SlideShare a Scribd company logo
1 of 12
Download to read offline
Quality of Service Channelling for
Latency Sensitive Edge Applications
Atakan Aral, Ivona Brandić
Institute of Software Technology and Interactive Systems
Vienna University of Technology
{atakan.aral, ivona.brandic}@tuwien.ac.at
http://rucon.ec.tuwien.ac.at/
A Dilemma in Edge
Edge applications are;
• Latency sensitive
• Data dependent
• Hence, geographically distributed / replicated.
2
NTT Press Releases, 23.01.2014
A Dilemma in Edge
However, Edge data centers are;
• Lacking expensive support systems
• Prone to failures (hardware, software, network, …)
• Hence, unreliable for guaranteeing QoS (e.g. response
time or throughput).
3
Cost of Failures
Average downtime duration:
18:30 hours
Cost of downtime:
$700,000 per hour
Cascading failures
• US-EAST-1 on February 28th
• Two S3 subsystems were
shut down accidentally
• 11 hours of disruption not
only for S3 but also EC2
 Adobe services, Bitbucket,
Quora, Coursera, Docker,
Github, LonelyPlanet, …
 Connected lightbulbs,
thermostats, … 4
Operational,
45%
Natural,
35%
Human,
19%
Other, 1%
Failure causes
Sources: https://www.infrascale.com, https://aws.amazon.com
Challenges
5
• Recovery cost is too high.
Reactive methods alone are
not sufficient
• Failures have various characteristics:
cause, effect on availability, etc.
• Failures are statistically dependent to
each other.
• Dependencies are dynamic.
• Optimization is online, failure prediction
should be done in real-time.
Proactive methods require
failure prediction
Proposed Solution
6
Solution Details
7
Experimental Setup
Server failure data collected by Los Alamos National
Laboratory (LANL)
• Collected between 1999-2005
• 19.436 failures of 122 types
• 3.577 servers from 22 systems
8
Results
9
Please, refer to the paper for additional simulation results.
Conclusion
Edge computing requires intelligent and efficient
mechanisms to cope with unreliability.
Key message: Exploiting the dependencies between
different failures allow us to predict them quite
accurately.
Current work:
• Link failures (e.g. network congestion, router outage, etc.)
• Dependencies between Edge nodes (e.g. geographical,
cascading, etc.)
• Node availability  Distributed service availability
• http://rucon.ec.tuwien.ac.at/
10
Thank you for your attention!
Atakan Aral, Ivona Brandić
Institute of Software Technology and Interactive Systems
Vienna University of Technology
{atakan.aral, ivona.brandic}@tuwien.ac.at
http://rucon.ec.tuwien.ac.at/
Simulation Results
Number of SLO violations for each configuration using Bayesian Network Estimation (BN) or only Prior Knowledge (PK)

More Related Content

What's hot

Artificial neural network for misuse detection
Artificial neural network for misuse detectionArtificial neural network for misuse detection
Artificial neural network for misuse detectionSajan Sahu
 
IEEE 2014 JAVA NETWORK SECURITY PROJECTS Tradeoff between reliability and sec...
IEEE 2014 JAVA NETWORK SECURITY PROJECTS Tradeoff between reliability and sec...IEEE 2014 JAVA NETWORK SECURITY PROJECTS Tradeoff between reliability and sec...
IEEE 2014 JAVA NETWORK SECURITY PROJECTS Tradeoff between reliability and sec...IEEEGLOBALSOFTSTUDENTPROJECTS
 
Model-Simulation-and-Measurement-Based Systems Engineering of Power System Sy...
Model-Simulation-and-Measurement-Based Systems Engineering of Power System Sy...Model-Simulation-and-Measurement-Based Systems Engineering of Power System Sy...
Model-Simulation-and-Measurement-Based Systems Engineering of Power System Sy...Luigi Vanfretti
 
Applications of WSN
Applications of WSNApplications of WSN
Applications of WSNADEEBANADEEM
 
RaDEn : A Scalable and Efficient Platform for Engineering Radiation Data
RaDEn :  A Scalable and Efficient Platform for Engineering Radiation DataRaDEn :  A Scalable and Efficient Platform for Engineering Radiation Data
RaDEn : A Scalable and Efficient Platform for Engineering Radiation DataHadi Fadlallah
 

What's hot (7)

Artificial neural networks
Artificial neural networks Artificial neural networks
Artificial neural networks
 
Artificial neural network for misuse detection
Artificial neural network for misuse detectionArtificial neural network for misuse detection
Artificial neural network for misuse detection
 
Resume Haley Roughton
Resume Haley RoughtonResume Haley Roughton
Resume Haley Roughton
 
IEEE 2014 JAVA NETWORK SECURITY PROJECTS Tradeoff between reliability and sec...
IEEE 2014 JAVA NETWORK SECURITY PROJECTS Tradeoff between reliability and sec...IEEE 2014 JAVA NETWORK SECURITY PROJECTS Tradeoff between reliability and sec...
IEEE 2014 JAVA NETWORK SECURITY PROJECTS Tradeoff between reliability and sec...
 
Model-Simulation-and-Measurement-Based Systems Engineering of Power System Sy...
Model-Simulation-and-Measurement-Based Systems Engineering of Power System Sy...Model-Simulation-and-Measurement-Based Systems Engineering of Power System Sy...
Model-Simulation-and-Measurement-Based Systems Engineering of Power System Sy...
 
Applications of WSN
Applications of WSNApplications of WSN
Applications of WSN
 
RaDEn : A Scalable and Efficient Platform for Engineering Radiation Data
RaDEn :  A Scalable and Efficient Platform for Engineering Radiation DataRaDEn :  A Scalable and Efficient Platform for Engineering Radiation Data
RaDEn : A Scalable and Efficient Platform for Engineering Radiation Data
 

Similar to Quality of Service Channelling for Latency Sensitive Edge Applications

CS5032 Lecture 20: Dependable infrastructure 2
CS5032 Lecture 20: Dependable infrastructure 2CS5032 Lecture 20: Dependable infrastructure 2
CS5032 Lecture 20: Dependable infrastructure 2John Rooksby
 
Deep Learning Fault Detection Algorithms in WSNs
Deep Learning Fault Detection Algorithms in WSNsDeep Learning Fault Detection Algorithms in WSNs
Deep Learning Fault Detection Algorithms in WSNsIRJET Journal
 
Real time visualization of structured things
Real time visualization of structured thingsReal time visualization of structured things
Real time visualization of structured thingsNurul Amin Choudhury
 
Proactive Population-Risk Based Defense Against Denial of Cyber-Physical Serv...
Proactive Population-Risk Based Defense Against Denial of Cyber-Physical Serv...Proactive Population-Risk Based Defense Against Denial of Cyber-Physical Serv...
Proactive Population-Risk Based Defense Against Denial of Cyber-Physical Serv...IRJET Journal
 
Distributed Checkpointing on an Enterprise Desktop Grid
Distributed Checkpointing on an Enterprise Desktop GridDistributed Checkpointing on an Enterprise Desktop Grid
Distributed Checkpointing on an Enterprise Desktop Gridbrent.wilson
 
Mastering IoT Design: Sense, Process, Connect: Processing: Turning IoT Data i...
Mastering IoT Design: Sense, Process, Connect: Processing: Turning IoT Data i...Mastering IoT Design: Sense, Process, Connect: Processing: Turning IoT Data i...
Mastering IoT Design: Sense, Process, Connect: Processing: Turning IoT Data i...Deepak Shankar
 
A Survey of Fault Tolerance Methods in Wireless Sensor Networks
A Survey of Fault Tolerance Methods in Wireless Sensor NetworksA Survey of Fault Tolerance Methods in Wireless Sensor Networks
A Survey of Fault Tolerance Methods in Wireless Sensor NetworksIRJET Journal
 
ON FAULT TOLERANCE OF RESOURCES IN COMPUTATIONAL GRIDS
ON FAULT TOLERANCE OF RESOURCES IN COMPUTATIONAL GRIDSON FAULT TOLERANCE OF RESOURCES IN COMPUTATIONAL GRIDS
ON FAULT TOLERANCE OF RESOURCES IN COMPUTATIONAL GRIDSijgca
 
Design and Analysis of a Broadcast Network Using Logical Segmentation
Design and Analysis of a Broadcast Network Using Logical SegmentationDesign and Analysis of a Broadcast Network Using Logical Segmentation
Design and Analysis of a Broadcast Network Using Logical SegmentationTELKOMNIKA JOURNAL
 
IRJET- Iot Based Underground Cable Line Fault Detection
IRJET- Iot Based Underground Cable Line Fault DetectionIRJET- Iot Based Underground Cable Line Fault Detection
IRJET- Iot Based Underground Cable Line Fault DetectionIRJET Journal
 
IRJET- A Wireless Sensor Network based Border Monitoring System using Clusters
IRJET- A Wireless Sensor Network based Border Monitoring System using ClustersIRJET- A Wireless Sensor Network based Border Monitoring System using Clusters
IRJET- A Wireless Sensor Network based Border Monitoring System using ClustersIRJET Journal
 
D. Ardagna - PARVIS - Performance mAnagement of VIrtualized Systems
D. Ardagna - PARVIS - Performance mAnagement of VIrtualized SystemsD. Ardagna - PARVIS - Performance mAnagement of VIrtualized Systems
D. Ardagna - PARVIS - Performance mAnagement of VIrtualized SystemsFolco Bombardieri
 
Edge Computing TS.pptx
Edge Computing TS.pptxEdge Computing TS.pptx
Edge Computing TS.pptxMilanap1
 
High Fault Coverage For On Chip Network Using Priority Based Routing Algorithm
High Fault Coverage For On Chip Network Using Priority Based Routing AlgorithmHigh Fault Coverage For On Chip Network Using Priority Based Routing Algorithm
High Fault Coverage For On Chip Network Using Priority Based Routing AlgorithmIJSRD
 
High Fault Coverage For On Chip Network Using Priority Based Routing Algorithm
High Fault Coverage For On Chip Network Using Priority Based Routing AlgorithmHigh Fault Coverage For On Chip Network Using Priority Based Routing Algorithm
High Fault Coverage For On Chip Network Using Priority Based Routing AlgorithmIJSRD
 
A Comparative Review on Reliability and Fault Tolerance Enhancement Protocols...
A Comparative Review on Reliability and Fault Tolerance Enhancement Protocols...A Comparative Review on Reliability and Fault Tolerance Enhancement Protocols...
A Comparative Review on Reliability and Fault Tolerance Enhancement Protocols...IRJET Journal
 
System interconnect architecture
System interconnect architectureSystem interconnect architecture
System interconnect architectureGagan Kumar
 
VL2: A scalable and flexible Data Center Network
VL2: A scalable and flexible Data Center NetworkVL2: A scalable and flexible Data Center Network
VL2: A scalable and flexible Data Center NetworkAnkita Mahajan
 

Similar to Quality of Service Channelling for Latency Sensitive Edge Applications (20)

CS5032 Lecture 20: Dependable infrastructure 2
CS5032 Lecture 20: Dependable infrastructure 2CS5032 Lecture 20: Dependable infrastructure 2
CS5032 Lecture 20: Dependable infrastructure 2
 
Deep Learning Fault Detection Algorithms in WSNs
Deep Learning Fault Detection Algorithms in WSNsDeep Learning Fault Detection Algorithms in WSNs
Deep Learning Fault Detection Algorithms in WSNs
 
Sem
SemSem
Sem
 
Real time visualization of structured things
Real time visualization of structured thingsReal time visualization of structured things
Real time visualization of structured things
 
Proactive Population-Risk Based Defense Against Denial of Cyber-Physical Serv...
Proactive Population-Risk Based Defense Against Denial of Cyber-Physical Serv...Proactive Population-Risk Based Defense Against Denial of Cyber-Physical Serv...
Proactive Population-Risk Based Defense Against Denial of Cyber-Physical Serv...
 
Multilin™ Intelligent Line Monitoring System
Multilin™ Intelligent Line Monitoring SystemMultilin™ Intelligent Line Monitoring System
Multilin™ Intelligent Line Monitoring System
 
Distributed Checkpointing on an Enterprise Desktop Grid
Distributed Checkpointing on an Enterprise Desktop GridDistributed Checkpointing on an Enterprise Desktop Grid
Distributed Checkpointing on an Enterprise Desktop Grid
 
Mastering IoT Design: Sense, Process, Connect: Processing: Turning IoT Data i...
Mastering IoT Design: Sense, Process, Connect: Processing: Turning IoT Data i...Mastering IoT Design: Sense, Process, Connect: Processing: Turning IoT Data i...
Mastering IoT Design: Sense, Process, Connect: Processing: Turning IoT Data i...
 
A Survey of Fault Tolerance Methods in Wireless Sensor Networks
A Survey of Fault Tolerance Methods in Wireless Sensor NetworksA Survey of Fault Tolerance Methods in Wireless Sensor Networks
A Survey of Fault Tolerance Methods in Wireless Sensor Networks
 
ON FAULT TOLERANCE OF RESOURCES IN COMPUTATIONAL GRIDS
ON FAULT TOLERANCE OF RESOURCES IN COMPUTATIONAL GRIDSON FAULT TOLERANCE OF RESOURCES IN COMPUTATIONAL GRIDS
ON FAULT TOLERANCE OF RESOURCES IN COMPUTATIONAL GRIDS
 
Design and Analysis of a Broadcast Network Using Logical Segmentation
Design and Analysis of a Broadcast Network Using Logical SegmentationDesign and Analysis of a Broadcast Network Using Logical Segmentation
Design and Analysis of a Broadcast Network Using Logical Segmentation
 
IRJET- Iot Based Underground Cable Line Fault Detection
IRJET- Iot Based Underground Cable Line Fault DetectionIRJET- Iot Based Underground Cable Line Fault Detection
IRJET- Iot Based Underground Cable Line Fault Detection
 
IRJET- A Wireless Sensor Network based Border Monitoring System using Clusters
IRJET- A Wireless Sensor Network based Border Monitoring System using ClustersIRJET- A Wireless Sensor Network based Border Monitoring System using Clusters
IRJET- A Wireless Sensor Network based Border Monitoring System using Clusters
 
D. Ardagna - PARVIS - Performance mAnagement of VIrtualized Systems
D. Ardagna - PARVIS - Performance mAnagement of VIrtualized SystemsD. Ardagna - PARVIS - Performance mAnagement of VIrtualized Systems
D. Ardagna - PARVIS - Performance mAnagement of VIrtualized Systems
 
Edge Computing TS.pptx
Edge Computing TS.pptxEdge Computing TS.pptx
Edge Computing TS.pptx
 
High Fault Coverage For On Chip Network Using Priority Based Routing Algorithm
High Fault Coverage For On Chip Network Using Priority Based Routing AlgorithmHigh Fault Coverage For On Chip Network Using Priority Based Routing Algorithm
High Fault Coverage For On Chip Network Using Priority Based Routing Algorithm
 
High Fault Coverage For On Chip Network Using Priority Based Routing Algorithm
High Fault Coverage For On Chip Network Using Priority Based Routing AlgorithmHigh Fault Coverage For On Chip Network Using Priority Based Routing Algorithm
High Fault Coverage For On Chip Network Using Priority Based Routing Algorithm
 
A Comparative Review on Reliability and Fault Tolerance Enhancement Protocols...
A Comparative Review on Reliability and Fault Tolerance Enhancement Protocols...A Comparative Review on Reliability and Fault Tolerance Enhancement Protocols...
A Comparative Review on Reliability and Fault Tolerance Enhancement Protocols...
 
System interconnect architecture
System interconnect architectureSystem interconnect architecture
System interconnect architecture
 
VL2: A scalable and flexible Data Center Network
VL2: A scalable and flexible Data Center NetworkVL2: A scalable and flexible Data Center Network
VL2: A scalable and flexible Data Center Network
 

More from AtakanAral

Subgraph Matching for Resource Allocation in the Federated Cloud Environment
Subgraph Matching for Resource Allocation in the Federated Cloud EnvironmentSubgraph Matching for Resource Allocation in the Federated Cloud Environment
Subgraph Matching for Resource Allocation in the Federated Cloud EnvironmentAtakanAral
 
Resource Mapping Optimization for Distributed Cloud Services - PhD Thesis Def...
Resource Mapping Optimization for Distributed Cloud Services - PhD Thesis Def...Resource Mapping Optimization for Distributed Cloud Services - PhD Thesis Def...
Resource Mapping Optimization for Distributed Cloud Services - PhD Thesis Def...AtakanAral
 
Modeling and Optimization of Resource Allocation in Cloud [PhD Thesis Progres...
Modeling and Optimization of Resource Allocation in Cloud [PhD Thesis Progres...Modeling and Optimization of Resource Allocation in Cloud [PhD Thesis Progres...
Modeling and Optimization of Resource Allocation in Cloud [PhD Thesis Progres...AtakanAral
 
Modeling and Optimization of Resource Allocation in Cloud [PhD Thesis Progres...
Modeling and Optimization of Resource Allocation in Cloud [PhD Thesis Progres...Modeling and Optimization of Resource Allocation in Cloud [PhD Thesis Progres...
Modeling and Optimization of Resource Allocation in Cloud [PhD Thesis Progres...AtakanAral
 
Modeling and Optimization of Resource Allocation in Cloud [PhD Thesis Progres...
Modeling and Optimization of Resource Allocation in Cloud [PhD Thesis Progres...Modeling and Optimization of Resource Allocation in Cloud [PhD Thesis Progres...
Modeling and Optimization of Resource Allocation in Cloud [PhD Thesis Progres...AtakanAral
 
Modeling and Optimization of Resource Allocation in Cloud [PhD Thesis Progres...
Modeling and Optimization of Resource Allocation in Cloud [PhD Thesis Progres...Modeling and Optimization of Resource Allocation in Cloud [PhD Thesis Progres...
Modeling and Optimization of Resource Allocation in Cloud [PhD Thesis Progres...AtakanAral
 
Software Engineering - RS4
Software Engineering - RS4Software Engineering - RS4
Software Engineering - RS4AtakanAral
 
Software Engineering - RS3
Software Engineering - RS3Software Engineering - RS3
Software Engineering - RS3AtakanAral
 
Software Engineering - RS2
Software Engineering - RS2Software Engineering - RS2
Software Engineering - RS2AtakanAral
 
Software Engineering - RS1
Software Engineering - RS1Software Engineering - RS1
Software Engineering - RS1AtakanAral
 
Modeling and Optimization of Resource Allocation in Cloud [PhD Thesis Proposal]
Modeling and Optimization of Resource Allocation in Cloud [PhD Thesis Proposal]Modeling and Optimization of Resource Allocation in Cloud [PhD Thesis Proposal]
Modeling and Optimization of Resource Allocation in Cloud [PhD Thesis Proposal]AtakanAral
 
Analysis of Algorithms II - PS5
Analysis of Algorithms II - PS5Analysis of Algorithms II - PS5
Analysis of Algorithms II - PS5AtakanAral
 
Improving Resource Utilization in Cloud using Application Placement Heuristics
Improving Resource Utilization in Cloud using Application Placement HeuristicsImproving Resource Utilization in Cloud using Application Placement Heuristics
Improving Resource Utilization in Cloud using Application Placement HeuristicsAtakanAral
 
Analysis of Algorithms II - PS3
Analysis of Algorithms II - PS3Analysis of Algorithms II - PS3
Analysis of Algorithms II - PS3AtakanAral
 
Analysis of Algorithms II - PS2
Analysis of Algorithms II - PS2Analysis of Algorithms II - PS2
Analysis of Algorithms II - PS2AtakanAral
 
Analysis of Algorithms - 5
Analysis of Algorithms - 5Analysis of Algorithms - 5
Analysis of Algorithms - 5AtakanAral
 
Analysis of Algorithms - 3
Analysis of Algorithms - 3Analysis of Algorithms - 3
Analysis of Algorithms - 3AtakanAral
 
Analysis of Algorithms - 2
Analysis of Algorithms - 2Analysis of Algorithms - 2
Analysis of Algorithms - 2AtakanAral
 
Analysis of Algorithms - 1
Analysis of Algorithms - 1Analysis of Algorithms - 1
Analysis of Algorithms - 1AtakanAral
 
Mobile Multi-domain Search over Structured Web Data
Mobile Multi-domain Search over Structured Web DataMobile Multi-domain Search over Structured Web Data
Mobile Multi-domain Search over Structured Web DataAtakanAral
 

More from AtakanAral (20)

Subgraph Matching for Resource Allocation in the Federated Cloud Environment
Subgraph Matching for Resource Allocation in the Federated Cloud EnvironmentSubgraph Matching for Resource Allocation in the Federated Cloud Environment
Subgraph Matching for Resource Allocation in the Federated Cloud Environment
 
Resource Mapping Optimization for Distributed Cloud Services - PhD Thesis Def...
Resource Mapping Optimization for Distributed Cloud Services - PhD Thesis Def...Resource Mapping Optimization for Distributed Cloud Services - PhD Thesis Def...
Resource Mapping Optimization for Distributed Cloud Services - PhD Thesis Def...
 
Modeling and Optimization of Resource Allocation in Cloud [PhD Thesis Progres...
Modeling and Optimization of Resource Allocation in Cloud [PhD Thesis Progres...Modeling and Optimization of Resource Allocation in Cloud [PhD Thesis Progres...
Modeling and Optimization of Resource Allocation in Cloud [PhD Thesis Progres...
 
Modeling and Optimization of Resource Allocation in Cloud [PhD Thesis Progres...
Modeling and Optimization of Resource Allocation in Cloud [PhD Thesis Progres...Modeling and Optimization of Resource Allocation in Cloud [PhD Thesis Progres...
Modeling and Optimization of Resource Allocation in Cloud [PhD Thesis Progres...
 
Modeling and Optimization of Resource Allocation in Cloud [PhD Thesis Progres...
Modeling and Optimization of Resource Allocation in Cloud [PhD Thesis Progres...Modeling and Optimization of Resource Allocation in Cloud [PhD Thesis Progres...
Modeling and Optimization of Resource Allocation in Cloud [PhD Thesis Progres...
 
Modeling and Optimization of Resource Allocation in Cloud [PhD Thesis Progres...
Modeling and Optimization of Resource Allocation in Cloud [PhD Thesis Progres...Modeling and Optimization of Resource Allocation in Cloud [PhD Thesis Progres...
Modeling and Optimization of Resource Allocation in Cloud [PhD Thesis Progres...
 
Software Engineering - RS4
Software Engineering - RS4Software Engineering - RS4
Software Engineering - RS4
 
Software Engineering - RS3
Software Engineering - RS3Software Engineering - RS3
Software Engineering - RS3
 
Software Engineering - RS2
Software Engineering - RS2Software Engineering - RS2
Software Engineering - RS2
 
Software Engineering - RS1
Software Engineering - RS1Software Engineering - RS1
Software Engineering - RS1
 
Modeling and Optimization of Resource Allocation in Cloud [PhD Thesis Proposal]
Modeling and Optimization of Resource Allocation in Cloud [PhD Thesis Proposal]Modeling and Optimization of Resource Allocation in Cloud [PhD Thesis Proposal]
Modeling and Optimization of Resource Allocation in Cloud [PhD Thesis Proposal]
 
Analysis of Algorithms II - PS5
Analysis of Algorithms II - PS5Analysis of Algorithms II - PS5
Analysis of Algorithms II - PS5
 
Improving Resource Utilization in Cloud using Application Placement Heuristics
Improving Resource Utilization in Cloud using Application Placement HeuristicsImproving Resource Utilization in Cloud using Application Placement Heuristics
Improving Resource Utilization in Cloud using Application Placement Heuristics
 
Analysis of Algorithms II - PS3
Analysis of Algorithms II - PS3Analysis of Algorithms II - PS3
Analysis of Algorithms II - PS3
 
Analysis of Algorithms II - PS2
Analysis of Algorithms II - PS2Analysis of Algorithms II - PS2
Analysis of Algorithms II - PS2
 
Analysis of Algorithms - 5
Analysis of Algorithms - 5Analysis of Algorithms - 5
Analysis of Algorithms - 5
 
Analysis of Algorithms - 3
Analysis of Algorithms - 3Analysis of Algorithms - 3
Analysis of Algorithms - 3
 
Analysis of Algorithms - 2
Analysis of Algorithms - 2Analysis of Algorithms - 2
Analysis of Algorithms - 2
 
Analysis of Algorithms - 1
Analysis of Algorithms - 1Analysis of Algorithms - 1
Analysis of Algorithms - 1
 
Mobile Multi-domain Search over Structured Web Data
Mobile Multi-domain Search over Structured Web DataMobile Multi-domain Search over Structured Web Data
Mobile Multi-domain Search over Structured Web Data
 

Recently uploaded

Call Girls in Munirka Delhi 💯Call Us 🔝8264348440🔝
Call Girls in Munirka Delhi 💯Call Us 🔝8264348440🔝Call Girls in Munirka Delhi 💯Call Us 🔝8264348440🔝
Call Girls in Munirka Delhi 💯Call Us 🔝8264348440🔝soniya singh
 
Welcome to GFDL for Take Your Child To Work Day
Welcome to GFDL for Take Your Child To Work DayWelcome to GFDL for Take Your Child To Work Day
Welcome to GFDL for Take Your Child To Work DayZachary Labe
 
Best Call Girls In Sector 29 Gurgaon❤️8860477959 EscorTs Service In 24/7 Delh...
Best Call Girls In Sector 29 Gurgaon❤️8860477959 EscorTs Service In 24/7 Delh...Best Call Girls In Sector 29 Gurgaon❤️8860477959 EscorTs Service In 24/7 Delh...
Best Call Girls In Sector 29 Gurgaon❤️8860477959 EscorTs Service In 24/7 Delh...lizamodels9
 
Grafana in space: Monitoring Japan's SLIM moon lander in real time
Grafana in space: Monitoring Japan's SLIM moon lander  in real timeGrafana in space: Monitoring Japan's SLIM moon lander  in real time
Grafana in space: Monitoring Japan's SLIM moon lander in real timeSatoshi NAKAHIRA
 
LIGHT-PHENOMENA-BY-CABUALDIONALDOPANOGANCADIENTE-CONDEZA (1).pptx
LIGHT-PHENOMENA-BY-CABUALDIONALDOPANOGANCADIENTE-CONDEZA (1).pptxLIGHT-PHENOMENA-BY-CABUALDIONALDOPANOGANCADIENTE-CONDEZA (1).pptx
LIGHT-PHENOMENA-BY-CABUALDIONALDOPANOGANCADIENTE-CONDEZA (1).pptxmalonesandreagweneth
 
Gas_Laws_powerpoint_notes.ppt for grade 10
Gas_Laws_powerpoint_notes.ppt for grade 10Gas_Laws_powerpoint_notes.ppt for grade 10
Gas_Laws_powerpoint_notes.ppt for grade 10ROLANARIBATO3
 
Recombinant DNA technology( Transgenic plant and animal)
Recombinant DNA technology( Transgenic plant and animal)Recombinant DNA technology( Transgenic plant and animal)
Recombinant DNA technology( Transgenic plant and animal)DHURKADEVIBASKAR
 
Forest laws, Indian forest laws, why they are important
Forest laws, Indian forest laws, why they are importantForest laws, Indian forest laws, why they are important
Forest laws, Indian forest laws, why they are importantadityabhardwaj282
 
Spermiogenesis or Spermateleosis or metamorphosis of spermatid
Spermiogenesis or Spermateleosis or metamorphosis of spermatidSpermiogenesis or Spermateleosis or metamorphosis of spermatid
Spermiogenesis or Spermateleosis or metamorphosis of spermatidSarthak Sekhar Mondal
 
Call Girls in Hauz Khas Delhi 💯Call Us 🔝9953322196🔝 💯Escort.
Call Girls in Hauz Khas Delhi 💯Call Us 🔝9953322196🔝 💯Escort.Call Girls in Hauz Khas Delhi 💯Call Us 🔝9953322196🔝 💯Escort.
Call Girls in Hauz Khas Delhi 💯Call Us 🔝9953322196🔝 💯Escort.aasikanpl
 
Solution chemistry, Moral and Normal solutions
Solution chemistry, Moral and Normal solutionsSolution chemistry, Moral and Normal solutions
Solution chemistry, Moral and Normal solutionsHajira Mahmood
 
Temporomandibular joint Muscles of Mastication
Temporomandibular joint Muscles of MasticationTemporomandibular joint Muscles of Mastication
Temporomandibular joint Muscles of Masticationvidulajaib
 
insect anatomy and insect body wall and their physiology
insect anatomy and insect body wall and their  physiologyinsect anatomy and insect body wall and their  physiology
insect anatomy and insect body wall and their physiologyDrAnita Sharma
 
Microphone- characteristics,carbon microphone, dynamic microphone.pptx
Microphone- characteristics,carbon microphone, dynamic microphone.pptxMicrophone- characteristics,carbon microphone, dynamic microphone.pptx
Microphone- characteristics,carbon microphone, dynamic microphone.pptxpriyankatabhane
 
RESPIRATORY ADAPTATIONS TO HYPOXIA IN HUMNAS.pptx
RESPIRATORY ADAPTATIONS TO HYPOXIA IN HUMNAS.pptxRESPIRATORY ADAPTATIONS TO HYPOXIA IN HUMNAS.pptx
RESPIRATORY ADAPTATIONS TO HYPOXIA IN HUMNAS.pptxFarihaAbdulRasheed
 
TOTAL CHOLESTEROL (lipid profile test).pptx
TOTAL CHOLESTEROL (lipid profile test).pptxTOTAL CHOLESTEROL (lipid profile test).pptx
TOTAL CHOLESTEROL (lipid profile test).pptxdharshini369nike
 
Manassas R - Parkside Middle School 🌎🏫
Manassas R - Parkside Middle School 🌎🏫Manassas R - Parkside Middle School 🌎🏫
Manassas R - Parkside Middle School 🌎🏫qfactory1
 
Neurodevelopmental disorders according to the dsm 5 tr
Neurodevelopmental disorders according to the dsm 5 trNeurodevelopmental disorders according to the dsm 5 tr
Neurodevelopmental disorders according to the dsm 5 trssuser06f238
 
Heredity: Inheritance and Variation of Traits
Heredity: Inheritance and Variation of TraitsHeredity: Inheritance and Variation of Traits
Heredity: Inheritance and Variation of TraitsCharlene Llagas
 
Scheme-of-Work-Science-Stage-4 cambridge science.docx
Scheme-of-Work-Science-Stage-4 cambridge science.docxScheme-of-Work-Science-Stage-4 cambridge science.docx
Scheme-of-Work-Science-Stage-4 cambridge science.docxyaramohamed343013
 

Recently uploaded (20)

Call Girls in Munirka Delhi 💯Call Us 🔝8264348440🔝
Call Girls in Munirka Delhi 💯Call Us 🔝8264348440🔝Call Girls in Munirka Delhi 💯Call Us 🔝8264348440🔝
Call Girls in Munirka Delhi 💯Call Us 🔝8264348440🔝
 
Welcome to GFDL for Take Your Child To Work Day
Welcome to GFDL for Take Your Child To Work DayWelcome to GFDL for Take Your Child To Work Day
Welcome to GFDL for Take Your Child To Work Day
 
Best Call Girls In Sector 29 Gurgaon❤️8860477959 EscorTs Service In 24/7 Delh...
Best Call Girls In Sector 29 Gurgaon❤️8860477959 EscorTs Service In 24/7 Delh...Best Call Girls In Sector 29 Gurgaon❤️8860477959 EscorTs Service In 24/7 Delh...
Best Call Girls In Sector 29 Gurgaon❤️8860477959 EscorTs Service In 24/7 Delh...
 
Grafana in space: Monitoring Japan's SLIM moon lander in real time
Grafana in space: Monitoring Japan's SLIM moon lander  in real timeGrafana in space: Monitoring Japan's SLIM moon lander  in real time
Grafana in space: Monitoring Japan's SLIM moon lander in real time
 
LIGHT-PHENOMENA-BY-CABUALDIONALDOPANOGANCADIENTE-CONDEZA (1).pptx
LIGHT-PHENOMENA-BY-CABUALDIONALDOPANOGANCADIENTE-CONDEZA (1).pptxLIGHT-PHENOMENA-BY-CABUALDIONALDOPANOGANCADIENTE-CONDEZA (1).pptx
LIGHT-PHENOMENA-BY-CABUALDIONALDOPANOGANCADIENTE-CONDEZA (1).pptx
 
Gas_Laws_powerpoint_notes.ppt for grade 10
Gas_Laws_powerpoint_notes.ppt for grade 10Gas_Laws_powerpoint_notes.ppt for grade 10
Gas_Laws_powerpoint_notes.ppt for grade 10
 
Recombinant DNA technology( Transgenic plant and animal)
Recombinant DNA technology( Transgenic plant and animal)Recombinant DNA technology( Transgenic plant and animal)
Recombinant DNA technology( Transgenic plant and animal)
 
Forest laws, Indian forest laws, why they are important
Forest laws, Indian forest laws, why they are importantForest laws, Indian forest laws, why they are important
Forest laws, Indian forest laws, why they are important
 
Spermiogenesis or Spermateleosis or metamorphosis of spermatid
Spermiogenesis or Spermateleosis or metamorphosis of spermatidSpermiogenesis or Spermateleosis or metamorphosis of spermatid
Spermiogenesis or Spermateleosis or metamorphosis of spermatid
 
Call Girls in Hauz Khas Delhi 💯Call Us 🔝9953322196🔝 💯Escort.
Call Girls in Hauz Khas Delhi 💯Call Us 🔝9953322196🔝 💯Escort.Call Girls in Hauz Khas Delhi 💯Call Us 🔝9953322196🔝 💯Escort.
Call Girls in Hauz Khas Delhi 💯Call Us 🔝9953322196🔝 💯Escort.
 
Solution chemistry, Moral and Normal solutions
Solution chemistry, Moral and Normal solutionsSolution chemistry, Moral and Normal solutions
Solution chemistry, Moral and Normal solutions
 
Temporomandibular joint Muscles of Mastication
Temporomandibular joint Muscles of MasticationTemporomandibular joint Muscles of Mastication
Temporomandibular joint Muscles of Mastication
 
insect anatomy and insect body wall and their physiology
insect anatomy and insect body wall and their  physiologyinsect anatomy and insect body wall and their  physiology
insect anatomy and insect body wall and their physiology
 
Microphone- characteristics,carbon microphone, dynamic microphone.pptx
Microphone- characteristics,carbon microphone, dynamic microphone.pptxMicrophone- characteristics,carbon microphone, dynamic microphone.pptx
Microphone- characteristics,carbon microphone, dynamic microphone.pptx
 
RESPIRATORY ADAPTATIONS TO HYPOXIA IN HUMNAS.pptx
RESPIRATORY ADAPTATIONS TO HYPOXIA IN HUMNAS.pptxRESPIRATORY ADAPTATIONS TO HYPOXIA IN HUMNAS.pptx
RESPIRATORY ADAPTATIONS TO HYPOXIA IN HUMNAS.pptx
 
TOTAL CHOLESTEROL (lipid profile test).pptx
TOTAL CHOLESTEROL (lipid profile test).pptxTOTAL CHOLESTEROL (lipid profile test).pptx
TOTAL CHOLESTEROL (lipid profile test).pptx
 
Manassas R - Parkside Middle School 🌎🏫
Manassas R - Parkside Middle School 🌎🏫Manassas R - Parkside Middle School 🌎🏫
Manassas R - Parkside Middle School 🌎🏫
 
Neurodevelopmental disorders according to the dsm 5 tr
Neurodevelopmental disorders according to the dsm 5 trNeurodevelopmental disorders according to the dsm 5 tr
Neurodevelopmental disorders according to the dsm 5 tr
 
Heredity: Inheritance and Variation of Traits
Heredity: Inheritance and Variation of TraitsHeredity: Inheritance and Variation of Traits
Heredity: Inheritance and Variation of Traits
 
Scheme-of-Work-Science-Stage-4 cambridge science.docx
Scheme-of-Work-Science-Stage-4 cambridge science.docxScheme-of-Work-Science-Stage-4 cambridge science.docx
Scheme-of-Work-Science-Stage-4 cambridge science.docx
 

Quality of Service Channelling for Latency Sensitive Edge Applications

  • 1. Quality of Service Channelling for Latency Sensitive Edge Applications Atakan Aral, Ivona Brandić Institute of Software Technology and Interactive Systems Vienna University of Technology {atakan.aral, ivona.brandic}@tuwien.ac.at http://rucon.ec.tuwien.ac.at/
  • 2. A Dilemma in Edge Edge applications are; • Latency sensitive • Data dependent • Hence, geographically distributed / replicated. 2 NTT Press Releases, 23.01.2014
  • 3. A Dilemma in Edge However, Edge data centers are; • Lacking expensive support systems • Prone to failures (hardware, software, network, …) • Hence, unreliable for guaranteeing QoS (e.g. response time or throughput). 3
  • 4. Cost of Failures Average downtime duration: 18:30 hours Cost of downtime: $700,000 per hour Cascading failures • US-EAST-1 on February 28th • Two S3 subsystems were shut down accidentally • 11 hours of disruption not only for S3 but also EC2  Adobe services, Bitbucket, Quora, Coursera, Docker, Github, LonelyPlanet, …  Connected lightbulbs, thermostats, … 4 Operational, 45% Natural, 35% Human, 19% Other, 1% Failure causes Sources: https://www.infrascale.com, https://aws.amazon.com
  • 5. Challenges 5 • Recovery cost is too high. Reactive methods alone are not sufficient • Failures have various characteristics: cause, effect on availability, etc. • Failures are statistically dependent to each other. • Dependencies are dynamic. • Optimization is online, failure prediction should be done in real-time. Proactive methods require failure prediction
  • 8. Experimental Setup Server failure data collected by Los Alamos National Laboratory (LANL) • Collected between 1999-2005 • 19.436 failures of 122 types • 3.577 servers from 22 systems 8
  • 9. Results 9 Please, refer to the paper for additional simulation results.
  • 10. Conclusion Edge computing requires intelligent and efficient mechanisms to cope with unreliability. Key message: Exploiting the dependencies between different failures allow us to predict them quite accurately. Current work: • Link failures (e.g. network congestion, router outage, etc.) • Dependencies between Edge nodes (e.g. geographical, cascading, etc.) • Node availability  Distributed service availability • http://rucon.ec.tuwien.ac.at/ 10
  • 11. Thank you for your attention! Atakan Aral, Ivona Brandić Institute of Software Technology and Interactive Systems Vienna University of Technology {atakan.aral, ivona.brandic}@tuwien.ac.at http://rucon.ec.tuwien.ac.at/
  • 12. Simulation Results Number of SLO violations for each configuration using Bayesian Network Estimation (BN) or only Prior Knowledge (PK)