Edge Computing Platforms and Protocols - Ph.D. thesis

N
Nitinder MohanPost doctoral fellow at Technical University of Munich
Edge Computing
Platforms and Protocols
Nitinder Mohan
Cloud Computing
• Global network of inter-connected datacenters
• Datacenters managed and operated by cloud
providers, e.g. Google, Microsoft, Amazon etc.
• Developers can deploy their applications on
virtualized resources of the cloud worldwide
1
More than 60% of Internet workloads are cloud-based
Next Generation Applications
Trends by year 2025
• More than 75 billion connected devices
• Expected 11 trillion USD market share
• On average 7 sensors per person worldwide
Requirements
1. Latency-critical processing
2. Big data aggregation and analysis
3. Location and context aware computations
Internet-of-Things
3
Problem: Network!
Ø High transport cost
Ø High data volume
Ø High network latency
Can Cloud support next-generation applications?
4
Edge Computing
Small-scale server(s) deployed near the users to
compute generated data
Benefits:
üDecreased latency for computation
üReduced network load due to pre-processing
üLocation and contextual awareness
Network
DatacenterEdge
Server
User
5
Problems in Edge computing
1. Unmanaged hardware
2. Constrained network
3. Inconsistent reliability and availability
4. Lack of standardized protocols
6
Hardware
Deployment, Cooling, Maintenance
Infrastructure
Processing, Storage, Networking
Platform
Virtual Machines, Containers,
Databases
Software
Parental Control, Firewall, Content
Catalog, User Authentication
Cloud Computing Service Model
7
Hardware
Deployment, Cooling, Maintenance
Infrastructure
Processing, Storage, Networking
Platform
Virtual Machines, Containers,
Databases
Software
Cloud Computing Service Model Edge Computing Service Model
Hardware
Organization? Installation?
Maintenance? Security?
Infrastructure
Mobile hardware? Limited
processing? Low storage?
Wireless/Cellular NICs?
Platform
Server Discovery? Self-Organizing
Containers?
Parental Control, Firewall, Content
Catalog, User Authentication
Factory Automation, Intelligence,
Autonomous vehicles, IoT Analytics
Cloud providers?
Crowdsourced?
ISPs?
Light-weight VM?
Mirage OS?
Unikernels?
Smartphone
manufactures?
Specialized
servers?
7
Hardware Thesis Contributions
Edge-Fog Cloud: All-inclusive, node-oriented edge computing architecture which logically
categorizes resources in layers.
Anveshak: Deployment framework that assists service providers to identify best locations in a
geographical region for installing edge servers.
Infrastructure
QAware: Cross-layer scheduler for Multipath TCP which allows edge servers to use multiple
network paths simultaneously while overcoming excessive buffering and delays on any path.
Data Grouping protocol: Edge caching mechanism which predicts and pre-caches prerequisite
data in local caches of edge servers for upcoming computations.
LPCF & eLPCF: Task allocation frameworks which distributes application jobs on a cluster of
edge servers while minimizing processing, networking and energy costs.
Platform
ICON: Self-managing virtualized containers which can automatically migrate and replicate to servers
experiencing more user traffic without involving application owner.
ExEC: Open platform which allows cloud providers to discover and utilize resources offered by third-
party edge providers operating in the network.
8
Hardware Thesis Contributions
Edge-Fog Cloud: All-inclusive, node-oriented edge computing architecture which logically
categorizes resources in layers.
Anveshak: Deployment framework that assists service providers to identify best locations in a
geographical region for installing edge servers.
Infrastructure
QAware: Cross-layer scheduler for Multipath TCP which allows edge servers to use multiple
network paths simultaneously while overcoming excessive buffering and delays on any path.
Data Grouping protocol: Edge caching mechanism which predicts and pre-caches prerequisite
data in local caches of edge servers for upcoming computations.
LPCF & eLPCF: Task allocation frameworks which distributes application jobs on a cluster of
edge servers while minimizing processing, networking and energy costs.
Platform
ICON: Self-managing virtualized containers which can automatically migrate and replicate to servers
experiencing more user traffic without involving application owner.
ExEC: Open platform which allows cloud providers to discover and utilize resources offered by third-
party edge providers operating in the network.
8
Hardware Thesis Contributions
Edge-Fog Cloud: All-inclusive, node-oriented edge computing architecture which logically
categorizes resources in layers.
Anveshak: Deployment framework that assists service providers to identify best locations in a
geographical region for installing edge servers.
Infrastructure
QAware: Cross-layer scheduler for Multipath TCP which allows edge servers to use multiple
network paths simultaneously while overcoming excessive buffering and delays on any path.
Data Grouping protocol: Edge caching mechanism which predicts and pre-caches prerequisite
data in local caches of edge servers for upcoming computations.
LPCF & eLPCF: Task allocation frameworks which distributes application jobs on a cluster of
edge servers while minimizing processing, networking and energy costs.
Platform
ICON: Self-managing virtualized containers which can automatically migrate and replicate to servers
experiencing more user traffic without involving application owner.
ExEC: Open platform which allows cloud providers to discover and utilize resources offered by third-
party edge providers operating in the network.
How to do computations on edge clouds?
Hardware Thesis Contributions
Edge-Fog Cloud: All-inclusive, node-oriented edge computing architecture which logically
categorizes resources in layers.
Anveshak: Deployment framework that assists service providers to identify best locations in a
geographical region for installing edge servers.
Infrastructure
QAware: Cross-layer scheduler for Multipath TCP which allows edge servers to use multiple
network paths simultaneously while overcoming excessive buffering and delays on any path.
Data Grouping protocol: Edge caching mechanism which predicts and pre-caches prerequisite
data in local caches of edge servers for upcoming computations.
LPCF & eLPCF: Task allocation frameworks which distributes application jobs on a cluster of
edge servers while minimizing processing, networking and energy costs.
Platform
ICON: Self-managing virtualized containers which can automatically migrate and replicate to servers
experiencing more user traffic without involving application owner.
ExEC: Open platform which allows cloud providers to discover and utilize resources offered by third-
party edge providers operating in the network.
8
Requirement of Edge Computing
Need of a reference architecture for designing protocols and
platforms!
Constraints? Capabilities? Capacities?
9
Edge-Fog Cloud (EFCloud)
Edge
Ø Collection of devices:
i. Loosely-coupled
ii. Voluntary/Crowdsourced
iii. Owned by independent operators
Ø Extremely close to sensors & clients
Ø Device-to-device connectivity over
WiFi/cellular/Bluetooth/Zigbee etc.
Ø Varying processing capability
e.g. desktops, laptops, workstations,
nano data centers etc. 10
Edge-Fog Cloud (EFCloud)
Fog
Ø High capacity compute servers
Ø Co-located with networking devices
Ø Designed, manufactured, managed
and deployed by cloud vendors
Ø Lies farther from sensors and clients
Ø Dense connectivity within layer
Ø Support for virtualization
technologies
e.g. routers, switches, basestations etc.
11
Edge-Fog Cloud (EFCloud)
Data Store
Ø Data archival and storage
Ø No computation on data
Ø Reliable, ease-of-access, secure and
global access to storage for Edge and
Fog resources
12
Edge-Fog Cloud (EFCloud)
Salient Features
1. All-inclusive edge architecture
2. Native support for mobility
3. Satisfies emerging application
requirements
4. Context-aware computation
5. No single point-of-failure
6. No vendor lock-in
13
Hardware Thesis Contributions
Edge-Fog Cloud: All-inclusive, node-oriented edge computing architecture which logically
categorizes resources in layers.
Anveshak: Deployment framework that assists service providers to identify best locations in a
geographical region for installing edge servers.
Infrastructure
QAware: Cross-layer scheduler for Multipath TCP which allows edge servers to use multiple
network paths simultaneously while overcoming excessive buffering and delays on any path.
Data Grouping protocol: Edge caching mechanism which predicts and pre-caches prerequisite
data in local caches of edge servers for upcoming computations.
LPCF & eLPCF: Task allocation frameworks which distributes application jobs on a cluster of
edge servers while minimizing processing, networking and energy costs.
Platform
ICON: Self-managing virtualized containers which can automatically migrate and replicate to servers
experiencing more user traffic without involving application owner.
ExEC: Open platform which allows cloud providers to discover and utilize resources offered by third-
party edge providers operating in the network.
14
Edge-Fog Cloud
Formalizing Task Deployment
15
Edge-Fog Cloud
Formalizing Task Deployment𝜆/𝜋/BW
𝜆/𝜋/BW
𝜆/𝜋/BW
𝜆 / 𝜋/ BW
𝜆 / 𝜋/ BW
15
Edge-Fog Cloud
Formalizing Task Deployment
D1 D2 D3
D4 D5
1
4 34
1
15
Edge-Fog Cloud
Formalizing Task Deployment
D1 D2 D3
D4 D5
1
4 34
1
16
Edge-Fog Cloud
J1 J2 J3
J4
J5
Job Graph
Formalizing Task Deployment
D1 D2 D3
D4 D5
1
4 34
1
16
J1 J2 J3
J4
J5
Formalizing Task Deployment
D1 D2 D3
D4 D5
1
4 34
1
Objective: Find best placement of jobs on Edge and Fog
devices 16
D1 D2 D3
D4 D5
1
4 34
1
J1 J2 J3
J4 J5
∞ 1 8 4 5
1 ∞ 7 5 4
8 7 ∞ 4 3
4 5 4 ∞ 1
5 4 3 1 ∞
0 1 0 1 0
1 0 1 0 1
0 1 0 0 0
1 0 0 0 1
0 1 0 1 0
Dconn[ i,j ] =
Jconn[ i,j ] =
17
De-facto: Network Only Cost Assignment
De-facto: Network Only Cost Assignment
Dconn[ i,j ] =
0 1 0 1 0
1 0 1 0 1
0 1 0 0 0
1 0 0 0 1
0 1 0 1 0
Jconn[ i,j ] =
Quadratic Assignment Problem
Minimize:
NP-hard!
• For 30 nodes, it will take 2500
servers to solve it
• Optimal solution not guaranteed
$
%(',))∈,
𝐽./00 𝑖, 𝑗 ∗ 𝐷./00(𝑓 𝑖 , 𝑓(𝑗))
∞ 1 8 4 5
1 ∞ 7 5 4
8 7 ∞ 4 3
4 5 4 ∞ 1
5 4 3 1 ∞
17
Our Approach
Optimize Processing
Time
Search Space
Reduction
Least Network
Cost
Least Processing Cost First (LPCF)
Optimize Processing
Energy
Search Space
Reduction
Least Network
Energy
energy-efficient Least Processing
Cost First (eLPCF)
Multi-Objective
Optimization
D1 D2 D3
D4 D5
1
4 34
1
: 3 : 2 : 2
: 6: 5
D1 D2 D3
D4 D5
1
4 34
1
: 3 : 2 : 2
: 6: 5
18
18
Our Approach
Optimize Processing
Time
Search Space
Reduction
Least Network
Cost
Least Processing Cost First (LPCF)
Optimize Processing
Energy
Search Space
Reduction
Least Network
Energy
energy-efficient Least Processing
Cost First (eLPCF)
Multi-Objective
Optimization
D1 D2 D3
D4 D5
1
4 34
1
: 3 : 2 : 2
: 6: 5
D1 D2 D3
D4 D5
1
4 34
1
: 3 : 2 : 2
: 6: 5
Least Processing Cost First (LPCF)
D1:3 D2:2 D3:2
D4:5 D5:6
1
4 34
1
J1:4 J2:2 J3:5
J4:4 J5:2
3 2 2 5 6
4 2 5 4 2
Dproc [i] =
Jsize [i] =
19
Least Processing Cost First (LPCF)
I. Optimize Processing Time
Minimize:
Linear Assignment Problem
$
',)∈,
𝐶
𝐽7'89(𝑖)
𝐷:;/.(𝑗)
𝑥')
3 2 2 5 6
4 2 5 4 2
Dproc [i] =
Jsize [i] =
20
I. Optimize Processing Time
Minimize:
Linear Assignment Problem
• Solved using Kuhn-Munkres/
Hungarian algorithm
• Optimal solution guaranteed in
O(n3)
Least Processing Cost First (LPCF)
D1:3 D2:2 D3:2
D4:5 D5:6
1
4 34
1
J1:4 J2:2 J5:2
J4:4 J3:5
Least Processing Cost: 4.966
$
',)∈,
𝐶
𝐽7'89(𝑖)
𝐷:;/.(𝑗)
𝑥')
20
Least Processing Cost First (LPCF)
II. Create sub-problem space
Interchange homogeneous devices
running homogeneous jobs
Search Space Calculation:
1. Same processing power
→ interchange jobs
2. Same job size
→ interchange devices
D1:3 D2:2 D3:2
D4:5 D5:6
1
4 34
1
J1:4 J2:2 J5:2
J4:4 J3:5
J1:4 J5:2 J2:2
J4:4 J3:5
J4:4 J5:2 J2:2
J1:4 J3:5
21
Least Processing Cost First (LPCF)
II. Create sub-problem space
Interchange homogeneous devices
running homogeneous jobs
Search Space Calculation:
1. Same processing power
→ interchange jobs
2. Same job size
→ interchange devices
Least Processing Cost: 4.966
D1 D2 D3 D4 D5
1. J1 J2 J5 J4 J3
2. J1 J5 J2 J4 J3
3. J4 J5 J2 J1 J3
4. J4 J2 J5 J1 J3
21
Least Processing Cost First (LPCF)
III. Least Network Cost
1. Compute network cost of each
assignment
2. Choose the assignment with
least network cost
𝐽./00 𝑖, 𝑗 ∗ 𝐷./00(𝑓 𝑖 , 𝑓(𝑗))
D1 D2 D3 D4 D5
1. J1 J2 J5 J4 J3
2. J1 J5 J2 J4 J3
3. J4 J5 J2 J1 J3
4. J4 J2 J5 J1 J3
N/W
20
27
19
28
Least Processing Cost: 4.966
22
Performance Overview
5 20 40 60 80 100
Topology Size
0
1000
2000
3000
4000
NetworkCost
NOC
LPCF
Minimum bound
Maximum bound
20 40 60 80 100
Topology Size
0
50
100
150
200
250
ProcessingCost
NOC
LPCF
eLPCF
5 20 40 60 80 100
Topology Size
5
10
15
20
25
30
%decreaseinenergy
Edge
Fog
Network cost remains
within 10% range of
the optimal value
Processing cost is
multiple times lower
than de-facto solvers
10% decrease in overall energy
used. More than 20% energy
saved for battery constrained
devices
24
Hardware Thesis Contributions
Edge-Fog Cloud: All-inclusive, node-oriented edge computing architecture which logically
categorizes resources in layers.
Anveshak: Deployment framework that assists service providers to identify best locations in a
geographical region for installing edge servers.
Infrastructure
QAware: Cross-layer scheduler for Multipath TCP which allows edge servers to use multiple
network paths simultaneously while overcoming excessive buffering and delays on any path.
Data Grouping protocol: Edge caching mechanism which predicts and pre-caches prerequisite
data in local caches of edge servers for upcoming computations.
LPCF & eLPCF: Task allocation frameworks which distributes application jobs on a cluster of
edge servers while minimizing processing, networking and energy costs.
Platform
ICON: Self-managing virtualized containers which can automatically migrate and replicate to servers
experiencing more user traffic without involving application owner.
ExEC: Open platform which allows cloud providers to discover and utilize resources offered by third-
party edge providers operating in the network.
25
Hardware PublicationsInfrastructurePlatform
Anveshak: Placing Edge Servers In The Wild. N. Mohan, A. Zavodovski, P. Zhou, and J. Kangasharju, MECOMM 2018
Placing it right!: optimizing energy, processing, and transport in Edge-Fog clouds. N. Mohan and J. Kangasharju, Annals of
Telecommunication 2018
Managing Data in Computational Edge Cloud. N. Mohan, P. Zhou, K. Govindaraj and J. Kangasharju, MECOMM 2017
QAware: A Cross-Layer Approach to MPTCP Scheduling. T. Shreedhar, N. Mohan, S.K. Kaul, & J. Kangasharju. IFIP Networking 2018
ExEC: Elastic Extensible Edge Cloud. A. Zavodovski, N. Mohan, S. Bayhan, W. Wong and J. Kangasharju, EdgeSys 2019
ICON: Intelligent Container Overlays. A. Zavodovski, N. Mohan, S. Bayhan, W. Wong and J. Kangasharju, HotNets 2018
Is two greater than one?: Analyzing Multipath TCP over Dual-LTE in the Wild. N. Mohan, T. Shreedhar, A. Zavodovski, J. Kangasharju
& S.K. Kaul. Manuscript 2019.
25
Backup Slides
Next Generation Applications
Industrial
Automation
Autonomous Vehicles
Augmented Reality
Remote Monitoring &
Collaboration
Autonomous Drones
& many more ..
Smart Homes
2
Edge Computing Platforms and Protocols - Ph.D. thesis
Edge computing
Multiple edge computing approaches have
been proposed
i. Cloudlets → Miniature datacenters
Network
Edge computing
Multiple edge computing approaches have
been proposed
i. Cloudlets → Miniature datacenters
ii. Fog → Network devices (Base stations, Routers)
Network
Edge computing
Multiple edge computing approaches have
been proposed
i. Cloudlets → Miniature datacenters
ii. Fog → Network devices (Base stations, Routers)
iii. Edge → Crowdsourced (smartphones, smart
speakers)
Network
Edge computing
Multiple edge computing approaches have
been proposed
i. Cloudlets → Miniature datacenters
ii. Fog → Network devices (Base stations, Routers)
iii. Edge → Crowdsourced (smartphones, smart
speakers, ..)
iv. Mist → Data generators (sensors,
microcontrollers, ..)
Network
Hardware
Deployment, Cooling, Maintenance
Infrastructure
Processing, Storage, Networking
Platform
Virtual Machines, Containers,
Databases
Software
Parental Control, Firewall, Content
Catalog, User Authentication
Cloud Computing Service Model Edge Computing Service Model
Hardware
Deployment, Cooling, Maintenance
Infrastructure
Processing, Storage, Networking
Platform
Virtual Machines, Containers,
Databases
Software
Cloud Computing Service Model Edge Computing Service Model
Parental Control, Firewall, Content
Catalog, User Authentication
Factory Automation, Intelligence,
Autonomous vehicles, IoT Analytics
Hardware
Deployment, Cooling, Maintenance
Infrastructure
Processing, Storage, Networking
Platform
Virtual Machines, Containers,
Databases
Software
Cloud Computing Service Model Edge Computing Service Model
Hardware
Organization? Installation?
Maintenance? Security?
Parental Control, Firewall, Content
Catalog, User Authentication
Factory Automation, Intelligence,
Autonomous vehicles, IoT Analytics
Cloud providers?
Crowdsourced?
Cellular providers?
Hardware
Deployment, Cooling, Maintenance
Infrastructure
Processing, Storage, Networking
Platform
Virtual Machines, Containers,
Databases
Software
Cloud Computing Service Model Edge Computing Service Model
Hardware
Organization? Installation?
Maintenance? Security?
Infrastructure
Mobile hardware? Limited
processing? Low storage?
Wireless/Cellular NICs?
Parental Control, Firewall, Content
Catalog, User Authentication
Factory Automation, Intelligence,
Autonomous vehicles, IoT Analytics
Cloud providers?
Crowdsourced?
Cellular providers?
Hardware
Deployment, Cooling, Maintenance
Infrastructure
Processing, Storage, Networking
Platform
Virtual Machines, Containers,
Databases
Cloud Computing Service Model Edge Computing Service Model
Hardware
Organization? Installation?
Maintenance? Security?
Infrastructure
Mobile hardware? Limited processing?
Low storage? Wireless/Cellular NICs?
Platform
Server Discovery? Self-Organizing
Containers? Unikernels?
Cloud providers?
Crowdsourced?
Cellular providers?
Software
Parental Control, Firewall, Content
Catalog, User Authentication
Factory Automation, Intelligence,
Autonomous vehicles, IoT Analytics
Hardware Thesis Research Questions
RQ2: Can independent entities enroll their compute resources in an existing edge cloud
platform?
RQ1: Where should the cloud providers install compute servers in the physical world to
satisfy the application requirements at the "edge"?
Infrastructure
RQ6: How do we assure datacenter-like network behavior over edge servers which operate
on a public wireless network?
RQ5: Can existing network technologies available at the edge support the requirements
imposed by end-applications for optimal performance?
RQ4: How to pre-cache computational data within edge servers to improve computations?
RQ3: How do we utilize availability and variability of edge servers for computing tasks?
Platform
RQ9: How can independent edge providers generate revenue at par with cloud providers?
RQ8: How can edge cloud ensure the promised Quality-of-Service despite variability in user
requests and infrastructure hardware?
RQ7: How can existing cloud virtualization technologies be exploited in edge clouds?
Hardware Thesis Research Questions
RQ2: Can independent entities enroll their compute resources in an existing edge cloud
platform?
RQ1: Where should the cloud providers install compute servers in the physical world to
satisfy the application requirements at the "edge"?
Infrastructure
RQ6: How do we assure datacenter-like network behavior over edge servers which operate
on a public wireless network?
RQ5: Can existing network technologies available at the edge support the requirements
imposed by end-applications for optimal performance?
RQ4: How to pre-cache computational data within edge servers to improve computations?
RQ3: How do we utilize availability and variability of edge servers for computing tasks?
Platform
RQ9: How can independent edge providers generate revenue at par with cloud providers?
RQ8: How can edge cloud ensure the promised Quality-of-Service despite variability in user
requests and infrastructure hardware?
RQ7: How can existing cloud virtualization technologies be exploited in edge clouds?
Can independent entities enroll their compute
resources in an existing edge cloud platform?
Hardware
Infrastructure
Platform
Hardware
Infrastructure
Platform
How do we utilize availability and variability of
edge servers for computing tasks?
Deploying Tasks on Edge Clouds
Edge clouds cannot use existing datacenter-based assignment
protocols as Edge and Fog recourses can:
1. operate in non-to-semi unmanaged environments with variable
availability
2. be equipped with constrained processing hardware requiring
multiple servers to complete single task
3. be inter-connected via wireless network links prone to latency
and congestion
4. be powered by limited battery capacity
Task Deployment on EFCloud
Network-Only Cost Solver
1. Finds job placement which has
the least possible network cost
2. Very large problem search space
3. NP-hard optimization with no
guarantee for optimal solution
Least Processing Cost First
1. Finds job placement with least
processing cost and almost-least
networking cost
2. Reduced problem search space
3. Placement guaranteed for any
problem size in linear time
23
Hardware
Infrastructure
Platform
How can existing cloud virtualization
technologies be exploited in edge clouds?
Deploying Cloud Applications
Cloud applications are composed of
multiple integrated (micro)services
Catalog Retrieval
Parental Control
Application Metrics
Exception Tracking
Audit Logging
Health Check
…
700+
Deploying Cloud Applications
Cloud applications are composed of
multiple integrated (micro)services
→ Every microservice is encapsulated
as virtualized container which is
then deployed on the cloud
Parental Control
Catalog Retrieval
Catalog Retrieval
Parental Control
Application Metrics
Exception Tracking
Audit Logging
Health Check
…
700+
Container Migration on Cloud
Container Migration on Cloud
Container Migration on Cloud
Container Migration on Cloud
Does not work in Edge-Fog Clouds!
Fragmentation in EFCloud
EFCloud is amalgamation of different managing
entities with strict authoritative boundaries
Fragmentation in EFCloud
EFCloud is amalgamation of different managing
entities with strict authoritative boundaries
1. ISP-backed Fog + Cellular-based Edge
EdgeFog
Fragmentation in EFCloud
EFCloud is amalgamation of different managing
entities with strict authoritative boundaries
1. ISP-backed Fog + Cellular-based Edge
2. WiFi router Fog + Crowdsourced Edge
EdgeFog
Fragmentation in EFCloud
EFCloud is amalgamation of different managing
entities with strict authoritative boundaries
1. ISP-backed Fog + Cellular-based Edge
2. WiFi router Fog + Crowdsourced Edge
3. Fog of cloud providers + Independent Edge
servers
EdgeFog
Fragmentation in EFCloud
EFCloud is amalgamation of different managing
entities with strict authoritative boundaries
1. ISP-backed Fog + Cellular-based Edge
2. WiFi router Fog + Crowdsourced Edge
3. Fog of cloud providers + Independent Edge
servers
Multiple entities compete in/across every
grouping for larger market share
→ Heterogeneity in Hardware and Software!
EdgeFog
Intelligent Containers (ICONs)
Self-managing virtualized services which can intelligently
and automatically move to edge servers nearest to
incoming user requests
Intelligent Containers (ICONs)
Self-managing virtualized services which can intelligently
and automatically move to edge servers* nearest to
incoming user requests
*irrespective of who owns/operates them
Operation of ICON
ICON Edge/Fog
End-users
I. Initially, ICON is in the cloud
One or multiple origination points
Operation of ICON
ICON
End-users
Edge/Fog
I. Initially, ICON is in the cloud
One or multiple origination points
II. ICON monitors incoming flows
Where user requests are coming from?
Operation of ICON
ICON
End-users
Discover
Edge/Fog
I. Initially, ICON is in the cloud
One or multiple origination points
II. ICON monitors incoming flows
Where user requests are coming from?
III. ICON discovers deployment locations
In the domain of end-users or on a path to it
Operation of ICON
ICON
End-users
Replicate
Discover
Edge/Fog
I. Initially, ICON is in the cloud
One or multiple origination points
II. ICON monitors incoming flows
Where user requests are coming from?
III. ICON discovers deployment locations
In the domain of end-users or on a path to it
IV. ICON can take autonomous decisions
i. Deploy replica of itself
Operation of ICON
ICON
End-users
Use Edge
Discover
Edge/Fog
I. Initially, ICON is in the cloud
One or multiple origination points
II. ICON monitors incoming flows
Where user requests are coming from?
III. ICON discovers deployment locations
In the domain of end-users or on a path to it
IV. ICON can take autonomous decisions
i. Deploy replica of itself
I. Initially, ICON is in the cloud
One or multiple origination points
II. ICON monitors incoming flows
Where user requests are coming from?
III. ICON discovers deployment locations
In the domain of end-users or on a path to it
IV. ICON can take autonomous decisions
i. Deploy replica of itself
ii. Migrate closer to the end-users
ICON
End-users
Migrate
Operation of ICON
Edge/Fog
Salient Features of ICONs
• Capability to automatically move application services across
administrative boundaries
• Self-organizing architecture with zero management overhead
• Developers can tune the Quality-of-Experience by easily setting
budget and latency weights
• Hierarchical overlay with minimal communication overhead
• Automatic termination with budget reallocation based on thresholds
1 of 77

Recommended

IoT Meets the Cloud: The Origins of Edge Computing by
IoT Meets the Cloud:  The Origins of Edge ComputingIoT Meets the Cloud:  The Origins of Edge Computing
IoT Meets the Cloud: The Origins of Edge ComputingMaria Gorlatova
457 views45 slides
Edge computing by
Edge computingEdge computing
Edge computingBiddut Hossain
1.6K views15 slides
EDGE COMPUTING: VISION AND CHALLENGES by
EDGE COMPUTING: VISION AND CHALLENGESEDGE COMPUTING: VISION AND CHALLENGES
EDGE COMPUTING: VISION AND CHALLENGESsuthi
952 views10 slides
Edge Computing : future of IoT ? by
Edge Computing : future of IoT ? Edge Computing : future of IoT ?
Edge Computing : future of IoT ? Samir Bounab
7.7K views33 slides
What is Edge Computing and Why does it matter in IoT? by
What is Edge Computing and Why does it matter in IoT?What is Edge Computing and Why does it matter in IoT?
What is Edge Computing and Why does it matter in IoT?Sameer Ahmed
5.2K views11 slides
What's next in edge computing? by
What's next in edge computing?What's next in edge computing?
What's next in edge computing?Fastly
699 views52 slides

More Related Content

What's hot

Edge Computing: Bringing the Internet Closer to You by
Edge Computing: Bringing the Internet Closer to YouEdge Computing: Bringing the Internet Closer to You
Edge Computing: Bringing the Internet Closer to YouMegan O'Keefe
2.3K views32 slides
MRI Energy-Efficient Cloud Computing by
MRI Energy-Efficient Cloud ComputingMRI Energy-Efficient Cloud Computing
MRI Energy-Efficient Cloud ComputingRoger Rafanell Mas
1.2K views19 slides
Edge computing by
Edge computingEdge computing
Edge computingpramiidhaaavula
2.2K views16 slides
EDGE SEMINAR.pptx by
EDGE SEMINAR.pptxEDGE SEMINAR.pptx
EDGE SEMINAR.pptxSachuS16
193 views29 slides
Edge Computing & AI by
Edge Computing & AIEdge Computing & AI
Edge Computing & AIPaul O'Hagan
708 views8 slides
Overview of Cloud Computing by
Overview of Cloud ComputingOverview of Cloud Computing
Overview of Cloud ComputingNishant Munjal
9.3K views16 slides

What's hot(20)

Edge Computing: Bringing the Internet Closer to You by Megan O'Keefe
Edge Computing: Bringing the Internet Closer to YouEdge Computing: Bringing the Internet Closer to You
Edge Computing: Bringing the Internet Closer to You
Megan O'Keefe2.3K views
EDGE SEMINAR.pptx by SachuS16
EDGE SEMINAR.pptxEDGE SEMINAR.pptx
EDGE SEMINAR.pptx
SachuS16193 views
Overview of Cloud Computing by Nishant Munjal
Overview of Cloud ComputingOverview of Cloud Computing
Overview of Cloud Computing
Nishant Munjal9.3K views
presentation on Edge computing by sairamgoud16
presentation on Edge computingpresentation on Edge computing
presentation on Edge computing
sairamgoud1619.6K views
Security Issues of Cloud Computing by Falgun Rathod
Security Issues of Cloud ComputingSecurity Issues of Cloud Computing
Security Issues of Cloud Computing
Falgun Rathod9K views
EDGE COMPUTING by Mosin A
EDGE COMPUTINGEDGE COMPUTING
EDGE COMPUTING
Mosin A602 views
Breaking the Edge -- A Journey Through Cloud, Edge and Fog Computing by Angelo Corsaro
Breaking the Edge -- A Journey Through Cloud, Edge and Fog ComputingBreaking the Edge -- A Journey Through Cloud, Edge and Fog Computing
Breaking the Edge -- A Journey Through Cloud, Edge and Fog Computing
Angelo Corsaro778 views
Distributed Computing system by Sarvesh Meena
Distributed Computing system Distributed Computing system
Distributed Computing system
Sarvesh Meena4.5K views
Historical development of cloud computing by gaurav jain
Historical development of cloud computingHistorical development of cloud computing
Historical development of cloud computing
gaurav jain14.7K views
New Accelerated Compute Infrastructure Solutions from Supermicro by Rebekah Rodriguez
New Accelerated Compute Infrastructure Solutions from SupermicroNew Accelerated Compute Infrastructure Solutions from Supermicro
New Accelerated Compute Infrastructure Solutions from Supermicro
Rebekah Rodriguez113 views
Comet Cloud by pradeepas7
Comet CloudComet Cloud
Comet Cloud
pradeepas76.5K views
GREEN CLOUD COMPUTING BY SAIKIRAN PANJALA by Saikiran Panjala
GREEN CLOUD COMPUTING BY SAIKIRAN PANJALAGREEN CLOUD COMPUTING BY SAIKIRAN PANJALA
GREEN CLOUD COMPUTING BY SAIKIRAN PANJALA
Saikiran Panjala380 views
Data-Intensive Technologies for Cloud Computing by huda2018
Data-Intensive Technologies for CloudComputingData-Intensive Technologies for CloudComputing
Data-Intensive Technologies for Cloud Computing
huda20185.4K views

Similar to Edge Computing Platforms and Protocols - Ph.D. thesis

Open Source Edge Computing Platforms - Overview by
Open Source Edge Computing Platforms - OverviewOpen Source Edge Computing Platforms - Overview
Open Source Edge Computing Platforms - OverviewKrishna-Kumar
6.2K views32 slides
Feec telecom-nw-softwarization-aug-2015 by
Feec telecom-nw-softwarization-aug-2015Feec telecom-nw-softwarization-aug-2015
Feec telecom-nw-softwarization-aug-2015Christian Esteve Rothenberg
122 views37 slides
Multicloud as the Next Generation of Cloud Infrastructure by
Multicloud as the Next Generation of Cloud Infrastructure Multicloud as the Next Generation of Cloud Infrastructure
Multicloud as the Next Generation of Cloud Infrastructure Brad Eckert
151 views45 slides
Edge virtualisation for Carrier Networks by
Edge virtualisation for Carrier NetworksEdge virtualisation for Carrier Networks
Edge virtualisation for Carrier NetworksMyNOG
98 views13 slides
SDN 101: Software Defined Networking Course - Sameh Zaghloul/IBM - 2014 by
SDN 101: Software Defined Networking Course - Sameh Zaghloul/IBM - 2014SDN 101: Software Defined Networking Course - Sameh Zaghloul/IBM - 2014
SDN 101: Software Defined Networking Course - Sameh Zaghloul/IBM - 2014SAMeh Zaghloul
18.1K views125 slides
Innovations in Edge Computing and MEC by
Innovations in Edge Computing and MECInnovations in Edge Computing and MEC
Innovations in Edge Computing and MECSabidur Rahman
1.7K views20 slides

Similar to Edge Computing Platforms and Protocols - Ph.D. thesis(20)

Open Source Edge Computing Platforms - Overview by Krishna-Kumar
Open Source Edge Computing Platforms - OverviewOpen Source Edge Computing Platforms - Overview
Open Source Edge Computing Platforms - Overview
Krishna-Kumar 6.2K views
Multicloud as the Next Generation of Cloud Infrastructure by Brad Eckert
Multicloud as the Next Generation of Cloud Infrastructure Multicloud as the Next Generation of Cloud Infrastructure
Multicloud as the Next Generation of Cloud Infrastructure
Brad Eckert151 views
Edge virtualisation for Carrier Networks by MyNOG
Edge virtualisation for Carrier NetworksEdge virtualisation for Carrier Networks
Edge virtualisation for Carrier Networks
MyNOG98 views
SDN 101: Software Defined Networking Course - Sameh Zaghloul/IBM - 2014 by SAMeh Zaghloul
SDN 101: Software Defined Networking Course - Sameh Zaghloul/IBM - 2014SDN 101: Software Defined Networking Course - Sameh Zaghloul/IBM - 2014
SDN 101: Software Defined Networking Course - Sameh Zaghloul/IBM - 2014
SAMeh Zaghloul18.1K views
Innovations in Edge Computing and MEC by Sabidur Rahman
Innovations in Edge Computing and MECInnovations in Edge Computing and MEC
Innovations in Edge Computing and MEC
Sabidur Rahman1.7K views
Enabling the Deployment of Edge Services with the Open Network Edge Services ... by Liz Warner
Enabling the Deployment of Edge Services with the Open Network Edge Services ...Enabling the Deployment of Edge Services with the Open Network Edge Services ...
Enabling the Deployment of Edge Services with the Open Network Edge Services ...
Liz Warner1.1K views
Introduction to Software Defined Networking (SDN) presentation by Warren Finc... by APNIC
Introduction to Software Defined Networking (SDN) presentation by Warren Finc...Introduction to Software Defined Networking (SDN) presentation by Warren Finc...
Introduction to Software Defined Networking (SDN) presentation by Warren Finc...
APNIC223 views
Radisys/Wind River: The Telcom Cloud - Deployment Strategies: SDN/NFV and Vir... by Radisys Corporation
Radisys/Wind River: The Telcom Cloud - Deployment Strategies: SDN/NFV and Vir...Radisys/Wind River: The Telcom Cloud - Deployment Strategies: SDN/NFV and Vir...
Radisys/Wind River: The Telcom Cloud - Deployment Strategies: SDN/NFV and Vir...
Radisys Corporation3.4K views
Cloud computing ppt by A
Cloud computing pptCloud computing ppt
Cloud computing ppt
A 2.6K views
Introduction to cloud computing by Revathi Ram
Introduction to cloud computingIntroduction to cloud computing
Introduction to cloud computing
Revathi Ram536 views
Lect15 cloud by sree raj
Lect15 cloudLect15 cloud
Lect15 cloud
sree raj98 views
Lect15 cloud by Van Pham
Lect15 cloudLect15 cloud
Lect15 cloud
Van Pham296 views

More from Nitinder Mohan

Pruning Edge Research with Latency Shears by
Pruning Edge Research with Latency ShearsPruning Edge Research with Latency Shears
Pruning Edge Research with Latency ShearsNitinder Mohan
108 views20 slides
DeCloud: Truthful Decentralized Double Auction for Edge Clouds by
DeCloud: Truthful Decentralized Double Auction for Edge CloudsDeCloud: Truthful Decentralized Double Auction for Edge Clouds
DeCloud: Truthful Decentralized Double Auction for Edge CloudsNitinder Mohan
189 views33 slides
Big Data Frameworks: A primer on Apache Spark and MapReduce by
Big Data Frameworks: A primer on Apache Spark and MapReduceBig Data Frameworks: A primer on Apache Spark and MapReduce
Big Data Frameworks: A primer on Apache Spark and MapReduceNitinder Mohan
90 views38 slides
Open Infrastructure for Edge: A Distributed Ledger Outlook by
Open Infrastructure for Edge: A Distributed Ledger OutlookOpen Infrastructure for Edge: A Distributed Ledger Outlook
Open Infrastructure for Edge: A Distributed Ledger OutlookNitinder Mohan
172 views11 slides
ExEC: Elastic Extensible Edge Cloud by
ExEC: Elastic Extensible Edge Cloud ExEC: Elastic Extensible Edge Cloud
ExEC: Elastic Extensible Edge Cloud Nitinder Mohan
209 views31 slides
ICON: Intelligent Container Overlays by
ICON: Intelligent Container OverlaysICON: Intelligent Container Overlays
ICON: Intelligent Container OverlaysNitinder Mohan
236 views56 slides

More from Nitinder Mohan(12)

Pruning Edge Research with Latency Shears by Nitinder Mohan
Pruning Edge Research with Latency ShearsPruning Edge Research with Latency Shears
Pruning Edge Research with Latency Shears
Nitinder Mohan108 views
DeCloud: Truthful Decentralized Double Auction for Edge Clouds by Nitinder Mohan
DeCloud: Truthful Decentralized Double Auction for Edge CloudsDeCloud: Truthful Decentralized Double Auction for Edge Clouds
DeCloud: Truthful Decentralized Double Auction for Edge Clouds
Nitinder Mohan189 views
Big Data Frameworks: A primer on Apache Spark and MapReduce by Nitinder Mohan
Big Data Frameworks: A primer on Apache Spark and MapReduceBig Data Frameworks: A primer on Apache Spark and MapReduce
Big Data Frameworks: A primer on Apache Spark and MapReduce
Nitinder Mohan90 views
Open Infrastructure for Edge: A Distributed Ledger Outlook by Nitinder Mohan
Open Infrastructure for Edge: A Distributed Ledger OutlookOpen Infrastructure for Edge: A Distributed Ledger Outlook
Open Infrastructure for Edge: A Distributed Ledger Outlook
Nitinder Mohan172 views
ExEC: Elastic Extensible Edge Cloud by Nitinder Mohan
ExEC: Elastic Extensible Edge Cloud ExEC: Elastic Extensible Edge Cloud
ExEC: Elastic Extensible Edge Cloud
Nitinder Mohan209 views
ICON: Intelligent Container Overlays by Nitinder Mohan
ICON: Intelligent Container OverlaysICON: Intelligent Container Overlays
ICON: Intelligent Container Overlays
Nitinder Mohan236 views
Redesigning MPTCP in Edge clouds by Nitinder Mohan
Redesigning MPTCP in Edge cloudsRedesigning MPTCP in Edge clouds
Redesigning MPTCP in Edge clouds
Nitinder Mohan238 views
Anveshak: Placing Edge Servers In The Wild by Nitinder Mohan
Anveshak: Placing Edge Servers In The WildAnveshak: Placing Edge Servers In The Wild
Anveshak: Placing Edge Servers In The Wild
Nitinder Mohan285 views
MUTE: Multi-Tier Edge networks by Nitinder Mohan
MUTE: Multi-Tier Edge networksMUTE: Multi-Tier Edge networks
MUTE: Multi-Tier Edge networks
Nitinder Mohan354 views
Managing data in computational edge clouds by Nitinder Mohan
Managing data in computational edge cloudsManaging data in computational edge clouds
Managing data in computational edge clouds
Nitinder Mohan506 views
Edge-Fog Cloud: Scaling IoT computations on the edge by Nitinder Mohan
Edge-Fog Cloud: Scaling IoT computations on the edgeEdge-Fog Cloud: Scaling IoT computations on the edge
Edge-Fog Cloud: Scaling IoT computations on the edge
Nitinder Mohan1.1K views

Recently uploaded

Pollination By Nagapradheesh.M.pptx by
Pollination By Nagapradheesh.M.pptxPollination By Nagapradheesh.M.pptx
Pollination By Nagapradheesh.M.pptxMNAGAPRADHEESH
15 views9 slides
Artificial Intelligence Helps in Drug Designing and Discovery.pptx by
Artificial Intelligence Helps in Drug Designing and Discovery.pptxArtificial Intelligence Helps in Drug Designing and Discovery.pptx
Artificial Intelligence Helps in Drug Designing and Discovery.pptxabhinashsahoo2001
117 views22 slides
Batrachospermum.pptx by
Batrachospermum.pptxBatrachospermum.pptx
Batrachospermum.pptxnisarahmad632316
31 views37 slides
Ethical issues associated with Genetically Modified Crops and Genetically Mod... by
Ethical issues associated with Genetically Modified Crops and Genetically Mod...Ethical issues associated with Genetically Modified Crops and Genetically Mod...
Ethical issues associated with Genetically Modified Crops and Genetically Mod...PunithKumars6
18 views20 slides
ENTOMOLOGY PPT ON BOMBYCIDAE AND SATURNIIDAE.pptx by
ENTOMOLOGY PPT ON BOMBYCIDAE AND SATURNIIDAE.pptxENTOMOLOGY PPT ON BOMBYCIDAE AND SATURNIIDAE.pptx
ENTOMOLOGY PPT ON BOMBYCIDAE AND SATURNIIDAE.pptxMN
6 views13 slides
Conventional and non-conventional methods for improvement of cucurbits.pptx by
Conventional and non-conventional methods for improvement of cucurbits.pptxConventional and non-conventional methods for improvement of cucurbits.pptx
Conventional and non-conventional methods for improvement of cucurbits.pptxgandhi976
16 views35 slides

Recently uploaded(20)

Pollination By Nagapradheesh.M.pptx by MNAGAPRADHEESH
Pollination By Nagapradheesh.M.pptxPollination By Nagapradheesh.M.pptx
Pollination By Nagapradheesh.M.pptx
MNAGAPRADHEESH15 views
Artificial Intelligence Helps in Drug Designing and Discovery.pptx by abhinashsahoo2001
Artificial Intelligence Helps in Drug Designing and Discovery.pptxArtificial Intelligence Helps in Drug Designing and Discovery.pptx
Artificial Intelligence Helps in Drug Designing and Discovery.pptx
abhinashsahoo2001117 views
Ethical issues associated with Genetically Modified Crops and Genetically Mod... by PunithKumars6
Ethical issues associated with Genetically Modified Crops and Genetically Mod...Ethical issues associated with Genetically Modified Crops and Genetically Mod...
Ethical issues associated with Genetically Modified Crops and Genetically Mod...
PunithKumars618 views
ENTOMOLOGY PPT ON BOMBYCIDAE AND SATURNIIDAE.pptx by MN
ENTOMOLOGY PPT ON BOMBYCIDAE AND SATURNIIDAE.pptxENTOMOLOGY PPT ON BOMBYCIDAE AND SATURNIIDAE.pptx
ENTOMOLOGY PPT ON BOMBYCIDAE AND SATURNIIDAE.pptx
MN6 views
Conventional and non-conventional methods for improvement of cucurbits.pptx by gandhi976
Conventional and non-conventional methods for improvement of cucurbits.pptxConventional and non-conventional methods for improvement of cucurbits.pptx
Conventional and non-conventional methods for improvement of cucurbits.pptx
gandhi97616 views
Metatheoretical Panda-Samaneh Borji.pdf by samanehborji
Metatheoretical Panda-Samaneh Borji.pdfMetatheoretical Panda-Samaneh Borji.pdf
Metatheoretical Panda-Samaneh Borji.pdf
samanehborji16 views
Open Access Publishing in Astrophysics by Peter Coles
Open Access Publishing in AstrophysicsOpen Access Publishing in Astrophysics
Open Access Publishing in Astrophysics
Peter Coles543 views
A training, certification and marketing scheme for informal dairy vendors in ... by ILRI
A training, certification and marketing scheme for informal dairy vendors in ...A training, certification and marketing scheme for informal dairy vendors in ...
A training, certification and marketing scheme for informal dairy vendors in ...
ILRI10 views
Connecting communities to promote FAIR resources: perspectives from an RDA / ... by Allyson Lister
Connecting communities to promote FAIR resources: perspectives from an RDA / ...Connecting communities to promote FAIR resources: perspectives from an RDA / ...
Connecting communities to promote FAIR resources: perspectives from an RDA / ...
Allyson Lister33 views
Experimental animal Guinea pigs.pptx by Mansee Arya
Experimental animal Guinea pigs.pptxExperimental animal Guinea pigs.pptx
Experimental animal Guinea pigs.pptx
Mansee Arya10 views
Guinea Pig as a Model for Translation Research by PervaizDar1
Guinea Pig as a Model for Translation ResearchGuinea Pig as a Model for Translation Research
Guinea Pig as a Model for Translation Research
PervaizDar111 views
PRINCIPLES-OF ASSESSMENT by rbalmagro
PRINCIPLES-OF ASSESSMENTPRINCIPLES-OF ASSESSMENT
PRINCIPLES-OF ASSESSMENT
rbalmagro11 views
CSF -SHEEBA.D presentation.pptx by SheebaD7
CSF -SHEEBA.D presentation.pptxCSF -SHEEBA.D presentation.pptx
CSF -SHEEBA.D presentation.pptx
SheebaD710 views
Synthesis and Characterization of Magnetite-Magnesium Sulphate-Sodium Dodecyl... by GIFT KIISI NKIN
Synthesis and Characterization of Magnetite-Magnesium Sulphate-Sodium Dodecyl...Synthesis and Characterization of Magnetite-Magnesium Sulphate-Sodium Dodecyl...
Synthesis and Characterization of Magnetite-Magnesium Sulphate-Sodium Dodecyl...
GIFT KIISI NKIN14 views
Workshop Chemical Robotics ChemAI 231116.pptx by Marco Tibaldi
Workshop Chemical Robotics ChemAI 231116.pptxWorkshop Chemical Robotics ChemAI 231116.pptx
Workshop Chemical Robotics ChemAI 231116.pptx
Marco Tibaldi95 views
별헤는 사람들 2023년 12월호 전명원 교수 자료 by sciencepeople
별헤는 사람들 2023년 12월호 전명원 교수 자료별헤는 사람들 2023년 12월호 전명원 교수 자료
별헤는 사람들 2023년 12월호 전명원 교수 자료
sciencepeople7 views
A Ready-to-Analyze High-Plex Spatial Signature Development Workflow for Cance... by InsideScientific
A Ready-to-Analyze High-Plex Spatial Signature Development Workflow for Cance...A Ready-to-Analyze High-Plex Spatial Signature Development Workflow for Cance...
A Ready-to-Analyze High-Plex Spatial Signature Development Workflow for Cance...
Distinct distributions of elliptical and disk galaxies across the Local Super... by Sérgio Sacani
Distinct distributions of elliptical and disk galaxies across the Local Super...Distinct distributions of elliptical and disk galaxies across the Local Super...
Distinct distributions of elliptical and disk galaxies across the Local Super...
Sérgio Sacani30 views

Edge Computing Platforms and Protocols - Ph.D. thesis

  • 1. Edge Computing Platforms and Protocols Nitinder Mohan
  • 2. Cloud Computing • Global network of inter-connected datacenters • Datacenters managed and operated by cloud providers, e.g. Google, Microsoft, Amazon etc. • Developers can deploy their applications on virtualized resources of the cloud worldwide 1 More than 60% of Internet workloads are cloud-based
  • 3. Next Generation Applications Trends by year 2025 • More than 75 billion connected devices • Expected 11 trillion USD market share • On average 7 sensors per person worldwide Requirements 1. Latency-critical processing 2. Big data aggregation and analysis 3. Location and context aware computations Internet-of-Things 3
  • 4. Problem: Network! Ø High transport cost Ø High data volume Ø High network latency Can Cloud support next-generation applications? 4
  • 5. Edge Computing Small-scale server(s) deployed near the users to compute generated data Benefits: üDecreased latency for computation üReduced network load due to pre-processing üLocation and contextual awareness Network DatacenterEdge Server User 5
  • 6. Problems in Edge computing 1. Unmanaged hardware 2. Constrained network 3. Inconsistent reliability and availability 4. Lack of standardized protocols 6
  • 7. Hardware Deployment, Cooling, Maintenance Infrastructure Processing, Storage, Networking Platform Virtual Machines, Containers, Databases Software Parental Control, Firewall, Content Catalog, User Authentication Cloud Computing Service Model 7
  • 8. Hardware Deployment, Cooling, Maintenance Infrastructure Processing, Storage, Networking Platform Virtual Machines, Containers, Databases Software Cloud Computing Service Model Edge Computing Service Model Hardware Organization? Installation? Maintenance? Security? Infrastructure Mobile hardware? Limited processing? Low storage? Wireless/Cellular NICs? Platform Server Discovery? Self-Organizing Containers? Parental Control, Firewall, Content Catalog, User Authentication Factory Automation, Intelligence, Autonomous vehicles, IoT Analytics Cloud providers? Crowdsourced? ISPs? Light-weight VM? Mirage OS? Unikernels? Smartphone manufactures? Specialized servers? 7
  • 9. Hardware Thesis Contributions Edge-Fog Cloud: All-inclusive, node-oriented edge computing architecture which logically categorizes resources in layers. Anveshak: Deployment framework that assists service providers to identify best locations in a geographical region for installing edge servers. Infrastructure QAware: Cross-layer scheduler for Multipath TCP which allows edge servers to use multiple network paths simultaneously while overcoming excessive buffering and delays on any path. Data Grouping protocol: Edge caching mechanism which predicts and pre-caches prerequisite data in local caches of edge servers for upcoming computations. LPCF & eLPCF: Task allocation frameworks which distributes application jobs on a cluster of edge servers while minimizing processing, networking and energy costs. Platform ICON: Self-managing virtualized containers which can automatically migrate and replicate to servers experiencing more user traffic without involving application owner. ExEC: Open platform which allows cloud providers to discover and utilize resources offered by third- party edge providers operating in the network. 8
  • 10. Hardware Thesis Contributions Edge-Fog Cloud: All-inclusive, node-oriented edge computing architecture which logically categorizes resources in layers. Anveshak: Deployment framework that assists service providers to identify best locations in a geographical region for installing edge servers. Infrastructure QAware: Cross-layer scheduler for Multipath TCP which allows edge servers to use multiple network paths simultaneously while overcoming excessive buffering and delays on any path. Data Grouping protocol: Edge caching mechanism which predicts and pre-caches prerequisite data in local caches of edge servers for upcoming computations. LPCF & eLPCF: Task allocation frameworks which distributes application jobs on a cluster of edge servers while minimizing processing, networking and energy costs. Platform ICON: Self-managing virtualized containers which can automatically migrate and replicate to servers experiencing more user traffic without involving application owner. ExEC: Open platform which allows cloud providers to discover and utilize resources offered by third- party edge providers operating in the network. 8
  • 11. Hardware Thesis Contributions Edge-Fog Cloud: All-inclusive, node-oriented edge computing architecture which logically categorizes resources in layers. Anveshak: Deployment framework that assists service providers to identify best locations in a geographical region for installing edge servers. Infrastructure QAware: Cross-layer scheduler for Multipath TCP which allows edge servers to use multiple network paths simultaneously while overcoming excessive buffering and delays on any path. Data Grouping protocol: Edge caching mechanism which predicts and pre-caches prerequisite data in local caches of edge servers for upcoming computations. LPCF & eLPCF: Task allocation frameworks which distributes application jobs on a cluster of edge servers while minimizing processing, networking and energy costs. Platform ICON: Self-managing virtualized containers which can automatically migrate and replicate to servers experiencing more user traffic without involving application owner. ExEC: Open platform which allows cloud providers to discover and utilize resources offered by third- party edge providers operating in the network. How to do computations on edge clouds?
  • 12. Hardware Thesis Contributions Edge-Fog Cloud: All-inclusive, node-oriented edge computing architecture which logically categorizes resources in layers. Anveshak: Deployment framework that assists service providers to identify best locations in a geographical region for installing edge servers. Infrastructure QAware: Cross-layer scheduler for Multipath TCP which allows edge servers to use multiple network paths simultaneously while overcoming excessive buffering and delays on any path. Data Grouping protocol: Edge caching mechanism which predicts and pre-caches prerequisite data in local caches of edge servers for upcoming computations. LPCF & eLPCF: Task allocation frameworks which distributes application jobs on a cluster of edge servers while minimizing processing, networking and energy costs. Platform ICON: Self-managing virtualized containers which can automatically migrate and replicate to servers experiencing more user traffic without involving application owner. ExEC: Open platform which allows cloud providers to discover and utilize resources offered by third- party edge providers operating in the network. 8
  • 13. Requirement of Edge Computing Need of a reference architecture for designing protocols and platforms! Constraints? Capabilities? Capacities? 9
  • 14. Edge-Fog Cloud (EFCloud) Edge Ø Collection of devices: i. Loosely-coupled ii. Voluntary/Crowdsourced iii. Owned by independent operators Ø Extremely close to sensors & clients Ø Device-to-device connectivity over WiFi/cellular/Bluetooth/Zigbee etc. Ø Varying processing capability e.g. desktops, laptops, workstations, nano data centers etc. 10
  • 15. Edge-Fog Cloud (EFCloud) Fog Ø High capacity compute servers Ø Co-located with networking devices Ø Designed, manufactured, managed and deployed by cloud vendors Ø Lies farther from sensors and clients Ø Dense connectivity within layer Ø Support for virtualization technologies e.g. routers, switches, basestations etc. 11
  • 16. Edge-Fog Cloud (EFCloud) Data Store Ø Data archival and storage Ø No computation on data Ø Reliable, ease-of-access, secure and global access to storage for Edge and Fog resources 12
  • 17. Edge-Fog Cloud (EFCloud) Salient Features 1. All-inclusive edge architecture 2. Native support for mobility 3. Satisfies emerging application requirements 4. Context-aware computation 5. No single point-of-failure 6. No vendor lock-in 13
  • 18. Hardware Thesis Contributions Edge-Fog Cloud: All-inclusive, node-oriented edge computing architecture which logically categorizes resources in layers. Anveshak: Deployment framework that assists service providers to identify best locations in a geographical region for installing edge servers. Infrastructure QAware: Cross-layer scheduler for Multipath TCP which allows edge servers to use multiple network paths simultaneously while overcoming excessive buffering and delays on any path. Data Grouping protocol: Edge caching mechanism which predicts and pre-caches prerequisite data in local caches of edge servers for upcoming computations. LPCF & eLPCF: Task allocation frameworks which distributes application jobs on a cluster of edge servers while minimizing processing, networking and energy costs. Platform ICON: Self-managing virtualized containers which can automatically migrate and replicate to servers experiencing more user traffic without involving application owner. ExEC: Open platform which allows cloud providers to discover and utilize resources offered by third- party edge providers operating in the network. 14
  • 20. Edge-Fog Cloud Formalizing Task Deployment𝜆/𝜋/BW 𝜆/𝜋/BW 𝜆/𝜋/BW 𝜆 / 𝜋/ BW 𝜆 / 𝜋/ BW 15
  • 21. Edge-Fog Cloud Formalizing Task Deployment D1 D2 D3 D4 D5 1 4 34 1 15
  • 22. Edge-Fog Cloud Formalizing Task Deployment D1 D2 D3 D4 D5 1 4 34 1 16
  • 23. Edge-Fog Cloud J1 J2 J3 J4 J5 Job Graph Formalizing Task Deployment D1 D2 D3 D4 D5 1 4 34 1 16
  • 24. J1 J2 J3 J4 J5 Formalizing Task Deployment D1 D2 D3 D4 D5 1 4 34 1 Objective: Find best placement of jobs on Edge and Fog devices 16
  • 25. D1 D2 D3 D4 D5 1 4 34 1 J1 J2 J3 J4 J5 ∞ 1 8 4 5 1 ∞ 7 5 4 8 7 ∞ 4 3 4 5 4 ∞ 1 5 4 3 1 ∞ 0 1 0 1 0 1 0 1 0 1 0 1 0 0 0 1 0 0 0 1 0 1 0 1 0 Dconn[ i,j ] = Jconn[ i,j ] = 17 De-facto: Network Only Cost Assignment
  • 26. De-facto: Network Only Cost Assignment Dconn[ i,j ] = 0 1 0 1 0 1 0 1 0 1 0 1 0 0 0 1 0 0 0 1 0 1 0 1 0 Jconn[ i,j ] = Quadratic Assignment Problem Minimize: NP-hard! • For 30 nodes, it will take 2500 servers to solve it • Optimal solution not guaranteed $ %(',))∈, 𝐽./00 𝑖, 𝑗 ∗ 𝐷./00(𝑓 𝑖 , 𝑓(𝑗)) ∞ 1 8 4 5 1 ∞ 7 5 4 8 7 ∞ 4 3 4 5 4 ∞ 1 5 4 3 1 ∞ 17
  • 27. Our Approach Optimize Processing Time Search Space Reduction Least Network Cost Least Processing Cost First (LPCF) Optimize Processing Energy Search Space Reduction Least Network Energy energy-efficient Least Processing Cost First (eLPCF) Multi-Objective Optimization D1 D2 D3 D4 D5 1 4 34 1 : 3 : 2 : 2 : 6: 5 D1 D2 D3 D4 D5 1 4 34 1 : 3 : 2 : 2 : 6: 5 18
  • 28. 18 Our Approach Optimize Processing Time Search Space Reduction Least Network Cost Least Processing Cost First (LPCF) Optimize Processing Energy Search Space Reduction Least Network Energy energy-efficient Least Processing Cost First (eLPCF) Multi-Objective Optimization D1 D2 D3 D4 D5 1 4 34 1 : 3 : 2 : 2 : 6: 5 D1 D2 D3 D4 D5 1 4 34 1 : 3 : 2 : 2 : 6: 5
  • 29. Least Processing Cost First (LPCF) D1:3 D2:2 D3:2 D4:5 D5:6 1 4 34 1 J1:4 J2:2 J3:5 J4:4 J5:2 3 2 2 5 6 4 2 5 4 2 Dproc [i] = Jsize [i] = 19
  • 30. Least Processing Cost First (LPCF) I. Optimize Processing Time Minimize: Linear Assignment Problem $ ',)∈, 𝐶 𝐽7'89(𝑖) 𝐷:;/.(𝑗) 𝑥') 3 2 2 5 6 4 2 5 4 2 Dproc [i] = Jsize [i] = 20
  • 31. I. Optimize Processing Time Minimize: Linear Assignment Problem • Solved using Kuhn-Munkres/ Hungarian algorithm • Optimal solution guaranteed in O(n3) Least Processing Cost First (LPCF) D1:3 D2:2 D3:2 D4:5 D5:6 1 4 34 1 J1:4 J2:2 J5:2 J4:4 J3:5 Least Processing Cost: 4.966 $ ',)∈, 𝐶 𝐽7'89(𝑖) 𝐷:;/.(𝑗) 𝑥') 20
  • 32. Least Processing Cost First (LPCF) II. Create sub-problem space Interchange homogeneous devices running homogeneous jobs Search Space Calculation: 1. Same processing power → interchange jobs 2. Same job size → interchange devices D1:3 D2:2 D3:2 D4:5 D5:6 1 4 34 1 J1:4 J2:2 J5:2 J4:4 J3:5 J1:4 J5:2 J2:2 J4:4 J3:5 J4:4 J5:2 J2:2 J1:4 J3:5 21
  • 33. Least Processing Cost First (LPCF) II. Create sub-problem space Interchange homogeneous devices running homogeneous jobs Search Space Calculation: 1. Same processing power → interchange jobs 2. Same job size → interchange devices Least Processing Cost: 4.966 D1 D2 D3 D4 D5 1. J1 J2 J5 J4 J3 2. J1 J5 J2 J4 J3 3. J4 J5 J2 J1 J3 4. J4 J2 J5 J1 J3 21
  • 34. Least Processing Cost First (LPCF) III. Least Network Cost 1. Compute network cost of each assignment 2. Choose the assignment with least network cost 𝐽./00 𝑖, 𝑗 ∗ 𝐷./00(𝑓 𝑖 , 𝑓(𝑗)) D1 D2 D3 D4 D5 1. J1 J2 J5 J4 J3 2. J1 J5 J2 J4 J3 3. J4 J5 J2 J1 J3 4. J4 J2 J5 J1 J3 N/W 20 27 19 28 Least Processing Cost: 4.966 22
  • 35. Performance Overview 5 20 40 60 80 100 Topology Size 0 1000 2000 3000 4000 NetworkCost NOC LPCF Minimum bound Maximum bound 20 40 60 80 100 Topology Size 0 50 100 150 200 250 ProcessingCost NOC LPCF eLPCF 5 20 40 60 80 100 Topology Size 5 10 15 20 25 30 %decreaseinenergy Edge Fog Network cost remains within 10% range of the optimal value Processing cost is multiple times lower than de-facto solvers 10% decrease in overall energy used. More than 20% energy saved for battery constrained devices 24
  • 36. Hardware Thesis Contributions Edge-Fog Cloud: All-inclusive, node-oriented edge computing architecture which logically categorizes resources in layers. Anveshak: Deployment framework that assists service providers to identify best locations in a geographical region for installing edge servers. Infrastructure QAware: Cross-layer scheduler for Multipath TCP which allows edge servers to use multiple network paths simultaneously while overcoming excessive buffering and delays on any path. Data Grouping protocol: Edge caching mechanism which predicts and pre-caches prerequisite data in local caches of edge servers for upcoming computations. LPCF & eLPCF: Task allocation frameworks which distributes application jobs on a cluster of edge servers while minimizing processing, networking and energy costs. Platform ICON: Self-managing virtualized containers which can automatically migrate and replicate to servers experiencing more user traffic without involving application owner. ExEC: Open platform which allows cloud providers to discover and utilize resources offered by third- party edge providers operating in the network. 25
  • 37. Hardware PublicationsInfrastructurePlatform Anveshak: Placing Edge Servers In The Wild. N. Mohan, A. Zavodovski, P. Zhou, and J. Kangasharju, MECOMM 2018 Placing it right!: optimizing energy, processing, and transport in Edge-Fog clouds. N. Mohan and J. Kangasharju, Annals of Telecommunication 2018 Managing Data in Computational Edge Cloud. N. Mohan, P. Zhou, K. Govindaraj and J. Kangasharju, MECOMM 2017 QAware: A Cross-Layer Approach to MPTCP Scheduling. T. Shreedhar, N. Mohan, S.K. Kaul, & J. Kangasharju. IFIP Networking 2018 ExEC: Elastic Extensible Edge Cloud. A. Zavodovski, N. Mohan, S. Bayhan, W. Wong and J. Kangasharju, EdgeSys 2019 ICON: Intelligent Container Overlays. A. Zavodovski, N. Mohan, S. Bayhan, W. Wong and J. Kangasharju, HotNets 2018 Is two greater than one?: Analyzing Multipath TCP over Dual-LTE in the Wild. N. Mohan, T. Shreedhar, A. Zavodovski, J. Kangasharju & S.K. Kaul. Manuscript 2019. 25
  • 39. Next Generation Applications Industrial Automation Autonomous Vehicles Augmented Reality Remote Monitoring & Collaboration Autonomous Drones & many more .. Smart Homes
  • 40. 2
  • 42. Edge computing Multiple edge computing approaches have been proposed i. Cloudlets → Miniature datacenters Network
  • 43. Edge computing Multiple edge computing approaches have been proposed i. Cloudlets → Miniature datacenters ii. Fog → Network devices (Base stations, Routers) Network
  • 44. Edge computing Multiple edge computing approaches have been proposed i. Cloudlets → Miniature datacenters ii. Fog → Network devices (Base stations, Routers) iii. Edge → Crowdsourced (smartphones, smart speakers) Network
  • 45. Edge computing Multiple edge computing approaches have been proposed i. Cloudlets → Miniature datacenters ii. Fog → Network devices (Base stations, Routers) iii. Edge → Crowdsourced (smartphones, smart speakers, ..) iv. Mist → Data generators (sensors, microcontrollers, ..) Network
  • 46. Hardware Deployment, Cooling, Maintenance Infrastructure Processing, Storage, Networking Platform Virtual Machines, Containers, Databases Software Parental Control, Firewall, Content Catalog, User Authentication Cloud Computing Service Model Edge Computing Service Model
  • 47. Hardware Deployment, Cooling, Maintenance Infrastructure Processing, Storage, Networking Platform Virtual Machines, Containers, Databases Software Cloud Computing Service Model Edge Computing Service Model Parental Control, Firewall, Content Catalog, User Authentication Factory Automation, Intelligence, Autonomous vehicles, IoT Analytics
  • 48. Hardware Deployment, Cooling, Maintenance Infrastructure Processing, Storage, Networking Platform Virtual Machines, Containers, Databases Software Cloud Computing Service Model Edge Computing Service Model Hardware Organization? Installation? Maintenance? Security? Parental Control, Firewall, Content Catalog, User Authentication Factory Automation, Intelligence, Autonomous vehicles, IoT Analytics Cloud providers? Crowdsourced? Cellular providers?
  • 49. Hardware Deployment, Cooling, Maintenance Infrastructure Processing, Storage, Networking Platform Virtual Machines, Containers, Databases Software Cloud Computing Service Model Edge Computing Service Model Hardware Organization? Installation? Maintenance? Security? Infrastructure Mobile hardware? Limited processing? Low storage? Wireless/Cellular NICs? Parental Control, Firewall, Content Catalog, User Authentication Factory Automation, Intelligence, Autonomous vehicles, IoT Analytics Cloud providers? Crowdsourced? Cellular providers?
  • 50. Hardware Deployment, Cooling, Maintenance Infrastructure Processing, Storage, Networking Platform Virtual Machines, Containers, Databases Cloud Computing Service Model Edge Computing Service Model Hardware Organization? Installation? Maintenance? Security? Infrastructure Mobile hardware? Limited processing? Low storage? Wireless/Cellular NICs? Platform Server Discovery? Self-Organizing Containers? Unikernels? Cloud providers? Crowdsourced? Cellular providers? Software Parental Control, Firewall, Content Catalog, User Authentication Factory Automation, Intelligence, Autonomous vehicles, IoT Analytics
  • 51. Hardware Thesis Research Questions RQ2: Can independent entities enroll their compute resources in an existing edge cloud platform? RQ1: Where should the cloud providers install compute servers in the physical world to satisfy the application requirements at the "edge"? Infrastructure RQ6: How do we assure datacenter-like network behavior over edge servers which operate on a public wireless network? RQ5: Can existing network technologies available at the edge support the requirements imposed by end-applications for optimal performance? RQ4: How to pre-cache computational data within edge servers to improve computations? RQ3: How do we utilize availability and variability of edge servers for computing tasks? Platform RQ9: How can independent edge providers generate revenue at par with cloud providers? RQ8: How can edge cloud ensure the promised Quality-of-Service despite variability in user requests and infrastructure hardware? RQ7: How can existing cloud virtualization technologies be exploited in edge clouds?
  • 52. Hardware Thesis Research Questions RQ2: Can independent entities enroll their compute resources in an existing edge cloud platform? RQ1: Where should the cloud providers install compute servers in the physical world to satisfy the application requirements at the "edge"? Infrastructure RQ6: How do we assure datacenter-like network behavior over edge servers which operate on a public wireless network? RQ5: Can existing network technologies available at the edge support the requirements imposed by end-applications for optimal performance? RQ4: How to pre-cache computational data within edge servers to improve computations? RQ3: How do we utilize availability and variability of edge servers for computing tasks? Platform RQ9: How can independent edge providers generate revenue at par with cloud providers? RQ8: How can edge cloud ensure the promised Quality-of-Service despite variability in user requests and infrastructure hardware? RQ7: How can existing cloud virtualization technologies be exploited in edge clouds?
  • 53. Can independent entities enroll their compute resources in an existing edge cloud platform? Hardware Infrastructure Platform
  • 54. Hardware Infrastructure Platform How do we utilize availability and variability of edge servers for computing tasks?
  • 55. Deploying Tasks on Edge Clouds Edge clouds cannot use existing datacenter-based assignment protocols as Edge and Fog recourses can: 1. operate in non-to-semi unmanaged environments with variable availability 2. be equipped with constrained processing hardware requiring multiple servers to complete single task 3. be inter-connected via wireless network links prone to latency and congestion 4. be powered by limited battery capacity
  • 56. Task Deployment on EFCloud Network-Only Cost Solver 1. Finds job placement which has the least possible network cost 2. Very large problem search space 3. NP-hard optimization with no guarantee for optimal solution Least Processing Cost First 1. Finds job placement with least processing cost and almost-least networking cost 2. Reduced problem search space 3. Placement guaranteed for any problem size in linear time 23
  • 57. Hardware Infrastructure Platform How can existing cloud virtualization technologies be exploited in edge clouds?
  • 58. Deploying Cloud Applications Cloud applications are composed of multiple integrated (micro)services Catalog Retrieval Parental Control Application Metrics Exception Tracking Audit Logging Health Check … 700+
  • 59. Deploying Cloud Applications Cloud applications are composed of multiple integrated (micro)services → Every microservice is encapsulated as virtualized container which is then deployed on the cloud Parental Control Catalog Retrieval Catalog Retrieval Parental Control Application Metrics Exception Tracking Audit Logging Health Check … 700+
  • 63. Container Migration on Cloud Does not work in Edge-Fog Clouds!
  • 64. Fragmentation in EFCloud EFCloud is amalgamation of different managing entities with strict authoritative boundaries
  • 65. Fragmentation in EFCloud EFCloud is amalgamation of different managing entities with strict authoritative boundaries 1. ISP-backed Fog + Cellular-based Edge EdgeFog
  • 66. Fragmentation in EFCloud EFCloud is amalgamation of different managing entities with strict authoritative boundaries 1. ISP-backed Fog + Cellular-based Edge 2. WiFi router Fog + Crowdsourced Edge EdgeFog
  • 67. Fragmentation in EFCloud EFCloud is amalgamation of different managing entities with strict authoritative boundaries 1. ISP-backed Fog + Cellular-based Edge 2. WiFi router Fog + Crowdsourced Edge 3. Fog of cloud providers + Independent Edge servers EdgeFog
  • 68. Fragmentation in EFCloud EFCloud is amalgamation of different managing entities with strict authoritative boundaries 1. ISP-backed Fog + Cellular-based Edge 2. WiFi router Fog + Crowdsourced Edge 3. Fog of cloud providers + Independent Edge servers Multiple entities compete in/across every grouping for larger market share → Heterogeneity in Hardware and Software! EdgeFog
  • 69. Intelligent Containers (ICONs) Self-managing virtualized services which can intelligently and automatically move to edge servers nearest to incoming user requests
  • 70. Intelligent Containers (ICONs) Self-managing virtualized services which can intelligently and automatically move to edge servers* nearest to incoming user requests *irrespective of who owns/operates them
  • 71. Operation of ICON ICON Edge/Fog End-users I. Initially, ICON is in the cloud One or multiple origination points
  • 72. Operation of ICON ICON End-users Edge/Fog I. Initially, ICON is in the cloud One or multiple origination points II. ICON monitors incoming flows Where user requests are coming from?
  • 73. Operation of ICON ICON End-users Discover Edge/Fog I. Initially, ICON is in the cloud One or multiple origination points II. ICON monitors incoming flows Where user requests are coming from? III. ICON discovers deployment locations In the domain of end-users or on a path to it
  • 74. Operation of ICON ICON End-users Replicate Discover Edge/Fog I. Initially, ICON is in the cloud One or multiple origination points II. ICON monitors incoming flows Where user requests are coming from? III. ICON discovers deployment locations In the domain of end-users or on a path to it IV. ICON can take autonomous decisions i. Deploy replica of itself
  • 75. Operation of ICON ICON End-users Use Edge Discover Edge/Fog I. Initially, ICON is in the cloud One or multiple origination points II. ICON monitors incoming flows Where user requests are coming from? III. ICON discovers deployment locations In the domain of end-users or on a path to it IV. ICON can take autonomous decisions i. Deploy replica of itself
  • 76. I. Initially, ICON is in the cloud One or multiple origination points II. ICON monitors incoming flows Where user requests are coming from? III. ICON discovers deployment locations In the domain of end-users or on a path to it IV. ICON can take autonomous decisions i. Deploy replica of itself ii. Migrate closer to the end-users ICON End-users Migrate Operation of ICON Edge/Fog
  • 77. Salient Features of ICONs • Capability to automatically move application services across administrative boundaries • Self-organizing architecture with zero management overhead • Developers can tune the Quality-of-Experience by easily setting budget and latency weights • Hierarchical overlay with minimal communication overhead • Automatic termination with budget reallocation based on thresholds