NFVLearn: A multi‐resource, long short‐term memory‐based virtual network function resource usage prediction architecture

Virtual resource load prediction in network function virtualization (NFV) is the subject of intense research due to its crucial role in enabling proactive resource adaptation in dynamic NFV environments whose resource demand constantly changes. Several long short‐term memory (LSTM)‐based approaches...

Full description

Saved in:
Bibliographic Details
Published in:Software, practice & experience Vol. 53; no. 3; pp. 555 - 578
Main Authors: St‐Onge, Cédric, Kara, Nadjia, Edstrom, Claes
Format: Journal Article
Language:English
Published: Bognor Regis Wiley Subscription Services, Inc 01.03.2023
Subjects:
ISSN:0038-0644, 1097-024X
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Virtual resource load prediction in network function virtualization (NFV) is the subject of intense research due to its crucial role in enabling proactive resource adaptation in dynamic NFV environments whose resource demand constantly changes. Several long short‐term memory (LSTM)‐based approaches have been proposed to forecast the resource load of multiple resource attributes of a virtual network function (VNF) in a service function chain (SFC). In this article, we present NFVLearn, a flexible multivariate, many‐to‐many LSTM‐based model which uses different types of resource load history (CPU, memory, I/O bandwidth) from various VNFs of an SFC to predict future loads of multiple resources of a VNF. We then compare four novel automated input selection frameworks for NFVLearn. Simulations on those frameworks based on graph neural networks, Pearson correlation coefficient, Spearman rank correlation coefficient, and Kendall rank correlation coefficient demonstrate that models using lesser, highly correlated input features retain high prediction root mean squared error accuracy and coefficients of determination scores by leveraging resource attribute inter‐dependencies from the SFC. Those results show that resource attribute interdependency‐based input feature selection frameworks can reduce overhead in the control plane while keeping high accuracy and high fidelity resource load prediction of multiple resource attributes.
AbstractList Virtual resource load prediction in network function virtualization (NFV) is the subject of intense research due to its crucial role in enabling proactive resource adaptation in dynamic NFV environments whose resource demand constantly changes. Several long short‐term memory (LSTM)‐based approaches have been proposed to forecast the resource load of multiple resource attributes of a virtual network function (VNF) in a service function chain (SFC). In this article, we present NFVLearn, a flexible multivariate, many‐to‐many LSTM‐based model which uses different types of resource load history (CPU, memory, I/O bandwidth) from various VNFs of an SFC to predict future loads of multiple resources of a VNF. We then compare four novel automated input selection frameworks for NFVLearn. Simulations on those frameworks based on graph neural networks, Pearson correlation coefficient, Spearman rank correlation coefficient, and Kendall rank correlation coefficient demonstrate that models using lesser, highly correlated input features retain high prediction root mean squared error accuracy and coefficients of determination scores by leveraging resource attribute inter‐dependencies from the SFC. Those results show that resource attribute interdependency‐based input feature selection frameworks can reduce overhead in the control plane while keeping high accuracy and high fidelity resource load prediction of multiple resource attributes.
Author St‐Onge, Cédric
Edstrom, Claes
Kara, Nadjia
Author_xml – sequence: 1
  givenname: Cédric
  orcidid: 0000-0003-0759-4270
  surname: St‐Onge
  fullname: St‐Onge, Cédric
  email: cedric.st-onge.1@ens.etsmtl.ca
  organization: Université du Québec
– sequence: 2
  givenname: Nadjia
  surname: Kara
  fullname: Kara, Nadjia
  organization: Université du Québec
– sequence: 3
  givenname: Claes
  surname: Edstrom
  fullname: Edstrom, Claes
  organization: Ericsson Canada
BookMark eNp1kM9O3DAQxq0KpC5_pD6CpV44NMvYTrJJbwgttNIKkGhRb5HjjMGQxMvYAe2l4hF4Rp6kWbZcKnoazTe_-Wb07bCt3vfI2CcBUwEgD8MSp0rk8IFNBJSzBGT6a4tNAFSRQJ6mH9lOCLcAQmQyn7DfZydXC9TUf-VHvBva6F6engmDH8jgF976_pqHG09xlCNSxzvsPK3GrtYBG_7gKA665T3GR0933A69ic73_M2DD0FfI18SNm4z0WRuXEQTB8I9tm11G3D_b91lP0_mP46_JYvz0-_HR4vEyFJBIowEsAUYKLVVtTVZo1Q9ikKVeWZskTVapqkySpRNrY0w1tag7Ky0mVGlULvs88Z3Sf5-wBCr2_G7fjxZydlMFkWeSzlS0w1lyIdAaCvjol4_HUm7thJQrTOuxoyrdcbjwsE_C0tynabVe2iyQR9di6v_ctXlxfyV_wPfu5LA
CitedBy_id crossref_primary_10_1109_TNSM_2024_3403714
crossref_primary_10_1007_s11227_023_05283_3
Cites_doi 10.1007/s10922‐021‐09629‐1
10.1109/BigData.2017.8258087
10.1016/j.aiopen.2021.01.001
10.1016/j.eneco.2019.05.026
10.1016/j.comnet.2019.05.004
10.1016/j.jmva.2021.104798
10.1162/neco.1997.9.8.1735
10.1109/ICTC49870.2020.9289275
10.1109/ANTS47819.2019.9118065
10.1109/ACCESS.2018.2825538
10.1109/ICSPCS50536.2020.9310033
10.1155/2021/6032325
10.1109/TNSM.2020.3015244
10.1016/j.comnet.2021.108104
10.1109/NOMS.2014.6838258
10.1109/NetSoft48620.2020.9165449
10.1109/TNSM.2017.2666781
10.1016/j.future.2019.09.018
10.1109/COMST.2019.2904897
10.1109/NETSOFT.2019.8806620
10.1002/spe.2635
10.3390/fi12110196
10.1587/transinf.2020NTP0010
ContentType Journal Article
Copyright 2022 John Wiley & Sons Ltd.
2023 John Wiley & Sons, Ltd.
Copyright_xml – notice: 2022 John Wiley & Sons Ltd.
– notice: 2023 John Wiley & Sons, Ltd.
DBID AAYXX
CITATION
7SC
8FD
F28
FR3
JQ2
L7M
L~C
L~D
DOI 10.1002/spe.3160
DatabaseName CrossRef
Computer and Information Systems Abstracts
Technology Research Database
ANTE: Abstracts in New Technology & Engineering
Engineering 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
ProQuest Computer Science Collection
Computer and Information Systems Abstracts
Engineering Research Database
Advanced Technologies Database with Aerospace
ANTE: Abstracts in New Technology & Engineering
Computer and Information Systems Abstracts Professional
DatabaseTitleList
CrossRef
Technology Research Database
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
EISSN 1097-024X
EndPage 578
ExternalDocumentID 10_1002_spe_3160
SPE3160
Genre article
GrantInformation_xml – fundername: Natural Sciences and Engineering Research Council of Canada
  funderid: 492183
GroupedDBID -~X
.3N
.4S
.DC
.GA
.Y3
05W
0R~
10A
123
1L6
1OB
1OC
31~
33P
3EH
3R3
3SF
3WU
4.4
4ZD
50Y
50Z
51W
51X
52M
52N
52O
52P
52S
52T
52U
52W
52X
5VS
66C
702
7PT
8-0
8-1
8-3
8-4
8-5
85S
8UM
8WZ
930
9M8
A03
A6W
AAESR
AAEVG
AAHHS
AAHQN
AAMNL
AANHP
AANLZ
AAONW
AASGY
AAXRX
AAYCA
AAZKR
ABCQN
ABCUV
ABDPE
ABEFU
ABEML
ABIJN
ABLJU
ABTAH
ACAHQ
ACBWZ
ACCFJ
ACCZN
ACFBH
ACGFS
ACIWK
ACNCT
ACPOU
ACRPL
ACSCC
ACXBN
ACXQS
ACYXJ
ADBBV
ADEOM
ADIZJ
ADKYN
ADMGS
ADMXK
ADNMO
ADOZA
ADXAS
ADZMN
AEEZP
AEIGN
AEIMD
AENEX
AEQDE
AEUQT
AEUYR
AFBPY
AFFPM
AFGKR
AFPWT
AFWVQ
AFZJQ
AHBTC
AITYG
AIURR
AIWBW
AJBDE
AJXKR
ALAGY
ALMA_UNASSIGNED_HOLDINGS
ALUQN
ALVPJ
AMBMR
AMYDB
ARCSS
ASPBG
ATUGU
AUFTA
AVWKF
AZBYB
AZFZN
AZVAB
BAFTC
BDRZF
BFHJK
BHBCM
BMNLL
BNHUX
BROTX
BRXPI
BY8
CS3
CWDTD
D-E
D-F
D0L
DCZOG
DPXWK
DR2
DRFUL
DRSTM
DU5
EBS
EJD
F00
F01
F04
FEDTE
G-S
G.N
GNP
GODZA
H.T
H.X
HBH
HF~
HGLYW
HHY
HVGLF
HZ~
IX1
J0M
JPC
KQQ
LATKE
LAW
LC2
LC3
LEEKS
LH4
LITHE
LOXES
LP6
LP7
LUTES
LW6
LYRES
M61
MEWTI
MK4
MRFUL
MRSTM
MSFUL
MSSTM
MXFUL
MXSTM
N04
N05
N9A
NF~
NNB
O66
O9-
OIG
P2P
P2W
P2X
P4D
PALCI
PQQKQ
PZZ
Q.N
Q11
QB0
QRW
R.K
RIWAO
RJQFR
ROL
RWI
RX1
RXW
RYL
S10
SAMSI
SUPJJ
TAE
TUS
TWZ
UB1
V2E
W8V
W99
WBKPD
WH7
WIB
WIH
WIK
WOHZO
WQJ
WRC
WWW
WXSBR
WYISQ
WZISG
XG1
XPP
XV2
YYP
ZCA
ZY4
ZZTAW
~02
~IA
~WT
AAMMB
AAYXX
ABUFD
ADMLS
AEFGJ
AEYWJ
AGHNM
AGQPQ
AGXDD
AGYGG
AIDQK
AIDYY
AIQQE
CITATION
O8X
7SC
8FD
F28
FR3
JQ2
L7M
L~C
L~D
ID FETCH-LOGICAL-c2930-1c200f80c09af3bfc5d33bc2013965cf85da2443c319dbac1cffb03f79f5c3913
IEDL.DBID DRFUL
ISICitedReferencesCount 2
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000877540300001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0038-0644
IngestDate Fri Jul 25 12:14:03 EDT 2025
Sat Nov 29 04:02:38 EST 2025
Tue Nov 18 21:55:23 EST 2025
Wed Jan 22 16:24:14 EST 2025
IsPeerReviewed true
IsScholarly true
Issue 3
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c2930-1c200f80c09af3bfc5d33bc2013965cf85da2443c319dbac1cffb03f79f5c3913
Notes Funding information
Natural Sciences and Engineering Research Council of Canada, Grant/Award Number: 492183
ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0003-0759-4270
PQID 2772886622
PQPubID 1046349
PageCount 24
ParticipantIDs proquest_journals_2772886622
crossref_citationtrail_10_1002_spe_3160
crossref_primary_10_1002_spe_3160
wiley_primary_10_1002_spe_3160_SPE3160
PublicationCentury 2000
PublicationDate March 2023
2023-03-00
20230301
PublicationDateYYYYMMDD 2023-03-01
PublicationDate_xml – month: 03
  year: 2023
  text: March 2023
PublicationDecade 2020
PublicationPlace Bognor Regis
PublicationPlace_xml – name: Bognor Regis
PublicationSubtitle Practice & Experience
PublicationTitle Software, practice & experience
PublicationYear 2023
Publisher Wiley Subscription Services, Inc
Publisher_xml – name: Wiley Subscription Services, Inc
References 2018; 6
2016; 1
2019; 81
2020; 1
2017; 14
2021
2020
2019; 21
2021; 18
2021; 193
2019; 49
2021; E104.D
2019
2022; 30
2021; 186
2020; 12
2020; 102
2019; 161
1997; 9
2021; 2021
e_1_2_12_4_1
e_1_2_12_3_1
e_1_2_12_6_1
e_1_2_12_5_1
e_1_2_12_19_1
e_1_2_12_18_1
e_1_2_12_17_1
e_1_2_12_16_1
e_1_2_12_20_1
e_1_2_12_21_1
e_1_2_12_22_1
e_1_2_12_23_1
e_1_2_12_24_1
e_1_2_12_25_1
e_1_2_12_26_1
Boutaba R (e_1_2_12_2_1) 2021
e_1_2_12_15_1
e_1_2_12_14_1
e_1_2_12_13_1
e_1_2_12_12_1
e_1_2_12_8_1
e_1_2_12_11_1
e_1_2_12_7_1
e_1_2_12_10_1
e_1_2_12_9_1
References_xml – volume: 9
  start-page: 1735
  issue: 8
  year: 1997
  end-page: 1780
  article-title: Ltsm
  publication-title: Neural Comput
– start-page: 344
  year: 2020
  end-page: 346
– volume: 1
  start-page: 1
  year: 2016
  end-page: 20
– volume: 6
  start-page: 23 551
  year: 2018
  end-page: 23 560
  article-title: LSTM‐based analysis of industrial IoT equipment
  publication-title: IEEE Access
– volume: 193
  issue: September
  year: 2021
  article-title: Application of a Long Short Term Memory neural predictor with asymmetric loss function for the resource allocation in NFV network architectures
  publication-title: Comput Netw
– volume: 14
  start-page: 106
  issue: 1
  year: 2017
  end-page: 120
  article-title: Topology‐aware prediction of virtual network function resource requirements
  publication-title: IEEE Trans Netw Serv Manag
– volume: 12
  start-page: 1
  issue: 11
  year: 2020
  end-page: 13
  article-title: Proposal and investigation of an artificial intelligence (Ai)‐based cloud resource allocation algorithm in network function virtualization architectures
  publication-title: Future Internet
– volume: 1
  start-page: 57
  year: 2020
  end-page: 81
  article-title: Graph neural networks: a review of methods and applications
  publication-title: AI Open
– start-page: 1
  year: 2019
  end-page: 6
– volume: 186
  year: 2021
  article-title: Ordinal pattern dependence as a multivariate dependence measure
  publication-title: J Multivar Anal
– start-page: 272
  end-page: 276
– volume: 161
  start-page: 251
  year: 2019
  end-page: 263
  article-title: VNE‐TD: a virtual network embedding algorithm based on temporal‐difference learning
  publication-title: Comput Netw
– year: 2020
– start-page: 33
  year: 2021
  end-page: 68
  article-title: Managing virtualized networks and services with machine learning
  publication-title: Commun Netw Serv Manag Era Artif Intell Mach Learn
– volume: 2021
  year: 2021
  article-title: Determinants of commodity futures prices: decomposition approach
  publication-title: Math Probl Eng
– volume: 18
  start-page: 1476
  issue: 2
  year: 2021
  end-page: 1490
  article-title: A network intelligence architecture for efficient VNF lifecycle management
  publication-title: IEEE Trans Netw Serv Manag
– volume: 102
  start-page: 738
  year: 2020
  end-page: 745
  article-title: A new optimization algorithm for non‐stationary time series prediction based on recurrent neural networks
  publication-title: Futur Gener Comput Syst
– volume: 49
  start-page: 617
  issue: 4
  year: 2019
  end-page: 639
  article-title: A multitime‐steps‐ahead prediction approach for scheduling live migration in cloud data centers
  publication-title: Softw Pract Exp
– volume: E104.D
  start-page: 606
  issue: 5
  year: 2021
  end-page: 616
  article-title: Sparse regression model‐based relearning architecture for shortening learning time in traffic prediction
  publication-title: IEICE Trans Inf Syst
– volume: 30
  issue: 1
  year: 2022
  article-title: Comparison of machine learning techniques for VNF resource requirements prediction in NFV
  publication-title: J Netw Syst Manag
– volume: 21
  start-page: 2224
  issue: 3
  year: 2019
  end-page: 2287
  article-title: Deep learning in mobile and wireless networking: a survey
  publication-title: IEEE Commun Surv Tutor
– start-page: 444
  year: 2019
  end-page: 449
– volume: 81
  start-page: 899
  year: 2019
  end-page: 913
  article-title: A hybrid short‐term electricity price forecasting framework: Cuckoo search‐based feature selection with singular spectrum analysis and SVM
  publication-title: Energy Econ
– ident: e_1_2_12_14_1
  doi: 10.1007/s10922‐021‐09629‐1
– ident: e_1_2_12_19_1
  doi: 10.1109/BigData.2017.8258087
– ident: e_1_2_12_21_1
  doi: 10.1016/j.aiopen.2021.01.001
– ident: e_1_2_12_22_1
  doi: 10.1016/j.eneco.2019.05.026
– ident: e_1_2_12_16_1
  doi: 10.1016/j.comnet.2019.05.004
– ident: e_1_2_12_23_1
  doi: 10.1016/j.jmva.2021.104798
– ident: e_1_2_12_26_1
  doi: 10.1162/neco.1997.9.8.1735
– ident: e_1_2_12_4_1
  doi: 10.1109/ICTC49870.2020.9289275
– ident: e_1_2_12_15_1
  doi: 10.1109/ANTS47819.2019.9118065
– ident: e_1_2_12_25_1
  doi: 10.1109/ACCESS.2018.2825538
– ident: e_1_2_12_6_1
  doi: 10.1109/ICSPCS50536.2020.9310033
– ident: e_1_2_12_20_1
– ident: e_1_2_12_24_1
  doi: 10.1155/2021/6032325
– start-page: 33
  year: 2021
  ident: e_1_2_12_2_1
  article-title: Managing virtualized networks and services with machine learning
  publication-title: Commun Netw Serv Manag Era Artif Intell Mach Learn
– ident: e_1_2_12_12_1
  doi: 10.1109/TNSM.2020.3015244
– ident: e_1_2_12_7_1
  doi: 10.1016/j.comnet.2021.108104
– ident: e_1_2_12_13_1
  doi: 10.1109/NOMS.2014.6838258
– ident: e_1_2_12_9_1
  doi: 10.1109/NetSoft48620.2020.9165449
– ident: e_1_2_12_3_1
  doi: 10.1109/TNSM.2017.2666781
– ident: e_1_2_12_18_1
  doi: 10.1016/j.future.2019.09.018
– ident: e_1_2_12_17_1
  doi: 10.1109/COMST.2019.2904897
– ident: e_1_2_12_11_1
  doi: 10.1109/NETSOFT.2019.8806620
– ident: e_1_2_12_5_1
  doi: 10.1002/spe.2635
– ident: e_1_2_12_8_1
  doi: 10.3390/fi12110196
– ident: e_1_2_12_10_1
  doi: 10.1587/transinf.2020NTP0010
SSID ssj0011526
Score 2.3453577
Snippet Virtual resource load prediction in network function virtualization (NFV) is the subject of intense research due to its crucial role in enabling proactive...
SourceID proquest
crossref
wiley
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 555
SubjectTerms Accuracy
Correlation coefficients
GNN
Graph neural networks
input feature selection
Load
Load history
LSTM
network function virtualization
resource usage prediction
Virtual memory systems
Virtual networks
Title NFVLearn: A multi‐resource, long short‐term memory‐based virtual network function resource usage prediction architecture
URI https://onlinelibrary.wiley.com/doi/abs/10.1002%2Fspe.3160
https://www.proquest.com/docview/2772886622
Volume 53
WOSCitedRecordID wos000877540300001&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: PRVWIB
  databaseName: Wiley Online Library - Journals
  customDbUrl:
  eissn: 1097-024X
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0011526
  issn: 0038-0644
  databaseCode: DRFUL
  dateStart: 19960101
  isFulltext: true
  titleUrlDefault: https://onlinelibrary.wiley.com
  providerName: Wiley-Blackwell
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1PS8MwFA-yefDi_IvTKRFELxbbpk1bb0M3PMgY6mS3kqSNDmY32m3gRfwIfkY_iS9tuk1QEDyVpkkJeXl5v5e8_B5CJ7HNhCTMNVxOqeEw3zQ4d0DdqTAjjxGLSDNPNuF1On6_H3R1VKW6C1PwQ8w33JRm5Ou1UnDGs4sFaWg2jsHhpOCuV22Ytk4FVa_v2r3b-RkCWCZakDL6Bhhep6SeNe2Lsu13Y7RAmMs4NTc07dp_uriB1jW8xM1iPmyilTjZQrUydQPWmryN3jrtx5xa9RI3cR5U-Pn-keqt_HM8HCVPOHsGaA7FavHGLyoi9xXelNmL8GyQqosnOCmiyLEyj0rEuPwHnqqINTxO1UFQ_mX5yGIH9dqth6sbQ6diMATgAdOwBGiT9E1hBkwSLoUbEcKhEAAkdYX03YgBUCACNDriTFhCSm4S6QXSFSSwyC6qJKMk3kMYzCFgLtshzGGA3mQQUcA4sWV5UQxjFdTRWSmTUGiecpUuYxgWDMt2CMMaqmGto-N5zXHBzfFDnUYp1lBrZxba4FL4PoVe1NFpLsBf24f33ZZ67v-14gFaUxnpizC1BqpM0ml8iFbFbDLI0iM9R78A_rfv5w
linkProvider Wiley-Blackwell
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1bS8MwFD7IFPTFuzidGkH0xWLb9KpPopaJswzdZG8lTRsdaDe6OfBF_An-Rn-JJ73MCQqCT6VpUkJOTs6Xk5PvAOzFOuOCMlMxQ8tSDOaoShgaqO4WVyObUY0KNUs2Yfu-0-m4zSk4Ke_C5PwQY4eb1IxsvZYKLh3SR1-soYN-jDtOC_fr0wbOIrMC0-c3XrsxPkRA02TlrIyOgpbXKLlnVf2obPvdGn1BzEmgmlkab-FffVyE-QJgktN8RizBVJwsw0KZvIEUurwCr753l5GrHpNTkoUVfry9p4Uz_5A89pJ7MnhAcI7FcvkmTzIm9wXfpOGLyKibyqsnJMnjyIk0kFLIpPwHeZYxa6SfyqOg7MvkocUqtL2L1lldKZIxKBwRgapoHPVJOCpXXSZoKLgZURpiIUJIy-TCMSOGUIFy1OkoZFzjQoQqFbYrTE5dja5BJekl8ToQNIiIunSDMoMhfhNuZCHKiTXNjmIcK7cKB6VQAl4wlcuEGY9BzrGsBzisgRzWKuyOa_Zzdo4f6tRKuQaFfg4CHTcVjmNhL6qwn0nw1_bBbfNCPjf-WnEHZuut60bQuPSvNmFO5qfPg9ZqUBmmz_EWzPDRsDtIt4sJ-wlLf_PX
linkToPdf http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1dS8MwFL0MFfHF-YnTqRFEXyy2TZu1-iS6oihjqBPfSpo2OtButNvAF_En-Bv9Jd70Y1NQEHwqTZMSkpzck-TmXIDdyORCUm5rdsCYZnFH14LAQrgzoYcNTg0q9SzYRKPVcu7v3XYFjsu7MLk-xHjDTSEjm68VwKN-KA8nqqFpP8IVJ8P1-rRluwxROX127XWuxocIaJpYrsroaGh5rVJ7VjcPy7LfrdGEYn4lqpml8ar_quMCzBcEk5zkI2IRKlG8BNUyeAMpsLwMry3vLhNXPSInJHMr_Hh7T4rN_APy1IsfSPqI5ByT1fRNnpVP7gu-KcMXklE3UVdPSJz7kRNlIFUnk_IfZKh81kg_UUdB2ZevhxYr0PGat6fnWhGMQRPICHTNEIgn6ehCd7mkgRR2SGmAiUghmS2kY4ccqQIViOkw4MIQUgY6lQ1X2oK6Bl2FqbgXR2tA0CAi6zItyi2O_E26IUOWExlGI4ywrdwa7Jed4otCqVwFzHjyc41l08dm9VWz1mBnnLOfq3P8kKde9qtf4DP1TVxUOA7DWtRgL-vBX8v7N-2meq7_NeM2zLbPPP_qonW5AXMqPH3us1aHqUEyjDZhRowG3TTZKsbrJ-sI81I
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=NFVLearn%3A+A+multi%E2%80%90resource%2C+long+short%E2%80%90term+memory%E2%80%90based+virtual+network+function+resource+usage+prediction+architecture&rft.jtitle=Software%2C+practice+%26+experience&rft.au=St%E2%80%90Onge%2C+C%C3%A9dric&rft.au=Kara%2C+Nadjia&rft.au=Edstrom%2C+Claes&rft.date=2023-03-01&rft.issn=0038-0644&rft.eissn=1097-024X&rft.volume=53&rft.issue=3&rft.spage=555&rft.epage=578&rft_id=info:doi/10.1002%2Fspe.3160&rft.externalDBID=10.1002%252Fspe.3160&rft.externalDocID=SPE3160
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0038-0644&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0038-0644&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0038-0644&client=summon