_27
– ident: 10.1016/j.knosys.2022.109983_b39
  doi: 10.1109/WCSP49889.2020.9299801
– volume: 225
  year: 2021
  ident: 10.1016/j.knosys.2022.109983_b21
  article-title: A decomposition-based multi-objective genetic programming hyper-heuristic approach for the multi-skill resource constrained project scheduling problem
  publication-title: Knowl.-Based Syst.
  doi: 10.1016/j.knosys.2021.107099
– volume: 33
  start-page: 1873
  issue: 8
  year: 2022
  ident: 10.1016/j.knosys.2022.109983_b1
  article-title: CSEdge: Enabling collaborative edge storage for multi-access edge computing based on blockchain
  publication-title: IEEE Trans. Parallel Distrib. Syst.
  doi: 10.1109/TPDS.2021.3131680
– volume: 52
  start-page: 4028
  issue: 4
  year: 2022
  ident: 10.1016/j.knosys.2022.109983_b5
  article-title: Cost-efficient multi-service task offloading scheduling for mobile edge computing
  publication-title: Appl. Intell.
  doi: 10.1007/s10489-021-02549-2
– year: 2022
  ident: 10.1016/j.knosys.2022.109983_b20
  article-title: Smart contract-based caching and data transaction optimization in mobile edge computing
  publication-title: Knowl.-Based Syst.
– volume: 606
  start-page: 38
  year: 2022
  ident: 10.1016/j.knosys.2022.109983_b4
  article-title: Multi-objective workflow scheduling based on genetic algorithm in cloud environment
  publication-title: Inform. Sci.
  doi: 10.1016/j.ins.2022.05.053
– volume: 585
  start-page: 441
  year: 2022
  ident: 10.1016/j.knosys.2022.109983_b19
  article-title: An enhanced fast non-dominated solution sorting genetic algorithm for multi-objective problems
  publication-title: Inform. Sci.
  doi: 10.1016/j.ins.2021.11.052
– volume: 108
  year: 2020
  ident: 10.1016/j.knosys.2022.109983_b8
  article-title: Makespan-minimization workflow scheduling for complex networks with social groups in edge computing
  publication-title: J. Syst. Archit.
  doi: 10.1016/j.sysarc.2020.101799
– ident: 10.1016/j.knosys.2022.109983_b41
  doi: 10.1109/INFOCOM.2017.8057116
– year: 2017
  ident: 10.1016/j.knosys.2022.109983_b32
– ident: 10.1016/j.knosys.2022.109983_b9
  doi: 10.1109/Cybermatics_2018.2018.00109
– year: 2009
  ident: 10.1016/j.knosys.2022.109983_b12
– ident: 10.1016/j.knosys.2022.109983_b2
  doi: 10.1109/ICWS53863.2021.00078
– ident: 10.1016/j.knosys.2022.109983_b25
– volume: 21
  start-page: 940
  issue: 3
  year: 2022
  ident: 10.1016/j.knosys.2022.109983_b10
  article-title: Dynamic scheduling for stochastic edge-cloud computing environments using A3C learning and residual recurrent neural networks
  publication-title: IEEE Trans. Mob. Comput.
  doi: 10.1109/TMC.2020.3017079
– volume: 121
  year: 2022
  ident: 10.1016/j.knosys.2022.109983_b18
  article-title: Pyramid particle swarm optimization with novel strategies of competition and cooperation
  publication-title: Appl. Soft Comput.
  doi: 10.1016/j.asoc.2022.108731
– year: 2020
  ident: 10.1016/j.knosys.2022.109983_b26
– ident: 10.1016/j.knosys.2022.109983_b30
– volume: 70
  start-page: 228
  issue: 2
  year: 2021
  ident: 10.1016/j.knosys.2022.109983_b14
  article-title: A3C-DO: A regional resource scheduling framework based on deep reinforcement learning in edge scenario
  publication-title: IEEE Trans. Comput.
  doi: 10.1109/TC.2020.2987567
– ident: 10.1016/j.knosys.2022.109983_b35
  doi: 10.1145/3487552.3487815
– volume: 125
  start-page: 681
  year: 2017
  ident: 10.1016/j.knosys.2022.109983_b29
  article-title: Review: Multi-objective optimization methods and application in energy saving
  publication-title: Energy
  doi: 10.1016/j.energy.2017.02.174
– volume: 9
  start-page: 4677
  issue: 6
  year: 2022
  ident: 10.1016/j.knosys.2022.109983_b3
  article-title: DoSRA: A decentralized approach to online edge task scheduling and resource allocation
  publication-title: IEEE Internet Things J.
  doi: 10.1109/JIOT.2021.3107431
– start-page: 202
  year: 2007
  ident: 10.1016/j.knosys.2022.109983_b37
  article-title: Generalized cross-validation as a method for choosing a good ridge parameter
– volume: 34
  start-page: 561
  issue: 4
  year: 1992
  ident: 10.1016/j.knosys.2022.109983_b36
  article-title: Analysis of discrete ill-posed problems by means of the L-curve
  publication-title: SIAM Rev.
  doi: 10.1137/1034115
– volume: 40
  start-page: 611
  issue: 2
  year: 2022
  ident: 10.1016/j.knosys.2022.109983_b11
  article-title: Dynacomm: Accelerating distributed CNN training between edges and clouds through dynamic communication scheduling
  publication-title: IEEE J. Sel. Areas Commun.
  doi: 10.1109/JSAC.2021.3118419
– volume: 64
  start-page: 853
  year: 2014
  ident: 10.1016/j.knosys.2022.109983_b28
  article-title: The role of demand response in single and multi-objective wind-thermal generation scheduling: A stochastic programming
  publication-title: Energy
  doi: 10.1016/j.energy.2013.10.034
– year: 2011
  ident: 10.1016/j.knosys.2022.109983_b13
– volume: 27
  start-page: 2.3:1
  year: 2022
  ident: 10.1016/j.knosys.2022.109983_b17
  article-title: Area optimal polygonization using simulated annealing
  publication-title: ACM J. Exp. Algorithmics
  doi: 10.1145/3500911
– ident: 10.1016/j.knosys.2022.109983_b27
  doi: 10.1007/978-3-030-03596-9_15
SSID ssj0002218
Score 2.4346428
Snippet With the increasing popularity of edge computing, service providers are more likely to deploy services at the edge of the network to reduce the latency of...
SourceID crossref
elsevier
SourceType Enrichment Source
Index Database
Publisher
StartPage 109983
SubjectTerms Deep reinforcement learning
Edge computing
Pointer networks
Scheduling algorithm
Title Integrating deep reinforcement learning with pointer networks for service request scheduling in edge computing
URI https://dx.doi.org/10.1016/j.knosys.2022.109983
Volume 258
WOSCitedRecordID wos000880093300012&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: PRVESC
  databaseName: Elsevier SD Freedom Collection Journals 2021
  customDbUrl:
  eissn: 1872-7409
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002218
  issn: 0950-7051
  databaseCode: AIEXJ
  dateStart: 19950201
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1LbxMxELZCyoELb0R5yQdukSOzu67tY0FFFFDFoUiBy8r1zkLayAlpUvXKP2f82mwpKvTAZbVa2bPWzpeZ8ZfxDCEvBYa0LW99Rg0UrEIEM3VUVYy3HEqtykY2obr-R3lwoCYT_Wkw-JnPwpzNpHPq_Fwv_quq8Rkq2x-dvYa6O6H4AO9R6XhFteP1nxS_nwpAeA6gAViMlhCqo9pABOY2EYmBXcx9vYjlyMVs8FCcYXQa7QdODE5jhBtgdEizdPrFE3AhE329ym4vBbcfMj_HvG9sUpXoLmj_-t0EXvbL-se0ywMKyQSvs6DA7Kcc4R5u_f23aB1na9cnKorQM6Xoc5dacCZ5qi-bjG8RC7cn8-n_pot9bS5Z9kgyHI9P3BxXP_YvGG-GXyyk_ZuD69IOc0bbcR2l1F5KHaXcIFuFFFoNydbu_t7kfefOiyKQxN3q8_nLkCR4eTV_jm96McvhXXI7bTbobgTJPTIAd5_cyY08aLLrD4jrYYZ6zNALmKEZM9RjhibM0IwZigNpwgxNmKEbzNCpox4UtMPMQ_L57d7hm3csNeJgFneUK6ZUI6WRWokdy5uqsBqAW6EseksrTAOibIXE0NIqqMwrxUFoAVxCC_jZpCkfkaGbO3hM6I7hxnCQoNujqmmlAsAIySjAbQhGi3KblPnz1TZVqffNUmb1VcrbJqybtYhVWv4yXmbN1CnSjBFkjXC7cuaTa77pKbm1-S08I8PVcg3PyU17tpqeLl8krP0Cd2mnBw
linkProvider Elsevier
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=Integrating+deep+reinforcement+learning+with+pointer+networks+for+service+request+scheduling+in+edge+computing&rft.jtitle=Knowledge-based+systems&rft.au=Zhao%2C+Yuqi&rft.au=Li%2C+Bing&rft.au=Wang%2C+Jian&rft.au=Jiang%2C+Delun&rft.date=2022-12-22&rft.issn=0950-7051&rft.volume=258&rft.spage=109983&rft_id=info:doi/10.1016%2Fj.knosys.2022.109983&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_knosys_2022_109983
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0950-7051&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0950-7051&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0950-7051&client=summon