SlideShare une entreprise Scribd logo
1  sur  15
Prof. A. Taleb-Bendiab, talk: WO, Conference: ICIES’05, Miami, Date:Prof. A. Taleb-Bendiab, talk: WO, Conference: ICIES’05, Miami, Date: 01/28/1501/28/15, Slide:, Slide: 11
A Machine Learning
Middleware Service for On-
Demand Grid Services
Engineering and Support
Prof. A. Taleb-BendiabProf. A. Taleb-Bendiab
School of ComputingSchool of Computing
Liverpool John Moores UniversityLiverpool John Moores University
email:email: a.talebbendiab@livjm.ac.uka.talebbendiab@livjm.ac.uk
http://www.cms.livjm.ac.uk/talebhttp://www.cms.livjm.ac.uk/taleb
http://www.cms.livjm.ac.uk/Self-http://www.cms.livjm.ac.uk/Self-XX
ScopeScope
 Situated Autonomic ComputingSituated Autonomic Computing
 Problem Definition - ChallengesProblem Definition - Challenges
 Design including; coordination and controlDesign including; coordination and control
 model-based vs emergencemodel-based vs emergence
 Specification of control modelsSpecification of control models
 Design via experimentation and machine learningDesign via experimentation and machine learning
 Example – on-demand reservation ofExample – on-demand reservation of
application servicesapplication services
 User Classification scenarioUser Classification scenario
 Episodic resource requirementsEpisodic resource requirements
 SOM Classification for Connected HomeSOM Classification for Connected Home
MachineMachine
 ImplementationImplementation
 Case-studyCase-study
Prof. A. Taleb-Bendiab, Talk: WO, CSAC’05 Workshop, Conference: ICIES’05, Miami,
Date: 01/28/15, Slide: 3
Situated AC Scenario: E-FireSituated AC Scenario: E-Fire
ServicesServices
Prof. A. Taleb-Bendiab, Talk: WO, CSAC’05 Workshop, Conference: ICIES’05, Miami,
Date: 01/28/15, Slide: 4
Challenges -- Global ComputingChallenges -- Global Computing
 Global Enterprise SystemsGlobal Enterprise Systems
 High-assurance systems development and life-High-assurance systems development and life-
time managementtime management
 Complexity and scale is rapidly increasingComplexity and scale is rapidly increasing
 Bio-inspired Models -- AutonomyBio-inspired Models -- Autonomy
 devolving software management, maintenance todevolving software management, maintenance to
the software itselfthe software itself
 Self-managing, self-tuning, self-protecting, ...Self-managing, self-tuning, self-protecting, ...
 Need continuous measurement, introspectionNeed continuous measurement, introspection
to supportto support
 Observed and/or supervised adaptation for;Observed and/or supervised adaptation for;
 Safe, predictable,Safe, predictable,
 Coordinated, traceable, etc.Coordinated, traceable, etc.
Prof. A. Taleb-Bendiab, Talk: WO, CSAC’05 Workshop, Conference: ICIES’05, Miami,
Date: 01/28/15, Slide: 5
So far …!So far …!
 Current researchCurrent research
 Instrumentation middleware services forInstrumentation middleware services for
 improved usability and reliability for instance forimproved usability and reliability for instance for
 grid-based applications, and ubiquitousgrid-based applications, and ubiquitous
computingcomputing
 Monitor, control and manage grid users’ applications.Monitor, control and manage grid users’ applications.
 Context-awareness and QoS-Aware systemsContext-awareness and QoS-Aware systems
 Event-based systemsEvent-based systems
 Sensor networks, Etc.Sensor networks, Etc.
 Further research is requiredFurther research is required
 Management, assurance and fidelity of awarenessManagement, assurance and fidelity of awareness
layer is a major concernslayer is a major concerns
 Sensors and actuators (effectors) support webSensors and actuators (effectors) support web
services and grid computingservices and grid computing
 Current models looking at small scale systemsCurrent models looking at small scale systems
Prof. A. Taleb-Bendiab, Talk: WO, CSAC’05 Workshop, Conference: ICIES’05, Miami,
Date: 01/28/15, Slide: 6
Design Approach Informed byDesign Approach Informed by
Machine LearningMachine Learning
 Frameworks and ModelsFrameworks and Models
 Programming, interaction and/or controlProgramming, interaction and/or control
models.models.
 Two experiments were conductedTwo experiments were conducted
 User Classification and on-demand serviceUser Classification and on-demand service
reservationreservation
 Autonomic software restore serviceAutonomic software restore service
Prof. A. Taleb-Bendiab, Talk: WO, CSAC’05 Workshop, Conference: ICIES’05, Miami,
Date: 01/28/15, Slide: 7
Experiment #1: User ClassificationExperiment #1: User Classification
 The scenarioThe scenario
 Mining service usage models per class ofMining service usage models per class of
users for preemptive service reservation andusers for preemptive service reservation and
on-demand serviceson-demand services
 MethodMethod
 Developed an Simulation tool for IntelligentDeveloped an Simulation tool for Intelligent
Connected Home, which generate servicesConnected Home, which generate services
 Self-Organising Maps (SOM) applied extractSelf-Organising Maps (SOM) applied extract
feature or usage modelfeature or usage model
 Design and ImplementationDesign and Implementation
 To followTo follow
Prof. A. Taleb-Bendiab, Talk: WO, CSAC’05 Workshop, Conference: ICIES’05, Miami,
Date: 01/28/15, Slide: 8
Design and ImplementationDesign and Implementation
 Data generated tool is developed toData generated tool is developed to
produce training and test data for thisproduce training and test data for this
application.application.
 An OGSA and web service compliantAn OGSA and web service compliant
SOM middleware service wasSOM middleware service was
developeddeveloped
 For rapid prototyping a Matlab library forFor rapid prototyping a Matlab library for
SOM is used for classificationSOM is used for classification
Prof. A. Taleb-Bendiab, Talk: WO, CSAC’05 Workshop, Conference: ICIES’05, Miami,
Date: 01/28/15, Slide: 9
SOM Classification Results ForSOM Classification Results For
Connected Home Machine DevicesConnected Home Machine Devices
• Lights and PlayStationII correlates
• Video and Coffee Machine correlates
• Video CD and Fans correlates
• Vacuum cleaner and Washing machine correlates
Prof. A. Taleb-Bendiab, Talk: WO, CSAC’05 Workshop, Conference: ICIES’05, Miami,
Date: 01/28/15, Slide: 11
So WhatSo What??
 Exploiting ML:Exploiting ML:
 anticipate and organize the consumers’ requests inanticipate and organize the consumers’ requests in
advanced.advanced.
 Job schedule is responsible for managing theJob schedule is responsible for managing the
invocations of the services.invocations of the services.
 Just-in-time services invocation and usageJust-in-time services invocation and usage
 Etc.Etc.
 In addition to the presented ML middleware service withIn addition to the presented ML middleware service with
automated inclusion and use of usage model for userautomated inclusion and use of usage model for user
and service classificationand service classification
 Further support is required including;Further support is required including;
 Specification and modelling of mined models and theirSpecification and modelling of mined models and their
enactment for instance;enactment for instance;
 Control and/or actuation modelsControl and/or actuation models
 Neptune Meta-Language and Integrated developmentNeptune Meta-Language and Integrated development
environment will be used for this.environment will be used for this.
Prof. A. Taleb-Bendiab, Talk: WO, CSAC’05 Workshop, Conference: ICIES’05, Miami,
Date: 01/28/15, Slide: 12
Neptune Meta-Language #1Neptune Meta-Language #1
Prof. A. Taleb-Bendiab, Talk: WO, CSAC’05 Workshop, Conference: ICIES’05, Miami,
Date: 01/28/15, Slide: 13
Neptune Meta-Language #2Neptune Meta-Language #2
Prof. A. Taleb-Bendiab, Talk: WO, CSAC’05 Workshop, Conference: ICIES’05, Miami,
Date: 01/28/15, Slide: 14
Neptune Meta-Language #3Neptune Meta-Language #3
Prof. A. Taleb-Bendiab, Talk: WO, CSAC’05 Workshop, Conference: ICIES’05, Miami,
Date: 01/28/15, Slide: 15
Conclusions & Further WorkConclusions & Further Work
 Prototypes developed using .Net and supportPrototypes developed using .Net and support
Web Services StandardsWeb Services Standards
 Tested in a number of case studiesTested in a number of case studies
 Intelligent Connected HomesIntelligent Connected Homes
 E-HealthE-Health
 With PlanetLab environmentWith PlanetLab environment
 Further workFurther work
 Integration of this work with the Neptune Language toIntegration of this work with the Neptune Language to
supportsupport
 norm-governed web services and architectures.norm-governed web services and architectures.
 Situated Autonomic middlewareSituated Autonomic middleware
 Integration machine learning services to supportIntegration machine learning services to support
danger/novelty detectiondanger/novelty detection
 Further evaluation of the frameworkFurther evaluation of the framework
Prof. A. Taleb-Bendiab, Talk: WO, CSAC’05 Workshop, Conference: ICIES’05, Miami,
Date: 01/28/15, Slide: 16

Contenu connexe

Similaire à ppt

NetApp Industry Keynote - Flash Memory Summit - Aug2015
NetApp Industry Keynote - Flash Memory Summit - Aug2015NetApp Industry Keynote - Flash Memory Summit - Aug2015
NetApp Industry Keynote - Flash Memory Summit - Aug2015Val Bercovici
 
Cloud forum-lessons-learned-20110405c-final
Cloud forum-lessons-learned-20110405c-finalCloud forum-lessons-learned-20110405c-final
Cloud forum-lessons-learned-20110405c-finalMauricio Godoy
 
Workshop BI/DWH AGILE TESTING SNS Bank English
Workshop BI/DWH AGILE TESTING SNS Bank EnglishWorkshop BI/DWH AGILE TESTING SNS Bank English
Workshop BI/DWH AGILE TESTING SNS Bank EnglishMarcus Drost
 
ANALYSIS OF SOFTWARE SECURITY TESTING TECHNIQUES IN CLOUD COMPUTING
ANALYSIS OF SOFTWARE SECURITY TESTING TECHNIQUES IN CLOUD COMPUTINGANALYSIS OF SOFTWARE SECURITY TESTING TECHNIQUES IN CLOUD COMPUTING
ANALYSIS OF SOFTWARE SECURITY TESTING TECHNIQUES IN CLOUD COMPUTINGEditor IJMTER
 
Scale Container Operations with AIOps
Scale Container Operations with AIOpsScale Container Operations with AIOps
Scale Container Operations with AIOpsTimothy Chen
 
An Empirical Comparison of the Development History of CloudStack and Eucalyptus
An Empirical Comparison of the Development History of CloudStack and EucalyptusAn Empirical Comparison of the Development History of CloudStack and Eucalyptus
An Empirical Comparison of the Development History of CloudStack and EucalyptusAhmed Zerouali
 
Self-Tuning Data Centers
Self-Tuning Data CentersSelf-Tuning Data Centers
Self-Tuning Data CentersReza Rahimi
 
Test Your Cloud Maturity Level: A Practical Guide to Self Assessment
Test Your Cloud Maturity Level: A Practical Guide to Self AssessmentTest Your Cloud Maturity Level: A Practical Guide to Self Assessment
Test Your Cloud Maturity Level: A Practical Guide to Self AssessmentDavid Resnic
 
Ariel Litvin - CCSK
Ariel Litvin - CCSKAriel Litvin - CCSK
Ariel Litvin - CCSKCSAIsrael
 
Muves3 Elastic Grid Java One2009 Final
Muves3 Elastic Grid Java One2009 FinalMuves3 Elastic Grid Java One2009 Final
Muves3 Elastic Grid Java One2009 FinalElastic Grid, LLC.
 
ALM for Developing Engineered Systems - Michael Azoff (Ovum) - 14 May 2019
ALM for Developing Engineered Systems - Michael Azoff (Ovum) - 14 May 2019ALM for Developing Engineered Systems - Michael Azoff (Ovum) - 14 May 2019
ALM for Developing Engineered Systems - Michael Azoff (Ovum) - 14 May 2019Intland Software GmbH
 
Web 2.0: How Should IT Services and the Library Respond?
Web 2.0: How Should IT Services and the Library Respond?Web 2.0: How Should IT Services and the Library Respond?
Web 2.0: How Should IT Services and the Library Respond?lisbk
 
Brian Kelly and Paul Walk, SaaSy APIs (Openness in the Cloud)
Brian Kelly and Paul Walk, SaaSy APIs (Openness in the Cloud)Brian Kelly and Paul Walk, SaaSy APIs (Openness in the Cloud)
Brian Kelly and Paul Walk, SaaSy APIs (Openness in the Cloud)museums and the web
 
Ragha Deepika_Exp_4+
Ragha Deepika_Exp_4+Ragha Deepika_Exp_4+
Ragha Deepika_Exp_4+Ragha batchu
 
Securing a Cloud Migration
Securing a Cloud MigrationSecuring a Cloud Migration
Securing a Cloud MigrationVMware Tanzu
 
Improving Software quality for the Modern Web
Improving Software quality for the Modern WebImproving Software quality for the Modern Web
Improving Software quality for the Modern WebEuan Garden
 
Case Study: Datalink—Manage IT monitoring the MSP way
Case Study: Datalink—Manage IT monitoring the MSP wayCase Study: Datalink—Manage IT monitoring the MSP way
Case Study: Datalink—Manage IT monitoring the MSP wayCA Technologies
 

Similaire à ppt (20)

NetApp Industry Keynote - Flash Memory Summit - Aug2015
NetApp Industry Keynote - Flash Memory Summit - Aug2015NetApp Industry Keynote - Flash Memory Summit - Aug2015
NetApp Industry Keynote - Flash Memory Summit - Aug2015
 
Cloud forum-lessons-learned-20110405c-final
Cloud forum-lessons-learned-20110405c-finalCloud forum-lessons-learned-20110405c-final
Cloud forum-lessons-learned-20110405c-final
 
Workshop BI/DWH AGILE TESTING SNS Bank English
Workshop BI/DWH AGILE TESTING SNS Bank EnglishWorkshop BI/DWH AGILE TESTING SNS Bank English
Workshop BI/DWH AGILE TESTING SNS Bank English
 
ANALYSIS OF SOFTWARE SECURITY TESTING TECHNIQUES IN CLOUD COMPUTING
ANALYSIS OF SOFTWARE SECURITY TESTING TECHNIQUES IN CLOUD COMPUTINGANALYSIS OF SOFTWARE SECURITY TESTING TECHNIQUES IN CLOUD COMPUTING
ANALYSIS OF SOFTWARE SECURITY TESTING TECHNIQUES IN CLOUD COMPUTING
 
Scale Container Operations with AIOps
Scale Container Operations with AIOpsScale Container Operations with AIOps
Scale Container Operations with AIOps
 
An Empirical Comparison of the Development History of CloudStack and Eucalyptus
An Empirical Comparison of the Development History of CloudStack and EucalyptusAn Empirical Comparison of the Development History of CloudStack and Eucalyptus
An Empirical Comparison of the Development History of CloudStack and Eucalyptus
 
Self-Tuning Data Centers
Self-Tuning Data CentersSelf-Tuning Data Centers
Self-Tuning Data Centers
 
Test Your Cloud Maturity Level: A Practical Guide to Self Assessment
Test Your Cloud Maturity Level: A Practical Guide to Self AssessmentTest Your Cloud Maturity Level: A Practical Guide to Self Assessment
Test Your Cloud Maturity Level: A Practical Guide to Self Assessment
 
Ariel Litvin - CCSK
Ariel Litvin - CCSKAriel Litvin - CCSK
Ariel Litvin - CCSK
 
Cloud Security
Cloud Security Cloud Security
Cloud Security
 
Muves3 Elastic Grid Java One2009 Final
Muves3 Elastic Grid Java One2009 FinalMuves3 Elastic Grid Java One2009 Final
Muves3 Elastic Grid Java One2009 Final
 
ALM for Developing Engineered Systems - Michael Azoff (Ovum) - 14 May 2019
ALM for Developing Engineered Systems - Michael Azoff (Ovum) - 14 May 2019ALM for Developing Engineered Systems - Michael Azoff (Ovum) - 14 May 2019
ALM for Developing Engineered Systems - Michael Azoff (Ovum) - 14 May 2019
 
Web 2.0: How Should IT Services and the Library Respond?
Web 2.0: How Should IT Services and the Library Respond?Web 2.0: How Should IT Services and the Library Respond?
Web 2.0: How Should IT Services and the Library Respond?
 
Brian Kelly and Paul Walk, SaaSy APIs (Openness in the Cloud)
Brian Kelly and Paul Walk, SaaSy APIs (Openness in the Cloud)Brian Kelly and Paul Walk, SaaSy APIs (Openness in the Cloud)
Brian Kelly and Paul Walk, SaaSy APIs (Openness in the Cloud)
 
Ragha Deepika_Exp_4+
Ragha Deepika_Exp_4+Ragha Deepika_Exp_4+
Ragha Deepika_Exp_4+
 
Securing a Cloud Migration
Securing a Cloud MigrationSecuring a Cloud Migration
Securing a Cloud Migration
 
Securing a Cloud Migration
Securing a Cloud MigrationSecuring a Cloud Migration
Securing a Cloud Migration
 
Improving Software quality for the Modern Web
Improving Software quality for the Modern WebImproving Software quality for the Modern Web
Improving Software quality for the Modern Web
 
My pres
My presMy pres
My pres
 
Case Study: Datalink—Manage IT monitoring the MSP way
Case Study: Datalink—Manage IT monitoring the MSP wayCase Study: Datalink—Manage IT monitoring the MSP way
Case Study: Datalink—Manage IT monitoring the MSP way
 

Plus de butest

EL MODELO DE NEGOCIO DE YOUTUBE
EL MODELO DE NEGOCIO DE YOUTUBEEL MODELO DE NEGOCIO DE YOUTUBE
EL MODELO DE NEGOCIO DE YOUTUBEbutest
 
1. MPEG I.B.P frame之不同
1. MPEG I.B.P frame之不同1. MPEG I.B.P frame之不同
1. MPEG I.B.P frame之不同butest
 
LESSONS FROM THE MICHAEL JACKSON TRIAL
LESSONS FROM THE MICHAEL JACKSON TRIALLESSONS FROM THE MICHAEL JACKSON TRIAL
LESSONS FROM THE MICHAEL JACKSON TRIALbutest
 
Timeline: The Life of Michael Jackson
Timeline: The Life of Michael JacksonTimeline: The Life of Michael Jackson
Timeline: The Life of Michael Jacksonbutest
 
Popular Reading Last Updated April 1, 2010 Adams, Lorraine The ...
Popular Reading Last Updated April 1, 2010 Adams, Lorraine The ...Popular Reading Last Updated April 1, 2010 Adams, Lorraine The ...
Popular Reading Last Updated April 1, 2010 Adams, Lorraine The ...butest
 
LESSONS FROM THE MICHAEL JACKSON TRIAL
LESSONS FROM THE MICHAEL JACKSON TRIALLESSONS FROM THE MICHAEL JACKSON TRIAL
LESSONS FROM THE MICHAEL JACKSON TRIALbutest
 
Com 380, Summer II
Com 380, Summer IICom 380, Summer II
Com 380, Summer IIbutest
 
The MYnstrel Free Press Volume 2: Economic Struggles, Meet Jazz
The MYnstrel Free Press Volume 2: Economic Struggles, Meet JazzThe MYnstrel Free Press Volume 2: Economic Struggles, Meet Jazz
The MYnstrel Free Press Volume 2: Economic Struggles, Meet Jazzbutest
 
MICHAEL JACKSON.doc
MICHAEL JACKSON.docMICHAEL JACKSON.doc
MICHAEL JACKSON.docbutest
 
Social Networks: Twitter Facebook SL - Slide 1
Social Networks: Twitter Facebook SL - Slide 1Social Networks: Twitter Facebook SL - Slide 1
Social Networks: Twitter Facebook SL - Slide 1butest
 
Facebook
Facebook Facebook
Facebook butest
 
Executive Summary Hare Chevrolet is a General Motors dealership ...
Executive Summary Hare Chevrolet is a General Motors dealership ...Executive Summary Hare Chevrolet is a General Motors dealership ...
Executive Summary Hare Chevrolet is a General Motors dealership ...butest
 
Welcome to the Dougherty County Public Library's Facebook and ...
Welcome to the Dougherty County Public Library's Facebook and ...Welcome to the Dougherty County Public Library's Facebook and ...
Welcome to the Dougherty County Public Library's Facebook and ...butest
 
NEWS ANNOUNCEMENT
NEWS ANNOUNCEMENTNEWS ANNOUNCEMENT
NEWS ANNOUNCEMENTbutest
 
C-2100 Ultra Zoom.doc
C-2100 Ultra Zoom.docC-2100 Ultra Zoom.doc
C-2100 Ultra Zoom.docbutest
 
MAC Printing on ITS Printers.doc.doc
MAC Printing on ITS Printers.doc.docMAC Printing on ITS Printers.doc.doc
MAC Printing on ITS Printers.doc.docbutest
 
Mac OS X Guide.doc
Mac OS X Guide.docMac OS X Guide.doc
Mac OS X Guide.docbutest
 
WEB DESIGN!
WEB DESIGN!WEB DESIGN!
WEB DESIGN!butest
 

Plus de butest (20)

EL MODELO DE NEGOCIO DE YOUTUBE
EL MODELO DE NEGOCIO DE YOUTUBEEL MODELO DE NEGOCIO DE YOUTUBE
EL MODELO DE NEGOCIO DE YOUTUBE
 
1. MPEG I.B.P frame之不同
1. MPEG I.B.P frame之不同1. MPEG I.B.P frame之不同
1. MPEG I.B.P frame之不同
 
LESSONS FROM THE MICHAEL JACKSON TRIAL
LESSONS FROM THE MICHAEL JACKSON TRIALLESSONS FROM THE MICHAEL JACKSON TRIAL
LESSONS FROM THE MICHAEL JACKSON TRIAL
 
Timeline: The Life of Michael Jackson
Timeline: The Life of Michael JacksonTimeline: The Life of Michael Jackson
Timeline: The Life of Michael Jackson
 
Popular Reading Last Updated April 1, 2010 Adams, Lorraine The ...
Popular Reading Last Updated April 1, 2010 Adams, Lorraine The ...Popular Reading Last Updated April 1, 2010 Adams, Lorraine The ...
Popular Reading Last Updated April 1, 2010 Adams, Lorraine The ...
 
LESSONS FROM THE MICHAEL JACKSON TRIAL
LESSONS FROM THE MICHAEL JACKSON TRIALLESSONS FROM THE MICHAEL JACKSON TRIAL
LESSONS FROM THE MICHAEL JACKSON TRIAL
 
Com 380, Summer II
Com 380, Summer IICom 380, Summer II
Com 380, Summer II
 
PPT
PPTPPT
PPT
 
The MYnstrel Free Press Volume 2: Economic Struggles, Meet Jazz
The MYnstrel Free Press Volume 2: Economic Struggles, Meet JazzThe MYnstrel Free Press Volume 2: Economic Struggles, Meet Jazz
The MYnstrel Free Press Volume 2: Economic Struggles, Meet Jazz
 
MICHAEL JACKSON.doc
MICHAEL JACKSON.docMICHAEL JACKSON.doc
MICHAEL JACKSON.doc
 
Social Networks: Twitter Facebook SL - Slide 1
Social Networks: Twitter Facebook SL - Slide 1Social Networks: Twitter Facebook SL - Slide 1
Social Networks: Twitter Facebook SL - Slide 1
 
Facebook
Facebook Facebook
Facebook
 
Executive Summary Hare Chevrolet is a General Motors dealership ...
Executive Summary Hare Chevrolet is a General Motors dealership ...Executive Summary Hare Chevrolet is a General Motors dealership ...
Executive Summary Hare Chevrolet is a General Motors dealership ...
 
Welcome to the Dougherty County Public Library's Facebook and ...
Welcome to the Dougherty County Public Library's Facebook and ...Welcome to the Dougherty County Public Library's Facebook and ...
Welcome to the Dougherty County Public Library's Facebook and ...
 
NEWS ANNOUNCEMENT
NEWS ANNOUNCEMENTNEWS ANNOUNCEMENT
NEWS ANNOUNCEMENT
 
C-2100 Ultra Zoom.doc
C-2100 Ultra Zoom.docC-2100 Ultra Zoom.doc
C-2100 Ultra Zoom.doc
 
MAC Printing on ITS Printers.doc.doc
MAC Printing on ITS Printers.doc.docMAC Printing on ITS Printers.doc.doc
MAC Printing on ITS Printers.doc.doc
 
Mac OS X Guide.doc
Mac OS X Guide.docMac OS X Guide.doc
Mac OS X Guide.doc
 
hier
hierhier
hier
 
WEB DESIGN!
WEB DESIGN!WEB DESIGN!
WEB DESIGN!
 

ppt

  • 1. Prof. A. Taleb-Bendiab, talk: WO, Conference: ICIES’05, Miami, Date:Prof. A. Taleb-Bendiab, talk: WO, Conference: ICIES’05, Miami, Date: 01/28/1501/28/15, Slide:, Slide: 11 A Machine Learning Middleware Service for On- Demand Grid Services Engineering and Support Prof. A. Taleb-BendiabProf. A. Taleb-Bendiab School of ComputingSchool of Computing Liverpool John Moores UniversityLiverpool John Moores University email:email: a.talebbendiab@livjm.ac.uka.talebbendiab@livjm.ac.uk http://www.cms.livjm.ac.uk/talebhttp://www.cms.livjm.ac.uk/taleb http://www.cms.livjm.ac.uk/Self-http://www.cms.livjm.ac.uk/Self-XX
  • 2. ScopeScope  Situated Autonomic ComputingSituated Autonomic Computing  Problem Definition - ChallengesProblem Definition - Challenges  Design including; coordination and controlDesign including; coordination and control  model-based vs emergencemodel-based vs emergence  Specification of control modelsSpecification of control models  Design via experimentation and machine learningDesign via experimentation and machine learning  Example – on-demand reservation ofExample – on-demand reservation of application servicesapplication services  User Classification scenarioUser Classification scenario  Episodic resource requirementsEpisodic resource requirements  SOM Classification for Connected HomeSOM Classification for Connected Home MachineMachine  ImplementationImplementation  Case-studyCase-study
  • 3. Prof. A. Taleb-Bendiab, Talk: WO, CSAC’05 Workshop, Conference: ICIES’05, Miami, Date: 01/28/15, Slide: 3 Situated AC Scenario: E-FireSituated AC Scenario: E-Fire ServicesServices
  • 4. Prof. A. Taleb-Bendiab, Talk: WO, CSAC’05 Workshop, Conference: ICIES’05, Miami, Date: 01/28/15, Slide: 4 Challenges -- Global ComputingChallenges -- Global Computing  Global Enterprise SystemsGlobal Enterprise Systems  High-assurance systems development and life-High-assurance systems development and life- time managementtime management  Complexity and scale is rapidly increasingComplexity and scale is rapidly increasing  Bio-inspired Models -- AutonomyBio-inspired Models -- Autonomy  devolving software management, maintenance todevolving software management, maintenance to the software itselfthe software itself  Self-managing, self-tuning, self-protecting, ...Self-managing, self-tuning, self-protecting, ...  Need continuous measurement, introspectionNeed continuous measurement, introspection to supportto support  Observed and/or supervised adaptation for;Observed and/or supervised adaptation for;  Safe, predictable,Safe, predictable,  Coordinated, traceable, etc.Coordinated, traceable, etc.
  • 5. Prof. A. Taleb-Bendiab, Talk: WO, CSAC’05 Workshop, Conference: ICIES’05, Miami, Date: 01/28/15, Slide: 5 So far …!So far …!  Current researchCurrent research  Instrumentation middleware services forInstrumentation middleware services for  improved usability and reliability for instance forimproved usability and reliability for instance for  grid-based applications, and ubiquitousgrid-based applications, and ubiquitous computingcomputing  Monitor, control and manage grid users’ applications.Monitor, control and manage grid users’ applications.  Context-awareness and QoS-Aware systemsContext-awareness and QoS-Aware systems  Event-based systemsEvent-based systems  Sensor networks, Etc.Sensor networks, Etc.  Further research is requiredFurther research is required  Management, assurance and fidelity of awarenessManagement, assurance and fidelity of awareness layer is a major concernslayer is a major concerns  Sensors and actuators (effectors) support webSensors and actuators (effectors) support web services and grid computingservices and grid computing  Current models looking at small scale systemsCurrent models looking at small scale systems
  • 6. Prof. A. Taleb-Bendiab, Talk: WO, CSAC’05 Workshop, Conference: ICIES’05, Miami, Date: 01/28/15, Slide: 6 Design Approach Informed byDesign Approach Informed by Machine LearningMachine Learning  Frameworks and ModelsFrameworks and Models  Programming, interaction and/or controlProgramming, interaction and/or control models.models.  Two experiments were conductedTwo experiments were conducted  User Classification and on-demand serviceUser Classification and on-demand service reservationreservation  Autonomic software restore serviceAutonomic software restore service
  • 7. Prof. A. Taleb-Bendiab, Talk: WO, CSAC’05 Workshop, Conference: ICIES’05, Miami, Date: 01/28/15, Slide: 7 Experiment #1: User ClassificationExperiment #1: User Classification  The scenarioThe scenario  Mining service usage models per class ofMining service usage models per class of users for preemptive service reservation andusers for preemptive service reservation and on-demand serviceson-demand services  MethodMethod  Developed an Simulation tool for IntelligentDeveloped an Simulation tool for Intelligent Connected Home, which generate servicesConnected Home, which generate services  Self-Organising Maps (SOM) applied extractSelf-Organising Maps (SOM) applied extract feature or usage modelfeature or usage model  Design and ImplementationDesign and Implementation  To followTo follow
  • 8. Prof. A. Taleb-Bendiab, Talk: WO, CSAC’05 Workshop, Conference: ICIES’05, Miami, Date: 01/28/15, Slide: 8 Design and ImplementationDesign and Implementation  Data generated tool is developed toData generated tool is developed to produce training and test data for thisproduce training and test data for this application.application.  An OGSA and web service compliantAn OGSA and web service compliant SOM middleware service wasSOM middleware service was developeddeveloped  For rapid prototyping a Matlab library forFor rapid prototyping a Matlab library for SOM is used for classificationSOM is used for classification
  • 9. Prof. A. Taleb-Bendiab, Talk: WO, CSAC’05 Workshop, Conference: ICIES’05, Miami, Date: 01/28/15, Slide: 9 SOM Classification Results ForSOM Classification Results For Connected Home Machine DevicesConnected Home Machine Devices • Lights and PlayStationII correlates • Video and Coffee Machine correlates • Video CD and Fans correlates • Vacuum cleaner and Washing machine correlates
  • 10. Prof. A. Taleb-Bendiab, Talk: WO, CSAC’05 Workshop, Conference: ICIES’05, Miami, Date: 01/28/15, Slide: 11 So WhatSo What??  Exploiting ML:Exploiting ML:  anticipate and organize the consumers’ requests inanticipate and organize the consumers’ requests in advanced.advanced.  Job schedule is responsible for managing theJob schedule is responsible for managing the invocations of the services.invocations of the services.  Just-in-time services invocation and usageJust-in-time services invocation and usage  Etc.Etc.  In addition to the presented ML middleware service withIn addition to the presented ML middleware service with automated inclusion and use of usage model for userautomated inclusion and use of usage model for user and service classificationand service classification  Further support is required including;Further support is required including;  Specification and modelling of mined models and theirSpecification and modelling of mined models and their enactment for instance;enactment for instance;  Control and/or actuation modelsControl and/or actuation models  Neptune Meta-Language and Integrated developmentNeptune Meta-Language and Integrated development environment will be used for this.environment will be used for this.
  • 11. Prof. A. Taleb-Bendiab, Talk: WO, CSAC’05 Workshop, Conference: ICIES’05, Miami, Date: 01/28/15, Slide: 12 Neptune Meta-Language #1Neptune Meta-Language #1
  • 12. Prof. A. Taleb-Bendiab, Talk: WO, CSAC’05 Workshop, Conference: ICIES’05, Miami, Date: 01/28/15, Slide: 13 Neptune Meta-Language #2Neptune Meta-Language #2
  • 13. Prof. A. Taleb-Bendiab, Talk: WO, CSAC’05 Workshop, Conference: ICIES’05, Miami, Date: 01/28/15, Slide: 14 Neptune Meta-Language #3Neptune Meta-Language #3
  • 14. Prof. A. Taleb-Bendiab, Talk: WO, CSAC’05 Workshop, Conference: ICIES’05, Miami, Date: 01/28/15, Slide: 15 Conclusions & Further WorkConclusions & Further Work  Prototypes developed using .Net and supportPrototypes developed using .Net and support Web Services StandardsWeb Services Standards  Tested in a number of case studiesTested in a number of case studies  Intelligent Connected HomesIntelligent Connected Homes  E-HealthE-Health  With PlanetLab environmentWith PlanetLab environment  Further workFurther work  Integration of this work with the Neptune Language toIntegration of this work with the Neptune Language to supportsupport  norm-governed web services and architectures.norm-governed web services and architectures.  Situated Autonomic middlewareSituated Autonomic middleware  Integration machine learning services to supportIntegration machine learning services to support danger/novelty detectiondanger/novelty detection  Further evaluation of the frameworkFurther evaluation of the framework
  • 15. Prof. A. Taleb-Bendiab, Talk: WO, CSAC’05 Workshop, Conference: ICIES’05, Miami, Date: 01/28/15, Slide: 16

Notes de l'éditeur

  1. <number>
  2. <number>
  3. <number> “A collection of application services spread over networked computers, which clients use remotely via middleware services” Application services: represent physical and logical concepts such as a printer (hardware service) and a chat room (software service) Middleware services: bridge the gap between application services and network operating system to make life easier for application programmers including; Lookup, transaction, remote-event, etc. 1-reflection techniques are similar to self-adaptive software but self-adaptation exceeds the capabilities of reflection. (“ reflection can modify themselves at run time and change their behaviours but it can’t determine when and what the program needs to modify itself in run time”) 2- one of the key architecture concepts for self-adaptive software is a “reconfiguration “ which refer to a system that switches the control regime based on the runtime situation 3-As a new modelling paradigm self-adaptive software approaches provides two interactions; namely feedforward process from model to the executable and feedback process from execution to reconfiguration 4- it generalize software engineering as its adaptive control in the sense that the system will switch to a different algorithm when the environment changes.
  4. <number>
  5. <number>