Machine Learning Empowered Intelligent Data Center Networking: Evolution, Challenges and Opportunities

123 Pages·2023·2.343 MB·English

by  Ting Wang, Bo Li, Mingsong Chen, Shui Yu

SpringerBriefs in Computer Science
Ting Wang · Bo Li · Mingsong Chen · Shui Yu
Machine Learning
Empowered Intelligent
Data Center Networking
Evolution, Challenges and
Opportunities
SpringerBriefs in Computer Science
SeriesEditors
StanZdonik,BrownUniversity,Providence,RI,USA
ShashiShekhar,UniversityofMinnesota,Minneapolis,MN,USA
XindongWu,UniversityofVermont,Burlington,VT,USA
LakhmiC.Jain,UniversityofSouthAustralia,Adelaide,SA,Australia
DavidPadua,UniversityofIllinoisUrbana-Champaign,Urbana,IL,USA
XueminShermanShen,UniversityofWaterloo,Waterloo,ON,Canada
BorkoFurht,FloridaAtlanticUniversity,BocaRaton,FL,USA
V.S.Subrahmanian,UniversityofMaryland,CollegePark,MD,USA
MartialHebert,CarnegieMellonUniversity,Pittsburgh,PA,USA
KatsushiIkeuchi,UniversityofTokyo,Tokyo,Japan
BrunoSiciliano,UniversitàdiNapoliFedericoII,Napoli,Italy
SushilJajodia,GeorgeMasonUniversity,Fairfax,VA,USA
NewtonLee,InstituteforEducation,ResearchandScholarships,LosAngeles,CA,
USA
SpringerBriefs present concise summaries of cutting-edge research and practical
applicationsacrossawidespectrumoffields.Featuringcompactvolumesof50to
125pages,theseriescoversarangeofcontentfromprofessionaltoacademic.
Typicaltopicsmightinclude:
(cid:129) Atimelyreportofstate-of-theartanalyticaltechniques
(cid:129) A bridge between new research results, as published in journal articles, and a
contextualliteraturereview
(cid:129) Asnapshotofahotoremergingtopic
(cid:129) Anin-depthcasestudyorclinicalexample
(cid:129) Apresentationofcoreconceptsthatstudentsmustunderstandinordertomake
independentcontributions
Briefsallowauthorstopresenttheirideasandreaderstoabsorbthemwithminimal
time investment. Briefs will be published as part of Springer’s eBook collection,
withmillionsofusersworldwide.Inaddition,Briefswillbeavailableforindividual
print and electronic purchase. Briefs are characterized by fast, global electronic
dissemination, standard publishing contracts, easy-to-use manuscript preparation
and formatting guidelines, and expedited production schedules. We aim for pub-
lication 8–12 weeks after acceptance. Both solicited and unsolicited manuscripts
areconsideredforpublicationinthisseries.
**Indexing:ThisseriesisindexedinScopus,Ei-Compendex,andzbMATH**
Ting Wang (cid:129) Bo Li (cid:129) Mingsong Chen (cid:129) Shui Yu
Machine Learning
Empowered Intelligent Data
Center Networking
Evolution, Challenges and Opportunities
TingWang BoLi
SoftwareEngineeringInstitute SoftwareEngineeringInstitute
EastChinaNormalUniversity EastChinaNormalUniversity
Shanghai,China Shanghai,China
MingsongChen ShuiYu
SoftwareEngineeringInstitute SchoolofComputerScience
EastChinaNormalUniversity UniversityofTechnologySydney
Shanghai,China Ultimo,NSW,Australia
ISSN2191-5768 ISSN2191-5776 (electronic)
SpringerBriefsinComputerScience
ISBN978-981-19-7394-9 ISBN978-981-19-7395-6 (eBook)
https://doi.org/10.1007/978-981-19-7395-6
©TheAuthor(s),underexclusivelicensetoSpringerNatureSingaporePteLtd.2023
Thisworkissubjecttocopyright.AllrightsaresolelyandexclusivelylicensedbythePublisher,whether
thewholeorpartofthematerialisconcerned,specificallytherightsoftranslation,reprinting,reuse
ofillustrations,recitation,broadcasting,reproductiononmicrofilmsorinanyotherphysicalway,and
transmissionorinformationstorageandretrieval,electronicadaptation,computersoftware,orbysimilar
ordissimilarmethodologynowknownorhereafterdeveloped.
Theuseofgeneraldescriptivenames,registerednames,trademarks,servicemarks,etc.inthispublication
doesnotimply,evenintheabsenceofaspecificstatement,thatsuchnamesareexemptfromtherelevant
protectivelawsandregulationsandthereforefreeforgeneraluse.
Thepublisher,theauthors,andtheeditorsaresafetoassumethattheadviceandinformationinthisbook
arebelievedtobetrueandaccurateatthedateofpublication.Neitherthepublishernortheauthorsor
theeditorsgiveawarranty,expressedorimplied,withrespecttothematerialcontainedhereinorforany
errorsoromissionsthatmayhavebeenmade.Thepublisherremainsneutralwithregardtojurisdictional
claimsinpublishedmapsandinstitutionalaffiliations.
ThisSpringerimprintispublishedbytheregisteredcompanySpringerNatureSingaporePteLtd.
The registered company address is: 152 Beach Road, #21-01/04 Gateway East, Singapore 189721,
Singapore
Preface
To support the needs of ever-growing cloud-based services, the number of servers
andnetworkdevicesindatacentersisincreasingexponentially,whichinturnresults
in high complexities and difficulties in network optimization. To address these
challenges, both academia and industry turn to artificial intelligence technology
to realize network intelligence. To this end, a considerable number of novel and
creativemachinelearning-based(ML-based)researchworkshavebeenputforward
in recent few years. Nevertheless, there are still enormous challenges faced by
the intelligent optimization of data center networks (DCNs), especially in the
scenarioofonlinereal-timedynamicprocessingofmassiveheterogeneousservices
and traffic data. To the best of our knowledge, there is a lack of systematic
and original comprehensive investigations with in-depth analysis on intelligent
DCN. To this end, in this book, we comprehensively investigate the application
ofmachinelearningtodatacenternetworkingandprovideageneraloverviewand
in-depthanalysisoftherecentworks,coveringflowprediction,flowclassification,
load balancing, resource management, energy management, routing optimization,
congestion control, fault management, and network security. In order to provide
a multi-dimensional and multi-perspective comparison of various solutions, we
design a quality assessment criteria called REBEL-3S to impartially measure the
strengths and weaknesses of these research works. Moreover, we also present
uniqueinsightsintothetechnologyevolutionofthefusionofdatacenternetworks
andmachinelearning,togetherwithsomechallengesandpotentialfutureresearch
opportunities.
Shanghai,P.R.China TingWang
March2022 BoLi
MingsongChen
ShuiYu
v
Acknowledgments
This work was partially supported by the grants from National Key Research and
Development Program of China (2018YFB2101300), Natural Science Foundation
of China (61872147), the Dean’s Fund of Engineering Research Center of Soft-
ware/HardwareCo-designTechnologyandApplication,MinistryofEducation(East
ChinaNormalUniversity),andthegrantsfromShenzhenScienceandTechnology
PlanProject(CJGJZD20210408092400001).
vii
Contents
1 Introduction .................................................................. 1
References..................................................................... 5
2 FundamentalsofMachineLearninginDataCenterNetworks......... 9
2.1 LearningParadigm .................................................... 9
2.2 DataCollectionandProcessing....................................... 10
2.2.1 DataCollectionScenarios................................... 11
2.2.2 DataCollectionTechniques ................................. 11
2.2.3 FeatureEngineering.......................................... 11
2.2.4 ChallengesandInsights...................................... 12
2.3 PerformanceEvaluationofML-BasedSolutionsinDCN........... 13
References..................................................................... 14
3 MachineLearningEmpoweredIntelligentDataCenter
Networking ................................................................... 15
3.1 FlowPrediction........................................................ 15
3.1.1 Temporal-DependentModeling............................. 16
3.1.2 Spatial-DependentModeling................................ 16
3.1.3 DiscussionandInsights...................................... 17
3.2 FlowClassification .................................................... 17
3.2.1 SupervisedLearning-BasedFlowClassification ........... 22
3.2.2 UnsupervisedLearning-BasedFlowClassification ........ 23
3.2.3 DeepLearning-BasedFlowClassification.................. 23
3.2.4 ReinforcementLearning-BasedFlowClassification....... 24
3.2.5 DiscussionandInsights...................................... 24
3.3 LoadBalancing........................................................ 28
3.3.1 TraditionalSolutions......................................... 29
3.3.2 MachineLearning-BasedSolutions......................... 29
3.3.3 DiscussionandInsights...................................... 30
3.4 ResourceManagement ................................................ 31
3.4.1 Task-OrientedResourceManagement...................... 36
3.4.2 VirtualEntities-OrientedResourceManagement .......... 37
ix
x Contents
3.4.3 QoS-OrientedResourceManagement ...................... 37
3.4.4 ResourcePrediction-OrientedResourceManagement..... 38
3.4.5 ResourceUtilization-OrientedResourceManagement .... 38
3.4.6 DiscussionandInsights...................................... 39
3.5 EnergyManagement................................................... 46
3.5.1 ServerLevel.................................................. 47
3.5.2 NetworkLevel ............................................... 47
3.5.3 DataCenterLevel............................................ 48
3.5.4 DiscussionandInsights...................................... 49
3.6 RoutingOptimization ................................................. 54
3.6.1 Intra-DCRoutingOptimization............................. 55
3.6.2 Inter-DCRoutingOptimization............................. 55
3.6.3 DiscussionandInsights...................................... 55
3.7 CongestionControl.................................................... 61
3.7.1 CentralizedCongestionControl............................. 62
3.7.2 DistributedCongestionControl............................. 63
3.7.3 DiscussionandInsights...................................... 63
3.8 FaultManagement..................................................... 64
3.8.1 FaultPrediction .............................................. 69
3.8.2 FaultDetection............................................... 70
3.8.3 FaultLocation................................................ 70
3.8.4 FaultSelf-Healing............................................ 70
3.8.5 DiscussionandInsights...................................... 71
3.9 NetworkSecurity...................................................... 75
3.10 NewIntelligentNetworkingConcepts................................ 79
3.10.1 Intent-DrivenNetwork....................................... 80
3.10.2 Knowledge-DefinedNetwork ............................... 80
3.10.3 Self-DrivingNetwork........................................ 81
3.10.4 Intent-BasedNetwork(Gartner)............................. 82
3.10.5 Intent-BasedNetwork(Cisco)............................... 83
References..................................................................... 84
4 Insights,ChallengesandOpportunities ................................... 101
4.1 IndustryStandards..................................................... 105
4.1.1 NetworkIntelligenceQuantificationStandards ............ 105
4.1.2 DataQualityAssessmentStandards ........................ 105
4.2 ModelDesign.......................................................... 105
4.2.1 IntelligentResourceAllocationMechanism................ 105
4.2.2 Inter-DCIntelligentCollaborativeOptimization
Mechanism................................................... 106
4.2.3 AdaptiveFeatureEngineering............................... 106
4.2.4 IntelligentModelSelectionMechanism.................... 106
4.3 NetworkTransmission................................................. 106
4.4 NetworkVisualization................................................. 107
References..................................................................... 108
Contents xi
5 Conclusion.................................................................... 109
Index............................................................................... 111