SlideShare ist ein Scribd-Unternehmen logo
1 von 20
Downloaden Sie, um offline zu lesen
Adaptive Computation Offloading
                         from Mobile Devices into the Cloud


                              Dejan Kovachev, Tian Yu & Ralf Klamma
                                     RWTH Aachen University
                           Advanced Community Information Systems (ACIS)
                                  kovachev@dbis.rwth-aachen.de
Lehrstuhl Informatik 5
(Information Systems)
   Prof. Dr. M. Jarke
  I5-KYKl-0712-1            This work is licensed under a Creative Commons Attribution-ShareAlike 3.0 Unported License.
{Advanced | ATLAS | Awesome | Aachen}
                          Community Information Systems (ACIS)




                                                Responsive
                              Web Engineering                 Community




                                                                              Web Analytics
                                                   Open
                                                              Visualization
                                                Community
                                                                  and
                                                Information
                                                               Simulation
                                                  Systems



                                                Community      Community
                                                 Support        Analytics




Lehrstuhl Informatik 5
                                                  Requirements
(Information Systems)
   Prof. Dr. M. Jarke
  I5-KYKl-0712-2
                                                   Engineering
Agenda


                          Motivation
                          Offloading & Cloud Computing
                          Related Work
                          Mobile Augmentation Cloud Services
                          Evaluation
                          Conclusions


Lehrstuhl Informatik 5
(Information Systems)
   Prof. Dr. M. Jarke
  I5-KYKl-0712-3
Smartphones:
                                The Mobile Personal Computer
                            Trends
                             – Hardware improvement on mobile devices
                             – “The Swiss Army Knife” smartphone
                             – Decreased privacy
                            However, still not achieved
                             – Longer battery life
                                 – Battery lasts only 1-2 hours for continuous computing
                             – Same quality of experience as on desktops/laptops
                                 – Weaker CPU, Memory, GPU (compared to Desktop PCs)
                             – Running of “heavier” applications
                                 – E.g. OCR, 3D Rendering, Speech Recognition, Image Processing, Video
                                   Editing



Lehrstuhl Informatik 5
                            Need a transparent way to extend mobile devices’ capabilities
(Information Systems)
   Prof. Dr. M. Jarke
  I5-KYKl-0712-4
Mobile + Cloud Computing

                          Cloud computing allows to develop,                     Cloud
                           deploy and run applications that can
                            - Easily grow capacity (scalability),
                                                                                          Cloudlet/Surrogate
                                                                                          (nearby resources)

                                                                          Base Station/

                            - Work fast (performance),                      WiFi AP/
                                                                           Femto cell


                            - No concern to the nature and
                                                                                          Mobile Device
                              location of the underlying infrastructure
                          Mobile cloud computing benefits from
                            - The computation power of the clouds
                            - Anywhere at any time access
Lehrstuhl Informatik 5
(Information Systems)
   Prof. Dr. M. Jarke
  I5-KYKl-0712-5
Offloading
                            Offloading/Augmented execution
                             – Overcome limitations of mobile phones in terms of memory, CPU
                               and battery with external resources
                             – Illusion of virtually much more “powerful” devices
                            Benefits
                             – Stand-alone apps that can work offline
                             – Use of external resources on demand adaptively
                             – Natural privacy
                            Challenges
                             – Distributed app binaries
Lehrstuhl Informatik 5
                             – Computation/Storage offloading decision
                             – Seamless computation/storage integration and consistency
(Information Systems)
   Prof. Dr. M. Jarke
  I5-KYKl-0712-6
Approaches to
                                        Augment Mobile Devices
                            VM-based [Satynarayanan et al. 2009] [Chun and Maniatis 2009] [Kosta et al. 11]
                              – Simple idea, no code to be modified
                              – But, not scalable, too much overhead
                            Methods instrumenting [Ou et al. 2007] [Cuervo et al. 2010]
                              – Create proxy class to forward function calls
                            Service/Module Oriented [Kemp et al. 2010] [Giurgiu et al. 2009]
                              – Application logic is encapsulated in different services


Lehrstuhl Informatik 5
(Information Systems)
   Prof. Dr. M. Jarke
  I5-KYKl-0712-7
Partitioning Algorithms

                          Partitioning determines which part of code should be run locally/remotely
                                                                        Easy to    Optimization    Optimization
                         Method/Project               Model                                                               Profiling
                                                                      Implement      Result            Goal
                         AIDE                    Execution          No            N/A             Component         No
                         [Gu et al. 2002]        Graph                                            Granularity
                         (k+1)                   Multi-cost         No            Global          CPU, Memory,      No
                         [Ou et al. 2007]        Graph                                            Bandwidth

                         AlfredO                 Consumption        No            Local           Interaction       No
                         [Guirgiu et al. 2009]   Graph                                            Latency
                         MAUI                    Call Graph         No            N/A             Power             Yes
                         [Cuervo et al. 2010]                                                     Consumption

                         Scavenger               Multi-info Graph   No            N/A             Not Considering   Yes, dual profile
                         [Kristensen 2010]                                                        Energy Usage

                         MACS                    ILP optimization   Yes           Global          Flexible          Yes

Lehrstuhl Informatik 5
(Information Systems)
   Prof. Dr. M. Jarke
  I5-KYKl-0712-9
MACS Conceptual Approach
                          Metadata for each module
                            -   Offload Type
                            -   Memory Cost
                            -   Code Size
                            -   Transmission Data Size
                          Offloading Mechanisms
                            - Computation Offloading                            [Kovachev et. al. 2010]


                                  Services on Android
                            - Data Offloading
                          Partition Model
Lehrstuhl Informatik 5
                            - Transform into Integer Linear Programming (ILP)
(Information Systems)
   Prof. Dr. M. Jarke
 I5-KYKl-0712-10
MACS Partitioning Model
                          Input for each module Mi
                            memi, codei, ti, sendi, reci,tri
                          Goal
                            min(𝑐 𝑡𝑟𝑎𝑛𝑠𝑓𝑒𝑟 ∗ 𝑤 𝑡𝑟 + 𝑐          𝑚𝑒𝑚𝑜𝑟𝑦   ∗ 𝑤 𝑚𝑒𝑚 + 𝑐 𝐶𝑃𝑈 ∗ 𝑤 𝑐𝑝𝑢 )
                            where c is the cost, w is the weight factor.
                          Constraints
                            - Memory usage
                            - Energy consideration
                            - Execution time consideration
                          Output: xi
Lehrstuhl Informatik 5
(Information Systems)
   Prof. Dr. M. Jarke
 I5-KYKl-0712-11
MACS Architecture




                         Application logic is structured from multiple Android services (Si)
                         Services can be offloaded into the cloud.
Lehrstuhl Informatik 5
(Information Systems)
   Prof. Dr. M. Jarke
 I5-KYKl-0712-12
AIDL Tool
                          Android Interface Definition Language
                            - Define the interface of IPC
                          Embedded code into the generated code
                            - Hidden implementation details to developers
                            - Modification of the compile procedure
                                                                                  MACS
                                                                                  code

                                                                            Generated
                                                                              code




Lehrstuhl Informatik 5
(Information Systems)
   Prof. Dr. M. Jarke
 I5-KYKl-0712-13
Resource Monitor
                            Collect / Store Information
                             –   CPU
                             –   Memory
                             –   Service
                             –   Network
                            Make Offloading Decision
                             – Decision maker to solve optimization problem
                             – Default decision maker can be easily replaced

Lehrstuhl Informatik 5
(Information Systems)
   Prof. Dr. M. Jarke
 I5-KYKl-0712-14
Workflow



                         Service          Client         Monitor                         Cloud



                          Function Call            Register



                                                    Remote



                                                                    InitializeService
                                                                     Install Service
                                                                      TransmitCall
                                                                      Remote File


                                                                   Service NotResult
                                                                      Remote Installed
                                                                       InitializeOK
                                                                         Install OK
                                                                       File Needed
                                                                     Transmit File OK

Lehrstuhl Informatik 5          Result
(Information Systems)
   Prof. Dr. M. Jarke
 I5-KYKl-0712-15
Evaluation

                            Use cases:
                             – A: N-Queens problem on mobile devices
                                 Famous recursion problem
                             – B: Face detection and recognition in video file
                                 Involves huge video processing

                            Setup:                Hardware component        Mobile Device             Desktop

                                                  Processor             ARM Cortex A8 600 MHz   Intel Quad-Core 2.83
                                                                                                GHz
                                                  Memory                256 MB                  8 GB

                                                  WLAN                  Wi-Fi 802.11 b/g        N/A


Lehrstuhl Informatik 5                            OS                    Android 2.2             Windows XP x64
(Information Systems)
   Prof. Dr. M. Jarke                                                                                                  16
 I5-KYKl-0712-16
Results (cont.)
                          Execution Time




                                                       Use Case B
                                            Remote is always the better choice,
                                            nearly 30 times faster.
Lehrstuhl Informatik 5
(Information Systems)
   Prof. Dr. M. Jarke
 I5-KYKl-0712-17
Results (cont.)
                          Execution Time (detailed)
                          Remote




                                                        Use Case B

                                   While offloading, our framework introduces small overhead
Lehrstuhl Informatik 5
(Information Systems)
   Prof. Dr. M. Jarke
 I5-KYKl-0712-18
Results (cont.)
                          Lower Energy Consumption




                                                Use Case B

Lehrstuhl Informatik 5
(Information Systems)
   Prof. Dr. M. Jarke
 I5-KYKl-0712-19
Conclusions and Future Work
                            Conclusions
                             –   Less execution time (especially for huge computation)
                             –   Less energy consumption
                             –   Less CPU instructions
                             –   Low overhead
                            Future work
                             –   Multiple clouds/services
                             –   Runtime behavior estimation
                             –   Automatic offloading
                             –   Model checking
                             –   Integration with the Eclipse plugin
                             –   Support legacy applications

Lehrstuhl Informatik 5
(Information Systems)
   Prof. Dr. M. Jarke
 I5-KYKl-0712-20
Thanks for your attention!
                                  Q&A


Lehrstuhl Informatik 5
(Information Systems)
   Prof. Dr. M. Jarke
 I5-KYKl-0712-21

Weitere ähnliche Inhalte

Ähnlich wie Adaptive Computation Offloading from Mobile Devices into the Cloud

Beyond the Client-Server Architectures: A Survey of Mobile Cloud Techniques
Beyond the Client-Server Architectures: A Survey of Mobile Cloud TechniquesBeyond the Client-Server Architectures: A Survey of Mobile Cloud Techniques
Beyond the Client-Server Architectures: A Survey of Mobile Cloud TechniquesDejan Kovachev
 
Mobile Cloud Computing
Mobile Cloud ComputingMobile Cloud Computing
Mobile Cloud ComputingDejan Kovachev
 
An Embeddable Dashboard for Widget-Based Visual Analytics on Scientific Commu...
An Embeddable Dashboard for Widget-Based Visual Analytics on Scientific Commu...An Embeddable Dashboard for Widget-Based Visual Analytics on Scientific Commu...
An Embeddable Dashboard for Widget-Based Visual Analytics on Scientific Commu...Michael Derntl
 
Enhancing Academic Event Participation with Context-aware and Social Recommen...
Enhancing Academic Event Participation with Context-aware and Social Recommen...Enhancing Academic Event Participation with Context-aware and Social Recommen...
Enhancing Academic Event Participation with Context-aware and Social Recommen...Dejan Kovachev
 
DireWolf - Distributing and Migrating User Interfaces for Widget-based Web Ap...
DireWolf - Distributing and Migrating User Interfaces for Widget-based Web Ap...DireWolf - Distributing and Migrating User Interfaces for Widget-based Web Ap...
DireWolf - Distributing and Migrating User Interfaces for Widget-based Web Ap...Dejan Kovachev
 
SeViAnno 2.0: Web-Enabled Collaborative Semantic Video Annotation Beyond the ...
SeViAnno 2.0: Web-Enabled CollaborativeSemantic Video Annotation Beyond the ...SeViAnno 2.0: Web-Enabled CollaborativeSemantic Video Annotation Beyond the ...
SeViAnno 2.0: Web-Enabled Collaborative Semantic Video Annotation Beyond the ...Nicolaescu Petru
 
A Cloud Multimedia Platform
A Cloud Multimedia PlatformA Cloud Multimedia Platform
A Cloud Multimedia PlatformDejan Kovachev
 
Mobile Multimedia Cloud Computing and the Web
Mobile Multimedia Cloud Computing and the WebMobile Multimedia Cloud Computing and the Web
Mobile Multimedia Cloud Computing and the WebDejan Kovachev
 
Supporting Professional Communities in the Next Web
Supporting Professional Communities in the Next Web Supporting Professional Communities in the Next Web
Supporting Professional Communities in the Next Web Ralf Klamma
 
Big Data Beyond Hadoop*: Research Directions for the Future
Big Data Beyond Hadoop*: Research Directions for the FutureBig Data Beyond Hadoop*: Research Directions for the Future
Big Data Beyond Hadoop*: Research Directions for the FutureOdinot Stanislas
 
Greenplum Database Overview
Greenplum Database Overview Greenplum Database Overview
Greenplum Database Overview EMC
 
Clextra tablet applications
Clextra tablet applicationsClextra tablet applications
Clextra tablet applicationsEdgevalue
 
Model-Driven Mashup Personal Learning Environments
Model-Driven Mashup Personal Learning EnvironmentsModel-Driven Mashup Personal Learning Environments
Model-Driven Mashup Personal Learning EnvironmentsMohamed Amine Chatti
 
Browser-Based Collaborative Modeling in Near Real-Time
Browser-Based Collaborative Modeling in Near Real-TimeBrowser-Based Collaborative Modeling in Near Real-Time
Browser-Based Collaborative Modeling in Near Real-TimeNicolaescu Petru
 
A Methodology and Tool Support for Widget-based Web Application Development
A Methodology and Tool Support for Widget-based Web Application DevelopmentA Methodology and Tool Support for Widget-based Web Application Development
A Methodology and Tool Support for Widget-based Web Application DevelopmentNicolaescu Petru
 
Fujitsu keynote at Oracle OpenWorld 2012
Fujitsu keynote at Oracle OpenWorld 2012 Fujitsu keynote at Oracle OpenWorld 2012
Fujitsu keynote at Oracle OpenWorld 2012 Fujitsu Global
 
Designing Secure Cisco Data Centers
Designing Secure Cisco Data CentersDesigning Secure Cisco Data Centers
Designing Secure Cisco Data CentersCisco Russia
 
IRJET- Analysis of Forensics Tools in Cloud Environment
IRJET-  	  Analysis of Forensics Tools in Cloud EnvironmentIRJET-  	  Analysis of Forensics Tools in Cloud Environment
IRJET- Analysis of Forensics Tools in Cloud EnvironmentIRJET Journal
 

Ähnlich wie Adaptive Computation Offloading from Mobile Devices into the Cloud (20)

Beyond the Client-Server Architectures: A Survey of Mobile Cloud Techniques
Beyond the Client-Server Architectures: A Survey of Mobile Cloud TechniquesBeyond the Client-Server Architectures: A Survey of Mobile Cloud Techniques
Beyond the Client-Server Architectures: A Survey of Mobile Cloud Techniques
 
Mobile Cloud Computing
Mobile Cloud ComputingMobile Cloud Computing
Mobile Cloud Computing
 
An Embeddable Dashboard for Widget-Based Visual Analytics on Scientific Commu...
An Embeddable Dashboard for Widget-Based Visual Analytics on Scientific Commu...An Embeddable Dashboard for Widget-Based Visual Analytics on Scientific Commu...
An Embeddable Dashboard for Widget-Based Visual Analytics on Scientific Commu...
 
Enhancing Academic Event Participation with Context-aware and Social Recommen...
Enhancing Academic Event Participation with Context-aware and Social Recommen...Enhancing Academic Event Participation with Context-aware and Social Recommen...
Enhancing Academic Event Participation with Context-aware and Social Recommen...
 
DireWolf - Distributing and Migrating User Interfaces for Widget-based Web Ap...
DireWolf - Distributing and Migrating User Interfaces for Widget-based Web Ap...DireWolf - Distributing and Migrating User Interfaces for Widget-based Web Ap...
DireWolf - Distributing and Migrating User Interfaces for Widget-based Web Ap...
 
SeViAnno 2.0: Web-Enabled Collaborative Semantic Video Annotation Beyond the ...
SeViAnno 2.0: Web-Enabled CollaborativeSemantic Video Annotation Beyond the ...SeViAnno 2.0: Web-Enabled CollaborativeSemantic Video Annotation Beyond the ...
SeViAnno 2.0: Web-Enabled Collaborative Semantic Video Annotation Beyond the ...
 
A Cloud Multimedia Platform
A Cloud Multimedia PlatformA Cloud Multimedia Platform
A Cloud Multimedia Platform
 
Mobile Multimedia Cloud Computing and the Web
Mobile Multimedia Cloud Computing and the WebMobile Multimedia Cloud Computing and the Web
Mobile Multimedia Cloud Computing and the Web
 
Supporting Professional Communities in the Next Web
Supporting Professional Communities in the Next Web Supporting Professional Communities in the Next Web
Supporting Professional Communities in the Next Web
 
Big Data Beyond Hadoop*: Research Directions for the Future
Big Data Beyond Hadoop*: Research Directions for the FutureBig Data Beyond Hadoop*: Research Directions for the Future
Big Data Beyond Hadoop*: Research Directions for the Future
 
Greenplum Database Overview
Greenplum Database Overview Greenplum Database Overview
Greenplum Database Overview
 
Chapter 01
Chapter 01Chapter 01
Chapter 01
 
Clextra tablet applications
Clextra tablet applicationsClextra tablet applications
Clextra tablet applications
 
The Network Enabled EOC
The Network Enabled EOCThe Network Enabled EOC
The Network Enabled EOC
 
Model-Driven Mashup Personal Learning Environments
Model-Driven Mashup Personal Learning EnvironmentsModel-Driven Mashup Personal Learning Environments
Model-Driven Mashup Personal Learning Environments
 
Browser-Based Collaborative Modeling in Near Real-Time
Browser-Based Collaborative Modeling in Near Real-TimeBrowser-Based Collaborative Modeling in Near Real-Time
Browser-Based Collaborative Modeling in Near Real-Time
 
A Methodology and Tool Support for Widget-based Web Application Development
A Methodology and Tool Support for Widget-based Web Application DevelopmentA Methodology and Tool Support for Widget-based Web Application Development
A Methodology and Tool Support for Widget-based Web Application Development
 
Fujitsu keynote at Oracle OpenWorld 2012
Fujitsu keynote at Oracle OpenWorld 2012 Fujitsu keynote at Oracle OpenWorld 2012
Fujitsu keynote at Oracle OpenWorld 2012
 
Designing Secure Cisco Data Centers
Designing Secure Cisco Data CentersDesigning Secure Cisco Data Centers
Designing Secure Cisco Data Centers
 
IRJET- Analysis of Forensics Tools in Cloud Environment
IRJET-  	  Analysis of Forensics Tools in Cloud EnvironmentIRJET-  	  Analysis of Forensics Tools in Cloud Environment
IRJET- Analysis of Forensics Tools in Cloud Environment
 

Kürzlich hochgeladen

KubeConEU24-Monitoring Kubernetes and Cloud Spend with OpenCost
KubeConEU24-Monitoring Kubernetes and Cloud Spend with OpenCostKubeConEU24-Monitoring Kubernetes and Cloud Spend with OpenCost
KubeConEU24-Monitoring Kubernetes and Cloud Spend with OpenCostMatt Ray
 
Building AI-Driven Apps Using Semantic Kernel.pptx
Building AI-Driven Apps Using Semantic Kernel.pptxBuilding AI-Driven Apps Using Semantic Kernel.pptx
Building AI-Driven Apps Using Semantic Kernel.pptxUdaiappa Ramachandran
 
UiPath Studio Web workshop series - Day 8
UiPath Studio Web workshop series - Day 8UiPath Studio Web workshop series - Day 8
UiPath Studio Web workshop series - Day 8DianaGray10
 
Crea il tuo assistente AI con lo Stregatto (open source python framework)
Crea il tuo assistente AI con lo Stregatto (open source python framework)Crea il tuo assistente AI con lo Stregatto (open source python framework)
Crea il tuo assistente AI con lo Stregatto (open source python framework)Commit University
 
UWB Technology for Enhanced Indoor and Outdoor Positioning in Physiological M...
UWB Technology for Enhanced Indoor and Outdoor Positioning in Physiological M...UWB Technology for Enhanced Indoor and Outdoor Positioning in Physiological M...
UWB Technology for Enhanced Indoor and Outdoor Positioning in Physiological M...UbiTrack UK
 
Artificial Intelligence & SEO Trends for 2024
Artificial Intelligence & SEO Trends for 2024Artificial Intelligence & SEO Trends for 2024
Artificial Intelligence & SEO Trends for 2024D Cloud Solutions
 
Basic Building Blocks of Internet of Things.
Basic Building Blocks of Internet of Things.Basic Building Blocks of Internet of Things.
Basic Building Blocks of Internet of Things.YounusS2
 
9 Steps For Building Winning Founding Team
9 Steps For Building Winning Founding Team9 Steps For Building Winning Founding Team
9 Steps For Building Winning Founding TeamAdam Moalla
 
Cybersecurity Workshop #1.pptx
Cybersecurity Workshop #1.pptxCybersecurity Workshop #1.pptx
Cybersecurity Workshop #1.pptxGDSC PJATK
 
UiPath Platform: The Backend Engine Powering Your Automation - Session 1
UiPath Platform: The Backend Engine Powering Your Automation - Session 1UiPath Platform: The Backend Engine Powering Your Automation - Session 1
UiPath Platform: The Backend Engine Powering Your Automation - Session 1DianaGray10
 
Igniting Next Level Productivity with AI-Infused Data Integration Workflows
Igniting Next Level Productivity with AI-Infused Data Integration WorkflowsIgniting Next Level Productivity with AI-Infused Data Integration Workflows
Igniting Next Level Productivity with AI-Infused Data Integration WorkflowsSafe Software
 
Using IESVE for Loads, Sizing and Heat Pump Modeling to Achieve Decarbonization
Using IESVE for Loads, Sizing and Heat Pump Modeling to Achieve DecarbonizationUsing IESVE for Loads, Sizing and Heat Pump Modeling to Achieve Decarbonization
Using IESVE for Loads, Sizing and Heat Pump Modeling to Achieve DecarbonizationIES VE
 
How Accurate are Carbon Emissions Projections?
How Accurate are Carbon Emissions Projections?How Accurate are Carbon Emissions Projections?
How Accurate are Carbon Emissions Projections?IES VE
 
NIST Cybersecurity Framework (CSF) 2.0 Workshop
NIST Cybersecurity Framework (CSF) 2.0 WorkshopNIST Cybersecurity Framework (CSF) 2.0 Workshop
NIST Cybersecurity Framework (CSF) 2.0 WorkshopBachir Benyammi
 
Nanopower In Semiconductor Industry.pdf
Nanopower  In Semiconductor Industry.pdfNanopower  In Semiconductor Industry.pdf
Nanopower In Semiconductor Industry.pdfPedro Manuel
 
AI Fame Rush Review – Virtual Influencer Creation In Just Minutes
AI Fame Rush Review – Virtual Influencer Creation In Just MinutesAI Fame Rush Review – Virtual Influencer Creation In Just Minutes
AI Fame Rush Review – Virtual Influencer Creation In Just MinutesMd Hossain Ali
 
Anypoint Code Builder , Google Pub sub connector and MuleSoft RPA
Anypoint Code Builder , Google Pub sub connector and MuleSoft RPAAnypoint Code Builder , Google Pub sub connector and MuleSoft RPA
Anypoint Code Builder , Google Pub sub connector and MuleSoft RPAshyamraj55
 
OpenShift Commons Paris - Choose Your Own Observability Adventure
OpenShift Commons Paris - Choose Your Own Observability AdventureOpenShift Commons Paris - Choose Your Own Observability Adventure
OpenShift Commons Paris - Choose Your Own Observability AdventureEric D. Schabell
 
Secure your environment with UiPath and CyberArk technologies - Session 1
Secure your environment with UiPath and CyberArk technologies - Session 1Secure your environment with UiPath and CyberArk technologies - Session 1
Secure your environment with UiPath and CyberArk technologies - Session 1DianaGray10
 

Kürzlich hochgeladen (20)

KubeConEU24-Monitoring Kubernetes and Cloud Spend with OpenCost
KubeConEU24-Monitoring Kubernetes and Cloud Spend with OpenCostKubeConEU24-Monitoring Kubernetes and Cloud Spend with OpenCost
KubeConEU24-Monitoring Kubernetes and Cloud Spend with OpenCost
 
201610817 - edge part1
201610817 - edge part1201610817 - edge part1
201610817 - edge part1
 
Building AI-Driven Apps Using Semantic Kernel.pptx
Building AI-Driven Apps Using Semantic Kernel.pptxBuilding AI-Driven Apps Using Semantic Kernel.pptx
Building AI-Driven Apps Using Semantic Kernel.pptx
 
UiPath Studio Web workshop series - Day 8
UiPath Studio Web workshop series - Day 8UiPath Studio Web workshop series - Day 8
UiPath Studio Web workshop series - Day 8
 
Crea il tuo assistente AI con lo Stregatto (open source python framework)
Crea il tuo assistente AI con lo Stregatto (open source python framework)Crea il tuo assistente AI con lo Stregatto (open source python framework)
Crea il tuo assistente AI con lo Stregatto (open source python framework)
 
UWB Technology for Enhanced Indoor and Outdoor Positioning in Physiological M...
UWB Technology for Enhanced Indoor and Outdoor Positioning in Physiological M...UWB Technology for Enhanced Indoor and Outdoor Positioning in Physiological M...
UWB Technology for Enhanced Indoor and Outdoor Positioning in Physiological M...
 
Artificial Intelligence & SEO Trends for 2024
Artificial Intelligence & SEO Trends for 2024Artificial Intelligence & SEO Trends for 2024
Artificial Intelligence & SEO Trends for 2024
 
Basic Building Blocks of Internet of Things.
Basic Building Blocks of Internet of Things.Basic Building Blocks of Internet of Things.
Basic Building Blocks of Internet of Things.
 
9 Steps For Building Winning Founding Team
9 Steps For Building Winning Founding Team9 Steps For Building Winning Founding Team
9 Steps For Building Winning Founding Team
 
Cybersecurity Workshop #1.pptx
Cybersecurity Workshop #1.pptxCybersecurity Workshop #1.pptx
Cybersecurity Workshop #1.pptx
 
UiPath Platform: The Backend Engine Powering Your Automation - Session 1
UiPath Platform: The Backend Engine Powering Your Automation - Session 1UiPath Platform: The Backend Engine Powering Your Automation - Session 1
UiPath Platform: The Backend Engine Powering Your Automation - Session 1
 
Igniting Next Level Productivity with AI-Infused Data Integration Workflows
Igniting Next Level Productivity with AI-Infused Data Integration WorkflowsIgniting Next Level Productivity with AI-Infused Data Integration Workflows
Igniting Next Level Productivity with AI-Infused Data Integration Workflows
 
Using IESVE for Loads, Sizing and Heat Pump Modeling to Achieve Decarbonization
Using IESVE for Loads, Sizing and Heat Pump Modeling to Achieve DecarbonizationUsing IESVE for Loads, Sizing and Heat Pump Modeling to Achieve Decarbonization
Using IESVE for Loads, Sizing and Heat Pump Modeling to Achieve Decarbonization
 
How Accurate are Carbon Emissions Projections?
How Accurate are Carbon Emissions Projections?How Accurate are Carbon Emissions Projections?
How Accurate are Carbon Emissions Projections?
 
NIST Cybersecurity Framework (CSF) 2.0 Workshop
NIST Cybersecurity Framework (CSF) 2.0 WorkshopNIST Cybersecurity Framework (CSF) 2.0 Workshop
NIST Cybersecurity Framework (CSF) 2.0 Workshop
 
Nanopower In Semiconductor Industry.pdf
Nanopower  In Semiconductor Industry.pdfNanopower  In Semiconductor Industry.pdf
Nanopower In Semiconductor Industry.pdf
 
AI Fame Rush Review – Virtual Influencer Creation In Just Minutes
AI Fame Rush Review – Virtual Influencer Creation In Just MinutesAI Fame Rush Review – Virtual Influencer Creation In Just Minutes
AI Fame Rush Review – Virtual Influencer Creation In Just Minutes
 
Anypoint Code Builder , Google Pub sub connector and MuleSoft RPA
Anypoint Code Builder , Google Pub sub connector and MuleSoft RPAAnypoint Code Builder , Google Pub sub connector and MuleSoft RPA
Anypoint Code Builder , Google Pub sub connector and MuleSoft RPA
 
OpenShift Commons Paris - Choose Your Own Observability Adventure
OpenShift Commons Paris - Choose Your Own Observability AdventureOpenShift Commons Paris - Choose Your Own Observability Adventure
OpenShift Commons Paris - Choose Your Own Observability Adventure
 
Secure your environment with UiPath and CyberArk technologies - Session 1
Secure your environment with UiPath and CyberArk technologies - Session 1Secure your environment with UiPath and CyberArk technologies - Session 1
Secure your environment with UiPath and CyberArk technologies - Session 1
 

Adaptive Computation Offloading from Mobile Devices into the Cloud

  • 1. Adaptive Computation Offloading from Mobile Devices into the Cloud Dejan Kovachev, Tian Yu & Ralf Klamma RWTH Aachen University Advanced Community Information Systems (ACIS) kovachev@dbis.rwth-aachen.de Lehrstuhl Informatik 5 (Information Systems) Prof. Dr. M. Jarke I5-KYKl-0712-1 This work is licensed under a Creative Commons Attribution-ShareAlike 3.0 Unported License.
  • 2. {Advanced | ATLAS | Awesome | Aachen} Community Information Systems (ACIS) Responsive Web Engineering Community Web Analytics Open Visualization Community and Information Simulation Systems Community Community Support Analytics Lehrstuhl Informatik 5 Requirements (Information Systems) Prof. Dr. M. Jarke I5-KYKl-0712-2 Engineering
  • 3. Agenda  Motivation  Offloading & Cloud Computing  Related Work  Mobile Augmentation Cloud Services  Evaluation  Conclusions Lehrstuhl Informatik 5 (Information Systems) Prof. Dr. M. Jarke I5-KYKl-0712-3
  • 4. Smartphones: The Mobile Personal Computer  Trends – Hardware improvement on mobile devices – “The Swiss Army Knife” smartphone – Decreased privacy  However, still not achieved – Longer battery life – Battery lasts only 1-2 hours for continuous computing – Same quality of experience as on desktops/laptops – Weaker CPU, Memory, GPU (compared to Desktop PCs) – Running of “heavier” applications – E.g. OCR, 3D Rendering, Speech Recognition, Image Processing, Video Editing Lehrstuhl Informatik 5  Need a transparent way to extend mobile devices’ capabilities (Information Systems) Prof. Dr. M. Jarke I5-KYKl-0712-4
  • 5. Mobile + Cloud Computing  Cloud computing allows to develop, Cloud deploy and run applications that can - Easily grow capacity (scalability), Cloudlet/Surrogate (nearby resources) Base Station/ - Work fast (performance), WiFi AP/ Femto cell - No concern to the nature and Mobile Device location of the underlying infrastructure  Mobile cloud computing benefits from - The computation power of the clouds - Anywhere at any time access Lehrstuhl Informatik 5 (Information Systems) Prof. Dr. M. Jarke I5-KYKl-0712-5
  • 6. Offloading  Offloading/Augmented execution – Overcome limitations of mobile phones in terms of memory, CPU and battery with external resources – Illusion of virtually much more “powerful” devices  Benefits – Stand-alone apps that can work offline – Use of external resources on demand adaptively – Natural privacy  Challenges – Distributed app binaries Lehrstuhl Informatik 5 – Computation/Storage offloading decision – Seamless computation/storage integration and consistency (Information Systems) Prof. Dr. M. Jarke I5-KYKl-0712-6
  • 7. Approaches to Augment Mobile Devices  VM-based [Satynarayanan et al. 2009] [Chun and Maniatis 2009] [Kosta et al. 11] – Simple idea, no code to be modified – But, not scalable, too much overhead  Methods instrumenting [Ou et al. 2007] [Cuervo et al. 2010] – Create proxy class to forward function calls  Service/Module Oriented [Kemp et al. 2010] [Giurgiu et al. 2009] – Application logic is encapsulated in different services Lehrstuhl Informatik 5 (Information Systems) Prof. Dr. M. Jarke I5-KYKl-0712-7
  • 8. Partitioning Algorithms  Partitioning determines which part of code should be run locally/remotely Easy to Optimization Optimization Method/Project Model Profiling Implement Result Goal AIDE Execution No N/A Component No [Gu et al. 2002] Graph Granularity (k+1) Multi-cost No Global CPU, Memory, No [Ou et al. 2007] Graph Bandwidth AlfredO Consumption No Local Interaction No [Guirgiu et al. 2009] Graph Latency MAUI Call Graph No N/A Power Yes [Cuervo et al. 2010] Consumption Scavenger Multi-info Graph No N/A Not Considering Yes, dual profile [Kristensen 2010] Energy Usage MACS ILP optimization Yes Global Flexible Yes Lehrstuhl Informatik 5 (Information Systems) Prof. Dr. M. Jarke I5-KYKl-0712-9
  • 9. MACS Conceptual Approach  Metadata for each module - Offload Type - Memory Cost - Code Size - Transmission Data Size  Offloading Mechanisms - Computation Offloading [Kovachev et. al. 2010]  Services on Android - Data Offloading  Partition Model Lehrstuhl Informatik 5 - Transform into Integer Linear Programming (ILP) (Information Systems) Prof. Dr. M. Jarke I5-KYKl-0712-10
  • 10. MACS Partitioning Model  Input for each module Mi memi, codei, ti, sendi, reci,tri  Goal min(𝑐 𝑡𝑟𝑎𝑛𝑠𝑓𝑒𝑟 ∗ 𝑤 𝑡𝑟 + 𝑐 𝑚𝑒𝑚𝑜𝑟𝑦 ∗ 𝑤 𝑚𝑒𝑚 + 𝑐 𝐶𝑃𝑈 ∗ 𝑤 𝑐𝑝𝑢 ) where c is the cost, w is the weight factor.  Constraints - Memory usage - Energy consideration - Execution time consideration  Output: xi Lehrstuhl Informatik 5 (Information Systems) Prof. Dr. M. Jarke I5-KYKl-0712-11
  • 11. MACS Architecture Application logic is structured from multiple Android services (Si) Services can be offloaded into the cloud. Lehrstuhl Informatik 5 (Information Systems) Prof. Dr. M. Jarke I5-KYKl-0712-12
  • 12. AIDL Tool  Android Interface Definition Language - Define the interface of IPC  Embedded code into the generated code - Hidden implementation details to developers - Modification of the compile procedure MACS code Generated code Lehrstuhl Informatik 5 (Information Systems) Prof. Dr. M. Jarke I5-KYKl-0712-13
  • 13. Resource Monitor  Collect / Store Information – CPU – Memory – Service – Network  Make Offloading Decision – Decision maker to solve optimization problem – Default decision maker can be easily replaced Lehrstuhl Informatik 5 (Information Systems) Prof. Dr. M. Jarke I5-KYKl-0712-14
  • 14. Workflow Service Client Monitor Cloud Function Call Register Remote InitializeService Install Service TransmitCall Remote File Service NotResult Remote Installed InitializeOK Install OK File Needed Transmit File OK Lehrstuhl Informatik 5 Result (Information Systems) Prof. Dr. M. Jarke I5-KYKl-0712-15
  • 15. Evaluation  Use cases: – A: N-Queens problem on mobile devices Famous recursion problem – B: Face detection and recognition in video file Involves huge video processing  Setup: Hardware component Mobile Device Desktop Processor ARM Cortex A8 600 MHz Intel Quad-Core 2.83 GHz Memory 256 MB 8 GB WLAN Wi-Fi 802.11 b/g N/A Lehrstuhl Informatik 5 OS Android 2.2 Windows XP x64 (Information Systems) Prof. Dr. M. Jarke 16 I5-KYKl-0712-16
  • 16. Results (cont.)  Execution Time Use Case B Remote is always the better choice, nearly 30 times faster. Lehrstuhl Informatik 5 (Information Systems) Prof. Dr. M. Jarke I5-KYKl-0712-17
  • 17. Results (cont.)  Execution Time (detailed) Remote Use Case B While offloading, our framework introduces small overhead Lehrstuhl Informatik 5 (Information Systems) Prof. Dr. M. Jarke I5-KYKl-0712-18
  • 18. Results (cont.)  Lower Energy Consumption Use Case B Lehrstuhl Informatik 5 (Information Systems) Prof. Dr. M. Jarke I5-KYKl-0712-19
  • 19. Conclusions and Future Work  Conclusions – Less execution time (especially for huge computation) – Less energy consumption – Less CPU instructions – Low overhead  Future work – Multiple clouds/services – Runtime behavior estimation – Automatic offloading – Model checking – Integration with the Eclipse plugin – Support legacy applications Lehrstuhl Informatik 5 (Information Systems) Prof. Dr. M. Jarke I5-KYKl-0712-20
  • 20. Thanks for your attention! Q&A Lehrstuhl Informatik 5 (Information Systems) Prof. Dr. M. Jarke I5-KYKl-0712-21