ACACIA Context-aware Edge Computing for Continuous Interactive - - PowerPoint PPT Presentation

▶
acacia context aware edge computing for
SMART_READER_LITE
LIVE PREVIEW

ACACIA Context-aware Edge Computing for Continuous Interactive - - PowerPoint PPT Presentation

Dec 16, 2022 379 likes •1.16k views

ACACIA Context-aware Edge Computing for Continuous Interactive Applications over Mobile Networks Junguk Cho , Jacobus Van der Merwe, Karthikeyan Sundaresan, Rajesh Mahindra, and Sampath Rangarajan 1 Continuous Interactive (CI) Mobile Apps

slide-1
SLIDE 1

ACACIA – Context-aware Edge Computing for Continuous Interactive Applications over Mobile Networks

Junguk Cho, Jacobus Van der Merwe, Karthikeyan Sundaresan, Rajesh Mahindra, and Sampath Rangarajan

1

slide-2
SLIDE 2
  • Emerging Continuous Interactive (CI) mobile applications at scale

Continuous Interactive (CI) Mobile Apps

2

slide-3
SLIDE 3
  • Emerging Continuous Interactive (CI) mobile applications at scale
  • Example of Continuous Interactive (CI) mobile apps

Continuous Interactive (CI) Mobile Apps

3

slide-4
SLIDE 4
  • Emerging Continuous Interactive (CI) mobile applications at scale
  • Example of Continuous Interactive (CI) mobile apps
  • Augmented reality (AR)

Continuous Interactive (CI) Mobile Apps

4

slide-5
SLIDE 5
  • Emerging Continuous Interactive (CI) mobile applications at scale
  • Example of Continuous Interactive (CI) mobile apps
  • Augmented reality (AR)
  • Face Recognition

Continuous Interactive (CI) Mobile Apps

5

slide-6
SLIDE 6
  • Emerging Continuous Interactive (CI) mobile applications at scale
  • Example of Continuous Interactive (CI) mobile apps
  • Augmented reality (AR)
  • Face Recognition
  • Virtual Reality (VR)

Continuous Interactive (CI) Mobile Apps

6

slide-7
SLIDE 7
  • Emerging Continuous Interactive (CI) mobile applications at scale
  • Example of Continuous Interactive (CI) mobile apps
  • Augmented reality (AR)
  • Face Recognition
  • Virtual Reality (VR)
  • Autonomous driving

Continuous Interactive (CI) Mobile Apps

7

slide-8
SLIDE 8

Characteristics of CI Mobile Apps

  • Highly responsive (~ 100 ms)
  • Overlay information (graphics, text or video) should be shown in real-time
  • Intensive computation
  • Too slow to run completely on mobile devices
  • Have centralized databases in the server

8

slide-9
SLIDE 9

Enablers for CI Mobile Apps

9

Computation offloading to cloud

slide-10
SLIDE 10

Enablers for CI Mobile Apps

10

Mobile network

slide-11
SLIDE 11

Enablers for CI Mobile Apps

11

slide-12
SLIDE 12

Enablers for CI Mobile Apps

12

User Context

slide-13
SLIDE 13

Enablers for CI Mobile Apps

13

slide-14
SLIDE 14

Each Components Have Evolved a Lot

14

slide-15
SLIDE 15

Standalone Approach Is Not Sufficient

  • The end to end latency of CI apps is affected by various factors
  • Network conditions (bandwidth & latency)
  • Application computation latency (object matching computation)

15

slide-16
SLIDE 16

Standalone Approach Is Not Sufficient

  • The end to end latency of CI apps is affected by various factors
  • Network conditions (bandwidth & latency)
  • Application computation latency (object matching computation)
  • Each approach treats others as blackbox
  • Computation offloading framework
  • No consideration of mobile network complexities
  • Evolving mobile network & context information
  • No well-defined protocol and interface to make synergies among them

16

slide-17
SLIDE 17

?

Need a General and Holistic E2E Approach

Application Mobile Network User Context

17

slide-18
SLIDE 18

Key Questions?

18

How should the three entities (application, network, and user) be jointly orchestrated and combined in a service abstraction over mobile networks to enable CI mobile applications?

?

Application Mobile Network User Context

slide-19
SLIDE 19

ACACIA

  • A service abstraction frameworks could be provided by

mobile operators

19

slide-20
SLIDE 20

ACACIA

  • A service abstraction frameworks could be provided by

mobile operators

  • A general and holistic end-to-end approach to enabling

CI services on edge clouds over mobile network

20

slide-21
SLIDE 21

ACACIA

  • A service abstraction frameworks could be provided by

mobile operators

  • A general and holistic end-to-end approach to enabling

CI services on edge clouds over mobile network

  • Leverage client context information through LTE-direct
  • Orchestrate three entities
  • Optimize both network and application processing

21

slide-22
SLIDE 22

ACACIA Usecase – Retail Mall

22

slide-23
SLIDE 23

AR Available in Laptop Section

Laptop SALESMAN

ACACIA Usecase – Retail Mall

AR Available in Food Section

Food SALESMAN

23

slide-24
SLIDE 24

AR Available in Laptop Section

Laptop SALESMAN

ACACIA Usecase – Retail Mall

AR Available in Food Section

Food SALESMAN

24

Retail App “Interest” in laptop

slide-25
SLIDE 25

Laptop SALESMAN

ACACIA Usecase – Retail Mall

Food SALESMAN Retail App “Interest” in laptop “Interest” Match “Interest” non- Match

25

AR Available in Laptop Section AR Available in Food Section

slide-26
SLIDE 26

Laptop SALESMAN

ACACIA Usecase – Retail Mall

Food SALESMAN Retail AR App “Interest” in laptop Mobile Edge Clouds Retail AR server

26

AR Available in Laptop Section AR Available in Food Section

slide-27
SLIDE 27

ACACIA Architecture

27

slide-28
SLIDE 28

User Context Discovery

28

slide-29
SLIDE 29

ACACIA Mobile Edge Network

29

slide-30
SLIDE 30

Context-aware Application Optimization

30

slide-31
SLIDE 31

User Context Discovery

31

slide-32
SLIDE 32

Android Framework SUBSCRIBER Modem(LTE)

Sub/CI App ACACIA device manager

  • Works as a proxy between CI apps and LTE modem

ACACIA Device Manager

32

Push “Interest”

DISCOVERY SUBSCRIBE FILTER

Android Framework PUBLISHER Modem(LTE)

Pub App ACACIA device manager DISCOVERY PUBLISH FILTER

slide-33
SLIDE 33

Android Framework SUBSCRIBER Modem(LTE)

Sub/CI App ACACIA device manager

  • Works as a proxy between CI apps and LTE modem

ACACIA Device Manager

33

DISCOVERY SUBSCRIBE FILTER

Android Framework PUBLISHER Modem(LTE)

Pub App ACACIA device manager DISCOVERY PUBLISH FILTER

Listen

slide-34
SLIDE 34

Android Framework SUBSCRIBER Modem(LTE)

Sub/CI App ACACIA device manager

  • Works as a proxy between CI apps and LTE modem

ACACIA Device Manager

34

DISCOVERY SUBSCRIBE FILTER

Android Framework PUBLISHER Modem(LTE)

Pub App ACACIA device manager DISCOVERY PUBLISH FILTER

Listen Push “Service”

slide-35
SLIDE 35

Android Framework SUBSCRIBER Modem(LTE)

Sub/CI App ACACIA device manager

  • Works as a proxy between CI apps and LTE modem

ACACIA Device Manager

35

DISCOVERY SUBSCRIBE FILTER

Android Framework PUBLISHER Modem(LTE)

Pub App ACACIA device manager DISCOVERY PUBLISH FILTER

Listen LTE-Direct BROADCAST

slide-36
SLIDE 36

Android Framework SUBSCRIBER Modem(LTE)

Sub/CI App ACACIA device manager

  • Works as a proxy between CI apps and LTE modem

ACACIA Device Manager

36

DISCOVERY SUBSCRIBE FILTER

Android Framework PUBLISHER Modem(LTE)

Pub App ACACIA device manager DISCOVERY PUBLISH FILTER

LTE-Direct BROADCAST IF MATCH ?

slide-37
SLIDE 37
  • Manage the network connectivity on demand

ACACIA Device Manager

37

First Match

slide-38
SLIDE 38
  • Manage the network connectivity on demand

ACACIA Device Manager

38

First Match

slide-39
SLIDE 39

39

ACACIA Mobile Edge Network

slide-40
SLIDE 40

LTE GW-U

Internet

Mobile Edge Clouds CI Server

Local LTE GW-U

40

ACACIA Mobile Edge Network

Mobile Core Component eNodeB

slide-41
SLIDE 41

LTE GW-U

Internet

Mobile Edge Clouds CI Server

CI APP

Local LTE GW-U

41

ACACIA Mobile Edge Network

Mobile Core Component eNodeB

slide-42
SLIDE 42

LTE GW-U

Internet

Mobile Edge Clouds CI Server

CI APP

Local LTE GW-U

42

ACACIA Mobile Edge Network

Mobile Core Component eNodeB

slide-43
SLIDE 43

LTE GW-U

Internet

Mobile Edge Clouds CI Server

Local LTE GW-U

43

ACACIA Mobile Edge Network

Mobile Core Component eNodeB

slide-44
SLIDE 44

LTE GW-U

Internet

Mobile Edge Clouds CI Server

Local LTE GW-U

44

ACACIA Mobile Edge Network

Mobile Core Component eNodeB

slide-45
SLIDE 45
  • On demand connectivity
  • Reduce control overhead due to two always-on connectivity
  • Fine-grained CI traffic control in LTE eNodeB and LTE GWs based on service types
  • No Impact on the rest of traffic
  • Cost effective
  • Without deploying middlebox for selective CI traffic
  • 3GPP standard compatible
  • Without modification of eNodeB, LTE interfaces and protocol

Requirements of ACACIA Mobile Edge Network

45

slide-46
SLIDE 46
  • On demand connectivity
  • Reduce control overhead due to two always-on connectivity
  • Fine-grained CI traffic control in LTE eNodeB and LTE GWs based on service types
  • No Impact on the rest of traffic
  • Cost effective
  • Without deploying middlebox for selective CI traffic
  • 3GPP standard compatible
  • Without modification of eNodeB, LTE interfaces and protocol

Requirements of ACACIA Mobile Edge Network

46

LTE/EPC QoS bearer framework with LTE Gateways using SDN & NFV

slide-47
SLIDE 47
  • Request mobile edge clouds connectivity

47

Steps to Set up Mobile Edge Connectivity

LTE GW-U

Internet

ACACIA Device Manager

Mobile Edge Clouds CI Server

CI APP

Local LTE GW-U Mobile Core Component eNodeB First Match

slide-48
SLIDE 48
  • LTE/EPC QoS bearer framework

48

Steps to Set up Mobile Edge Connectivity

LTE GW-U

Internet

ACACIA Device Manager

Mobile Edge Clouds CI Server

CI APP

Local LTE GW-U Mobile Core Component eNodeB

slide-49
SLIDE 49
  • LTE/EPC QoS bearer framework

49

Steps to Set up Mobile Edge Connectivity

LTE GW-U

Internet

ACACIA Device Manager

Mobile Edge Clouds CI Server

CI APP

Local LTE GW-U Mobile Core Component eNodeB

slide-50
SLIDE 50
  • LTE Gateways using SDN & NFV

50

Steps to Set up Mobile Edge Connectivity

LTE GW-U

Internet

ACACIA Device Manager

Mobile Edge Clouds CI Server

CI APP

Local LTE GW-U Mobile Core Component eNodeB

slide-51
SLIDE 51
  • LTE Gateways using SDN & NFV

51

Steps to Set up Mobile Edge Connectivity

LTE GW-U

Internet

ACACIA Device Manager

Mobile Edge Clouds CI Server

CI APP

Local LTE GW-U Mobile Core Component eNodeB

slide-52
SLIDE 52
  • LTE Gateways using SDN & NFV

52

Steps to Set up Mobile Edge Connectivity

LTE GW-U

Internet

ACACIA Device Manager

Mobile Edge Clouds CI Server

CI APP

Local LTE GW-U Mobile Core Component eNodeB

Traffic classification in LTE modem based on 5 tuples or other info

slide-53
SLIDE 53

Service Interests

53

?

slide-54
SLIDE 54

?

Service Interests

54

Mobile Edge Network

slide-55
SLIDE 55

> 1 sec

0.2 0.4 0.6 0.8 1 1.2

Object Matching Time (sec)

1440 * 1080 Image

1 Object 5 Objects 10 Objects 25 Objects 50 Objects

Application Processing is Still Heavy

55

slide-56
SLIDE 56

Database pruning!

0.2 0.4 0.6 0.8 1 1.2

Object Matching Time (sec)

1440 * 1080 Image

1 Object 5 Objects 10 Objects 25 Objects 50 Objects

Application Optimization

56

slide-57
SLIDE 57

Context-aware Application Optimization

57

slide-58
SLIDE 58

User Location Context

58

Geo-tagged AR Database Section 0

User Loc

Searching space (section 6)

slide-59
SLIDE 59

User Location Context

59

  • Use standard trilateration localization

Geo-tagged AR Database Section 0

User Loc

Searching space (section 6)

slide-60
SLIDE 60

Publishers as Landmarks

60

  • Use standard trilateration localization
  • Publishers act as landmarks
  • Use rxPower values from every service discovery message

Geo-tagged AR Database

Publishers (Landmarks)

Section 0

slide-61
SLIDE 61

Context-aware Application Optimization

61

AR Front-end

Mobile device

ACACIA device manager

CI Server on Edge Cloud

(Trilateration solver) LTE-direct Localization Manager Matcher Frames ( r x P

  • w

e r , L a n d m a r k n a m e )

(Discovery msg, rxPower)

User Context Data AR Data AR Back-end

slide-62
SLIDE 62

Context-aware Application Optimization

62

AR Front-end

Mobile device

ACACIA device manager

CI Server on Edge Cloud

(Trilateration solver) LTE-direct Localization Manager Matcher Frames ( r x P

  • w

e r , L a n d m a r k n a m e )

(Discovery msg, rxPower)

User Context Data AR Data AR Back-end

slide-63
SLIDE 63

Context-aware Application Optimization

63

AR Front-end

Mobile device

ACACIA device manager

CI Server on Edge Cloud

(Trilateration solver) LTE-direct Localization Manager Matcher Frames ( r x P

  • w

e r , L a n d m a r k n a m e )

(Discovery msg, rxPower)

User Context Data AR Data AR Back-end DB Get images for cell 6 Searching space (cell 6)

Landmarks

Cell 0

slide-64
SLIDE 64

Context-aware Application Optimization

64

AR Front-end

Mobile device

ACACIA device manager

CI Server on Edge Cloud

(Trilateration solver) LTE-direct Localization Manager Matcher Frames ( r x P

  • w

e r , L a n d m a r k n a m e )

(Discovery msg, rxPower)

User Context Data AR Data AR Back-end DB Get images for cell 6 Searching space (cell 6)

Landmarks

Cell 0

slide-65
SLIDE 65

Context-aware Application Optimization

65

AR Front-end

Mobile device

ACACIA device manager

CI Server on Edge Cloud

(Trilateration solver) LTE-direct Localization Manager Matcher Frames ( r x P

  • w

e r , L a n d m a r k n a m e )

(Discovery msg, rxPower)

User Context Data AR Data AR Back-end DB Get images for cell 6 Searching space (cell 6)

Landmarks

Cell 0

slide-66
SLIDE 66

66

Location Database pruning

?

slide-67
SLIDE 67

67

Service Interests Location Database pruning Mobile Edge Network

slide-68
SLIDE 68
  • Use OpenEPC for LTE core network components (MME, PCRF, PCEF)
  • ACACIA mobile edge network
  • Extend OpenEPC to support split LTE Gateways and QoS framework
  • Use Open vSwitch and Ryu SDN controller for Local LTE gateways
  • ACACIA Device Manager
  • Implement it as Android Service using Messenger class in android
  • AR-based Retail Application
  • Pub-Sub GUI application
  • Use OpenCV library (SURF) for object matching
  • Geo-tagged object database
  • Trilateration localization solver

ACACIA Implementation

68

slide-69
SLIDE 69

LTE IP.access (small cell) One+ One OpenEPC Core Network + GW-Us + MEC server

LTE Basestation OpenEPC Core Network GW-Us MEC MEC server One+ One

http://phantomnet.org/

ACACIA Evaluation

69

slide-70
SLIDE 70
  • Microbenchmark
  • ACACIA standard compliance
  • LTE GW performance
  • LTE-direct localization accuracy
  • Impact of network optimization
  • Impact of application optimization
  • End-to-end evaluation

ACACIA Evaluation Criteria

70

slide-71
SLIDE 71
  • Microbenchmark
  • ACACIA standard compliance
  • LTE GW performance
  • LTE-direct localization accuracy
  • Impact of network optimization
  • Impact of application optimization
  • End-to-end evaluation

ACACIA Evaluation Criteria

71

slide-72
SLIDE 72

Benchmark : AR application with geo-tagged AR DB ( 105 objects in 21 sections)

End-to-end Evaluation

0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9 Match Compute Network Total End-to-End Latency (sec)

ACACIA MEC CLOUD

72

slide-73
SLIDE 73

End-to-end Evaluation

0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9 Match Compute Network Total End-to-End Latency (sec)

ACACIA MEC CLOUD

73 Benchmark : AR application with geo-tagged AR DB ( 105 objects in 21 sections)

slide-74
SLIDE 74

End-to-end Evaluation

0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9 Match Compute Network Total End-to-End Latency (sec)

ACACIA MEC CLOUD

74 Benchmark : AR application with geo-tagged AR DB ( 105 objects in 21 sections)

slide-75
SLIDE 75

End-to-end Evaluation

0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9 Match Compute Network Total End-to-End Latency (sec)

ACACIA MEC CLOUD

ACACIA << MEC << CLOUD 75 Benchmark : AR application with geo-tagged AR DB ( 105 objects in 21 sections)

slide-76
SLIDE 76
  • Propose ACACIA - a service abstraction framework to enable CI apps
  • Give insights to design mobile edge computing and usecase of LTE-

direct on 5G network

  • Validate ACACIA design with smartphones, LTE base station and

Software-based EPC

https://wiki.phantomnet.org/wiki/phantomnet/acacia

Conclusion

76