ENNP: an enhanced neural networks-based power consumption prediction algorithm to deep learning-based workloads on AI-enabled data centers

The traditional power consumption prediction algorithms are no longer suitable for deep learning-based workloads owing to the long-term dependencies and highly volatile nature of power usage in such applications. To address these challenges, this study proposes ENNP, an enhanced neural network-based...

Full description

Saved in:
Bibliographic Details
Published in:Cluster computing Vol. 29; no. 1; p. 36
Main Authors: Wang, Hengdong, Jing, Chao
Format: Journal Article
Language:English
Published: New York Springer US 01.02.2026
Springer Nature B.V
Subjects:
ISSN:1386-7857, 1573-7543
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract The traditional power consumption prediction algorithms are no longer suitable for deep learning-based workloads owing to the long-term dependencies and highly volatile nature of power usage in such applications. To address these challenges, this study proposes ENNP, an enhanced neural network-based power consumption prediction algorithm for deep learning-based workloads in AI-enabled data centers. In general, ENNP inherits the advantages of the TimeMixer framework in mitigating model overfitting. However, direct application of TimeMixer does not provide the flexibility needed to handle complex power consumption patterns. To overcome this limitation, ENNP integrates three key techniques: Bayesian optimization, KAN, and LSTM, to maximize the predictive performance of TimeMixer. Specifically, (1) Bayesian optimization is employed for parameter selection and extraction of multiscale time series; (2) KAN is utilized to reconstruct multiscale time series; and (3) an improved LSTM is adopted to predict on multiscale time series and fusing these predictions to obtain the final prediction. Finally, experiments were conducted on real CPU/GPU servers using trace data collected from various deep learning workloads, including natural language processing, image recognition, multivariable prediction, and anomaly detection jobs. The experimental results show that ENNP achieves the best performance compared with other well-known prediction algorithms such as BP, LSTM, and MLR, as well as recent general time-series prediction models, with a maximum improvement of 38.29% in accuracy.
AbstractList The traditional power consumption prediction algorithms are no longer suitable for deep learning-based workloads owing to the long-term dependencies and highly volatile nature of power usage in such applications. To address these challenges, this study proposes ENNP, an enhanced neural network-based power consumption prediction algorithm for deep learning-based workloads in AI-enabled data centers. In general, ENNP inherits the advantages of the TimeMixer framework in mitigating model overfitting. However, direct application of TimeMixer does not provide the flexibility needed to handle complex power consumption patterns. To overcome this limitation, ENNP integrates three key techniques: Bayesian optimization, KAN, and LSTM, to maximize the predictive performance of TimeMixer. Specifically, (1) Bayesian optimization is employed for parameter selection and extraction of multiscale time series; (2) KAN is utilized to reconstruct multiscale time series; and (3) an improved LSTM is adopted to predict on multiscale time series and fusing these predictions to obtain the final prediction. Finally, experiments were conducted on real CPU/GPU servers using trace data collected from various deep learning workloads, including natural language processing, image recognition, multivariable prediction, and anomaly detection jobs. The experimental results show that ENNP achieves the best performance compared with other well-known prediction algorithms such as BP, LSTM, and MLR, as well as recent general time-series prediction models, with a maximum improvement of 38.29% in accuracy.
ArticleNumber 36
Author Jing, Chao
Wang, Hengdong
Author_xml – sequence: 1
  givenname: Hengdong
  surname: Wang
  fullname: Wang, Hengdong
  organization: School of Computer Science and Engineering, Guilin University of Technology
– sequence: 2
  givenname: Chao
  surname: Jing
  fullname: Jing, Chao
  email: jingchao@glut.edu.cn
  organization: School of Computer Science and Engineering, Guilin University of Technology, Guangxi Key Laboratory of Embedded Technology and Intelligent System, Guilin University of Technology
BookMark eNp9UM1KxDAYDKLg-vMCngKeo0nTbFpvy-LPwqIe9BzS5OvatZvUpKX4Cj610S548zTDfDPzwZygQ-cdIHTB6BWjVF5HRkUxJzQTJJGckvEAzZiQnEiR88PEeTrLQshjdBLjllJayqycoa_bx8fnG6wdBvemnQGLHQxBtwn60Yf3SCodk9r5EQI23sVh1_WNd7gLYBvzS3W78aHp33a499gCdLgFHVzjNvv0T1PrtY04uRcrAk5XbdKt7jU24HoI8Qwd1bqNcL7HU_R6d_uyfCDrp_vVcrEmhhVyJCA4t1zOLa2oqAth5sKCoaWVugJmQMqSZbllsrBVyfOqkLzktsrAFGUpa85P0eXU2wX_MUDs1dYPwaWXimeS81zQQiRXNrlM8DEGqFUXmp0On4pR9bO5mjZXaXP1u7kaU4hPoZjMbgPhr_qf1Dfnnok4
Cites_doi 10.1109/CVPR.2016.90
10.1109/MCI.2021.3084416
10.1016/j.eswa.2022.117892
10.1609/aaai.v35i12.17325
10.1016/j.eswa.2022.117176
10.1016/j.renene.2023.119706
10.1016/j.ins.2020.09.033
10.1007/s10723-023-09642-5
10.1016/j.jpdc.2022.05.005
10.1016/j.eswa.2024.123325
10.1007/s00607-020-00819-4
10.11591/ijece.v10i2.pp1524-1532
10.1016/j.eswa.2023.122012
10.1109/ACCESS.2021.3125092
10.1016/j.future.2021.10.019
10.1007/s10586-022-03959-8
10.1109/TSUSC.2019.2910129
10.1109/TCC.2017.2737624
10.14778/3665844.3665863
10.1007/s10796-016-9683-5
10.1016/j.eswa.2023.123078
10.1162/neco.1997.9.8.1735
10.1016/j.apenergy.2020.114806
10.1038/s41598-024-68339-1
10.1007/s12652-020-01711-x
ContentType Journal Article
Copyright The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025 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 Science+Business Media, LLC, part of Springer Nature 2025.
Copyright_xml – notice: The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025 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 Science+Business Media, LLC, part of Springer Nature 2025.
DBID AAYXX
CITATION
JQ2
DOI 10.1007/s10586-025-05840-w
DatabaseName CrossRef
ProQuest Computer Science Collection
DatabaseTitle CrossRef
ProQuest Computer Science Collection
DatabaseTitleList
ProQuest Computer Science Collection
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
EISSN 1573-7543
ExternalDocumentID 10_1007_s10586_025_05840_w
GrantInformation_xml – fundername: Guangxi Key Research and Development Program
  grantid: GUIKEAB23075116
  funderid: https://doi.org/10.13039/501100017691
– fundername: Guangxi Provincial Natural Science Foundation
  grantid: No.2020GXNSFAA159038
– fundername: Guangxi Science and Technology Major Program
  grantid: GUIKEAA 24263034
– fundername: National Natural Science Foundation of China
  grantid: No.62362018
GroupedDBID -~C
.86
.DC
.VR
06D
0R~
0VY
1N0
203
29B
2J2
2JN
2JY
2KG
2LR
2~H
30V
4.4
406
408
409
40D
40E
5GY
5VS
67Z
6NX
78A
8TC
8UJ
95-
95.
95~
96X
AAAVM
AABHQ
AACDK
AAHNG
AAJBT
AAJKR
AANZL
AAPKM
AARTL
AASML
AATNV
AATVU
AAUYE
AAWCG
AAYIU
AAYQN
ABAKF
ABBBX
ABBRH
ABBXA
ABDBE
ABDZT
ABECU
ABFTD
ABFTV
ABHLI
ABHQN
ABJNI
ABJOX
ABKCH
ABKTR
ABMNI
ABMQK
ABNWP
ABQBU
ABRTQ
ABSXP
ABTEG
ABTHY
ABTKH
ABTMW
ABWNU
ABXPI
ACAOD
ACDTI
ACGFS
ACHSB
ACHXU
ACKNC
ACMDZ
ACMLO
ACOKC
ACOMO
ACPIV
ACSNA
ACZOJ
ADHHG
ADHIR
ADKFA
ADKNI
ADKPE
ADRFC
ADTPH
ADURQ
ADYFF
ADZKW
AEFQL
AEGAL
AEGNC
AEJHL
AEJRE
AEMSY
AEOHA
AEPYU
AETLH
AEVLU
AEXYK
AFDZB
AFLOW
AFOHR
AFQWF
AFWTZ
AFZKB
AGAYW
AGDGC
AGJBK
AGMZJ
AGQEE
AGQMX
AGRTI
AGWIL
AGWZB
AGYKE
AHAVH
AHBYD
AHKAY
AHPBZ
AHYZX
AIAKS
AIGIU
AIIXL
AILAN
AITGF
AJRNO
AJZVZ
ALMA_UNASSIGNED_HOLDINGS
ALWAN
AMKLP
AMXSW
AMYLF
AMYQR
AOCGG
ARMRJ
ASPBG
ATHPR
AVWKF
AXYYD
AYFIA
AYJHY
AZFZN
B-.
BA0
BSONS
CS3
CSCUP
DDRTE
DL5
DNIVK
DPUIP
EBLON
EBS
EIOEI
ESBYG
FEDTE
FERAY
FFXSO
FIGPU
FNLPD
FRRFC
FWDCC
GGCAI
GGRSB
GJIRD
GNWQR
GQ7
GQ8
GXS
HF~
HG5
HG6
HMJXF
HQYDN
HRMNR
HVGLF
I09
IJ-
IKXTQ
IWAJR
IXC
IXD
IXE
IZIGR
IZQ
I~X
I~Z
J-C
J0Z
JBSCW
JCJTX
JZLTJ
KDC
KOV
LAK
LLZTM
MA-
NB0
NPVJJ
NQJWS
O93
O9J
OAM
P9O
PF0
PT4
PT5
QOS
R89
R9I
RNS
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
W23
W48
WK8
YLTOR
Z45
ZMTXR
~A9
-Y2
1SB
2P1
2VQ
AAIAL
AARHV
AAYTO
AAYXX
ABQSL
ABULA
ACBXY
ADHKG
AEBTG
AEKMD
AFFHD
AFGCZ
AFKRA
AGGDS
AGQPQ
AHSBF
AJBLW
ARAPS
BDATZ
BENPR
BGLVJ
BGNMA
CAG
CCPQU
CITATION
COF
EJD
FINBP
FSGXE
H13
HCIFZ
HZ~
IHE
K7-
M4Y
N2Q
NU0
O9-
OVD
PHGZM
PHGZT
PQGLB
RNI
RZC
RZE
RZK
TEORI
JQ2
ID FETCH-LOGICAL-c187w-e533d376d0b05f85c65dec09d7abe1ce779124d178db934b87393db2ec8997f33
IEDL.DBID RSV
ISSN 1386-7857
IngestDate Wed Nov 26 14:41:37 EST 2025
Thu Nov 27 00:31:25 EST 2025
Thu Nov 20 01:10:34 EST 2025
IsPeerReviewed true
IsScholarly true
Issue 1
Keywords Power consumption prediction
KAN
AI-enabled data centers
TimeMixer
LSTM
Bayesian optimization
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c187w-e533d376d0b05f85c65dec09d7abe1ce779124d178db934b87393db2ec8997f33
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
PQID 3273345085
PQPubID 2043865
ParticipantIDs proquest_journals_3273345085
crossref_primary_10_1007_s10586_025_05840_w
springer_journals_10_1007_s10586_025_05840_w
PublicationCentury 2000
PublicationDate 2026-02-01
PublicationDateYYYYMMDD 2026-02-01
PublicationDate_xml – month: 02
  year: 2026
  text: 2026-02-01
  day: 01
PublicationDecade 2020
PublicationPlace New York
PublicationPlace_xml – name: New York
– name: Dordrecht
PublicationSubtitle The Journal of Networks, Software Tools and Applications
PublicationTitle Cluster computing
PublicationTitleAbbrev Cluster Comput
PublicationYear 2026
Publisher Springer US
Springer Nature B.V
Publisher_xml – name: Springer US
– name: Springer Nature B.V
References 5840_CR5
J-T Hong (5840_CR25) 2024; 247
5840_CR34
G-F Fan (5840_CR2) 2024; 238
5840_CR19
5840_CR18
5840_CR17
5840_CR39
A Vaswani (5840_CR31) 2017; 30
X Fu (5840_CR10) 2017; 8
T Deepika (5840_CR9) 2020; 10
KMU Ahmed (5840_CR7) 2021; 9
T Khan (5840_CR13) 2022; 128
J Ji (5840_CR33) 2021; 16
SK Panda (5840_CR37) 2020; 11
5840_CR30
W Lin (5840_CR12) 2023
5840_CR26
5840_CR47
5840_CR46
5840_CR45
C Jing (5840_CR16) 2024; 27
5840_CR29
5840_CR28
H Zhao (5840_CR24) 2024; 220
5840_CR27
C Jin (5840_CR8) 2020; 265
Y Chen (5840_CR1) 2024; 245
X Huo (5840_CR3) 2022; 201
S Hochreiter (5840_CR32) 1997; 9
X Qiu (5840_CR23) 2024; 17
Z Zhou (5840_CR36) 2022; 167
SK Panda (5840_CR35) 2018; 20
W Lin (5840_CR6) 2019; 5
A Tarafdar (5840_CR15) 2023; 21
H Zhang (5840_CR14) 2024; 14
H Wu (5840_CR38) 2021; 34
W Lin (5840_CR11) 2021; 547
5840_CR40
5840_CR22
5840_CR44
5840_CR21
5840_CR43
Z Ji (5840_CR4) 2022; 206
5840_CR20
5840_CR42
5840_CR41
References_xml – ident: 5840_CR19
– ident: 5840_CR44
– ident: 5840_CR22
  doi: 10.1109/CVPR.2016.90
– volume: 16
  start-page: 50
  issue: 3
  year: 2021
  ident: 5840_CR33
  publication-title: IEEE Comput. Intell. Mag.
  doi: 10.1109/MCI.2021.3084416
– volume: 206
  year: 2022
  ident: 5840_CR4
  publication-title: Expert Syst. Appl.
  doi: 10.1016/j.eswa.2022.117892
– ident: 5840_CR46
– ident: 5840_CR26
  doi: 10.1609/aaai.v35i12.17325
– volume: 201
  year: 2022
  ident: 5840_CR3
  publication-title: Expert Syst. Appl.
  doi: 10.1016/j.eswa.2022.117176
– ident: 5840_CR27
– volume: 220
  year: 2024
  ident: 5840_CR24
  publication-title: Renewable Energy
  doi: 10.1016/j.renene.2023.119706
– volume: 547
  start-page: 1045
  year: 2021
  ident: 5840_CR11
  publication-title: Inf. Sci.
  doi: 10.1016/j.ins.2020.09.033
– ident: 5840_CR42
– volume: 21
  issue: 1
  year: 2023
  ident: 5840_CR15
  publication-title: Journal of Grid Computing
  doi: 10.1007/s10723-023-09642-5
– ident: 5840_CR21
– volume: 167
  start-page: 211
  year: 2022
  ident: 5840_CR36
  publication-title: J. Parallel Distrib. Comput.
  doi: 10.1016/j.jpdc.2022.05.005
– ident: 5840_CR40
– ident: 5840_CR5
– volume: 247
  year: 2024
  ident: 5840_CR25
  publication-title: Expert Systems with Applications
  doi: 10.1016/j.eswa.2024.123325
– year: 2023
  ident: 5840_CR12
  publication-title: Computing
  doi: 10.1007/s00607-020-00819-4
– ident: 5840_CR39
– volume: 10
  start-page: 1524
  issue: 2
  year: 2020
  ident: 5840_CR9
  publication-title: Int. J. Electr. Comput. Eng. (IJECE)
  doi: 10.11591/ijece.v10i2.pp1524-1532
– volume: 238
  year: 2024
  ident: 5840_CR2
  publication-title: Expert Systems with Applications
  doi: 10.1016/j.eswa.2023.122012
– ident: 5840_CR20
– ident: 5840_CR18
– ident: 5840_CR43
– ident: 5840_CR45
– volume: 9
  start-page: 152536
  year: 2021
  ident: 5840_CR7
  publication-title: IEEE Access
  doi: 10.1109/ACCESS.2021.3125092
– volume: 34
  start-page: 22419
  year: 2021
  ident: 5840_CR38
  publication-title: Adv. Neural. Inf. Process. Syst.
– volume: 128
  start-page: 320
  year: 2022
  ident: 5840_CR13
  publication-title: Futur. Gener. Comput. Syst.
  doi: 10.1016/j.future.2021.10.019
– ident: 5840_CR47
– ident: 5840_CR28
– ident: 5840_CR41
– volume: 27
  start-page: 377
  issue: 1
  year: 2024
  ident: 5840_CR16
  publication-title: Cluster Computing
  doi: 10.1007/s10586-022-03959-8
– volume: 5
  start-page: 329
  issue: 3
  year: 2019
  ident: 5840_CR6
  publication-title: IEEE Trans. Sustain. Comput.
  doi: 10.1109/TSUSC.2019.2910129
– volume: 8
  start-page: 246
  issue: 1
  year: 2017
  ident: 5840_CR10
  publication-title: IEEE Trans. Cloud Comput.
  doi: 10.1109/TCC.2017.2737624
– volume: 17
  start-page: 2363
  year: 2024
  ident: 5840_CR23
  publication-title: Proc. VLDB Endow.
  doi: 10.14778/3665844.3665863
– ident: 5840_CR29
– volume: 30
  start-page: I
  year: 2017
  ident: 5840_CR31
  publication-title: Adv. Neural Inf. Process. Syst.
– volume: 20
  start-page: 373
  year: 2018
  ident: 5840_CR35
  publication-title: Inf. Syst. Front.
  doi: 10.1007/s10796-016-9683-5
– volume: 245
  year: 2024
  ident: 5840_CR1
  publication-title: Expert Systems with Applications
  doi: 10.1016/j.eswa.2023.123078
– volume: 9
  start-page: 1735
  issue: 8
  year: 1997
  ident: 5840_CR32
  publication-title: Neural Comput.
  doi: 10.1162/neco.1997.9.8.1735
– volume: 265
  year: 2020
  ident: 5840_CR8
  publication-title: Appl. Energy
  doi: 10.1016/j.apenergy.2020.114806
– volume: 14
  issue: 1
  year: 2024
  ident: 5840_CR14
  publication-title: Sci. Rep.
  doi: 10.1038/s41598-024-68339-1
– ident: 5840_CR17
– ident: 5840_CR34
– ident: 5840_CR30
– volume: 11
  start-page: 4643
  year: 2020
  ident: 5840_CR37
  publication-title: Journal of Ambient Intelligence and Humanized Computing
  doi: 10.1007/s12652-020-01711-x
SSID ssj0009729
Score 2.3744223
Snippet The traditional power consumption prediction algorithms are no longer suitable for deep learning-based workloads owing to the long-term dependencies and highly...
SourceID proquest
crossref
springer
SourceType Aggregation Database
Index Database
Publisher
StartPage 36
SubjectTerms Accuracy
Algorithms
Anomalies
Bayesian analysis
Computer centers
Computer Communication Networks
Computer Science
Data centers
Deep learning
Machine learning
Natural language processing
Neural networks
Operating Systems
Optimization
Power consumption
Prediction models
Processor Architectures
Time series
Workload
Workloads
Title ENNP: an enhanced neural networks-based power consumption prediction algorithm to deep learning-based workloads on AI-enabled data centers
URI https://link.springer.com/article/10.1007/s10586-025-05840-w
https://www.proquest.com/docview/3273345085
Volume 29
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVAVX
  databaseName: SpringerLINK Contemporary 1997-Present
  customDbUrl:
  eissn: 1573-7543
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0009729
  issn: 1386-7857
  databaseCode: RSV
  dateStart: 19980101
  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/eLvHCXMwnV1bS8MwFA46ffDFecXplDz4poE2bZbUtyEbClKGl7G3kls3YbZjne4_-KtNspaq6IO-BXISQm7nC_nO-QA4lxHmxOcpwpISFEqPIxFxgTiOQo9LgrmTexve0Thmo1E0KIPCiortXn1Jupv6U7AbYZYwS5AphB5aroMN4-6YFWy4fxjWqXap0ybzA2NNGaFlqMzPfXx1RzXG_PYt6rxNv_m_ce6A7RJdwu5qO-yCNZ3tgWal3ADLg7wP3ntxPLiCPIM6mzgOALSJLU3TbEULL5B1bwrOrIgalC5O010ucDa3XzuuyKfjfP68mLzARQ6V1jNYalCMy9a2p2nOVQGNdfcWaReopaClpUJLCzXY8wA89XuP1zeoVGVA0md0ibQBiMpcS8oTHkkZkR2itPQiRbnQvtSURgYzKJ8yJaIgFMzm3FMCa2medjQNgkPQyPJMHwHYUSGmUepLYx_6TNj61BMdzrHPPaxb4KJanGS2Sr6R1GmW7TQnZpoTN83JsgXa1fol5UEsksDAsyA0KJS0wGW1XnX1770d_838BGxh85xd8bnboLGYv-pTsCnfFs_F_Mxt0A8-y-Nt
linkProvider Springer Nature
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LSwMxEB58gV6sT6xWzcGbBnazm2bXW5GKYl3EF96WvLYt6LZ0q_0P_mqTdJeq6EFvgUxCmCQzX8g3MwBHMiac-jzDRDKKQ-lxLGIuMCdx6HFJCXfl3h47LEmip6f4pgwKKyq2e_Ul6Sz1p2A3GlnCLMWmEXp4Mg-LofFYNmP-7d3jLNUuc7XJ_MBIs4iyMlTm5zm-uqMZxvz2Leq8zXntf-tcg9USXaLW9Disw5zON6BWVW5A5UXehPd2ktycIp4jnfccBwDZxJZmaD6lhRfYujeFhraIGpIuTtMZFzQc2a8d1-TP3cGoP-69oPEAKa2HqKxB0S1H25meB1wVyEi3LrF2gVoKWVoqsrRQgz234OG8fX92gcuqDFj6EZtgbQCiMmZJecKjWURlkyotvVgxLrQvNWOxwQzKZ5EScRCKyObcU4JoaZ52LAuCbVjIB7neAdRUIWFx5ksjH_qRsP2ZJ5qcE597RNfhuNqcdDhNvpHO0ixbNadGzalTczqpQ6Pav7S8iEUaGHgWhAaF0jqcVPs16_59tt2_iR_C8sX9dSftXCZXe7BCzNN2yu1uwMJ49Kr3YUm-jfvF6MAd1g_wkOZR
linkToPdf http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LS8QwEB58IV5cn7i6ag7eNNimzab1JuqiKGXBB95KXlVBu2W3uv_BX22StqyKHsRbIJMQMnl8w3wzA7AnY8KpzzNMJKM4lB7HIuYCcxKHHpeUcFfu7e6KJUl0fx_3P0XxO7Z745KsYhpslqa8PCxUdvgp8I1GljxLsWmEHh5Pw2xoifTWXr--m6TdZa5OmR8YaRZRVofN_DzH169pgje_uUjdz9Nr_X_NS7BYo050XB2TZZjS-Qq0mooOqL7gq_B-liT9I8RzpPNHxw1ANuGlGZpXdPERtt-eQoUtroaki990jw4qhtbl45r8-WEwfCofX1A5QErrAtW1KR7q0Xam5wFXI2Skjy-wdgFcClm6KrJ0UYNJ1-C2d3Zzco7rag1Y-hEbY22AozLPlfKER7OIyi5VWnqxYlxoX2rGYoMllM8iJeIgFJHNxacE0dKYfCwLgnWYyQe53gDUVSFhceZLIx_6kbD9mSe6nBOfe0S3Yb9RVFpUSTnSSfplu82p2ebUbXM6bkOn0WVaX9BRGhjYFoQGndI2HDS6m3T_Ptvm38R3Yb5_2kuvLpLLLVggxuKtKN8dmCmHr3ob5uRb-TQa7rhz-wGZ5u81
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=ENNP%3A+an+enhanced+neural+networks-based+power+consumption+prediction+algorithm+to+deep+learning-based+workloads+on+AI-enabled+data+centers&rft.jtitle=Cluster+computing&rft.au=Wang%2C+Hengdong&rft.au=Jing%2C+Chao&rft.date=2026-02-01&rft.pub=Springer+US&rft.issn=1386-7857&rft.eissn=1573-7543&rft.volume=29&rft.issue=1&rft_id=info:doi/10.1007%2Fs10586-025-05840-w&rft.externalDocID=10_1007_s10586_025_05840_w
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1386-7857&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1386-7857&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1386-7857&client=summon