Download Presentation

Loading in 3 Seconds

This presentation is the property of its rightful owner.

X

Sponsored Links

- 67 Views
- Uploaded on
- Presentation posted in: General

Scalable Group Communications and Systematic Group Modeling

Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author.While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server.

- - - - - - - - - - - - - - - - - - - - - - - - - - E N D - - - - - - - - - - - - - - - - - - - - - - - - - -

Scalable Group Communications and Systematic Group Modeling

Jun-Hong Cui

University of Connecticut

http://www.cse.uconn.edu/~jcui

Cool Application 2 : Telemedicine

Cool Application 3 : Net Gaming

- Multicast:
- One to many or many to many communications (group communications)

- To achieve multicast:
- Multiple unicast (one to one)
- Network multicast---IP multicast
- Overlay multicast (using proxies)
- Application layer multicast (end host)

- Scalable Group Communications
--- Aggregated Multicast

- Systematic Group Modeling
--- GEM Model

- Research Directions

group

NHop

g1

Ab, A3

Domain B

A2

B1

Domain A

Ab

Aa

A3

A1

Domain C

X1

Y1

C1

Domain X

Domain Y

D1

Customer Networks, Domain D

- Group: IP D class address
- Use Tree delivery structure
- Routers: keep forwarding entries per-group/source (multicast state)
- IP multicast
- Resource efficient
- Scalable to group size

group

NHop

Domain B

g1

Ab, A3

A2

B1

g2

Domain A

Ab, A3

Ab

Aa

A3

A1

X1

Domain C

Y1

C1

Domain X

Domain Y

D1

Customer Networks, Domain D

- More groups more trees
- More forwarding entries
- More tree maintenance overhead

- IP multicast NOT scalable to the number of groups
- State Scalability problem
- Serious in transit domains

- Our solution
- Aggregated multicast to improve state scalability

group

NHop

Domain B

g1

Ab, A3

A2

B1

g2

Domain A

Ab, A3

Ab

Aa

A3

A1

X1

Domain C

Y1

C1

Domain X

Domain Y

D1

Customer Networks, Domain D

- There are many overlaps among multicast trees in transit domains

Tree

NHop

Domain B

T1

Ab, A3

A2

B1

Domain A

Ab

Aa

A3

A1

X1

Domain C

Y1

C1

Domain X

Domain Y

D1

Customer Networks, Domain D

- Key idea:
- Force multiple groups share a single delivery tree (aggregated tree)

- Benefits:
- Reduce state at core routers
- Reduce tree maintenance overhead
- Push complexity to edge

- Target:
- Multicast provisioning in transit domains

Tree

NHop

Domain B

T1

Ab, A3

A2

B1

Domain A

De-aggregation

Ab

Aa

A3

De-aggregation

Aggregation

A1

X1

Domain C

Y1

C1

Domain X

Domain Y

D1

Customer Networks, Domain D

- Core routers:
- Keep state per-tree

- Edge routers:
- Keep group state

- Groups:
- Aggregate at incoming edge router
- De-aggregate at outgoing edge routers

Tree

NHop

Domain B

T1

Ab, A3

A2

B1

Domain A

Ab

DiscardPackets

Aa

A3

A1

X1

Domain C

Y1

C1

Domain X

Domain Y

D1

Customer Networks, Domain D

- Group-Tree match
- Perfect match
- Leaky match

- Bandwidth waste in leaky match
- Data delivery to non-member nodes

- Leaky match
- Good for tree aggregation
- But waste bandwidth

- There is a trade-off
- Static group-tree matching: NP hard
- A dynamic group-tree matching algorithm to control the trade-off
- Under a given bandwidth waste threshold

Domain B

Domain E

E1

A2

B1

Domain A

A4

Ab

Aa

A3

A1

X1

Domain C

Y1

C1

Domain X

Domain Y

D1

Customer Networks, Domain D

Domain B

Domain E

E1

A2

B1

Domain A

A4

Ab

Aa

A3

A1

X1

Domain C

Y1

C1

Domain X

Domain Y

D1

Customer Networks, Domain D

- Multiplex multiple groups over a shared tree
- IP encapsulation
- MPLS (Multi-Protocol Label Switching)

- Tree management and group-tree matching
- Tree Manager (need to know group membership)
- Distributed or centralized solutions

- Have designed and implemented protocols:
- ASSM for source specific multicast (SSM)
- BEAM for shared tree multicast (ASM)
- AQoSM for QoS multicast provisioning

- Overlay multicast
- Implement multicast in overlay net
- A collection of proxies (or gateways)

- Processing power, memory & bandwidth more critical
- Aggregated multicast reduces management overhead

- Implement multicast in overlay net
- Wireless multicast
- Implement multicast in wireless adhoc net
- No infrastructure, self-organized

- Energy, memory, bandwidth, resilience very critical
- Aggregated trees help to improve performance

- Implement multicast in wireless adhoc net

- Scalable Group Communications
--- Aggregated Multicast

- Systematic Group Modeling
--- GEM Model

- Research Directions

- The locations of the group members
- Given a graph, where should we place them?

- Current assumptions: uniform random model (unproven)
- All members uniformly distributed
- Not realistic for many applications

- Some studies have shown the locations of members have significant effects on
- Scaling properties of multicast trees
- Aggregatability of multicast state
- Performance of state reduction schemes

- Realistic group models
- Improve effectiveness of simulation
- Guide the design of protocols

- Measure real group membership properties
- MBONE (IETF/NASA) and Netgames (Quake)

- Design a model to generate realistic membership
- GEneralized Membership Model (GEM)
- Use Maximum Enthropy: a statistical method

- Membership Characteristics
- Measurement and Analysis Results
- Model Design and Validation

- How close are the members in a group?
- Are all the members same in group participation?
- What are the correlations between members in group participation?

Member Router

Edge Router

Seattle

0.7

Boston

0.5

Internet

1.0

Atlanta

0.4

Los Angeles

0.5

- Member clustering
- Capture proximity of group members
- Use network-aware clustering method

- Group participation probability
- Show difference among members/clusters

- Pairwise correlation in group participation
- Capture joint probability of two members/clusters
- Use correlation coefficient (normalized covariance)

- MBONE applications (from UCSB)
- IETF-43 (Audio and Video, Dec. 1998)
- NASA Shuttle Launch (Feb. 1999)
- Cumulative data sets on MBONE (1997-1999)

- Net Games (using QStat)
- Quake I (query master server)
- Choose 10 most popular servers (May. 2002)

- Examine three membership properties

MBONE cumulative data sets

(3, 0.64)

MBONE real data sets

Net game data sets

CDF of cluster size for MBONE and net games

CDF of participation probability for Net Game data sets

CDF of participation probability for MBONE applications

CDF of correlation coefficient for Net Game data sets

CDF of correlation coefficient for MBONE applications

Network topology

Cluster method

Group behavior

Distr. of participation prob.

Distr. of pairwise correlation

Distr. of member cluster size

Inputs

1. Create clusters in given topology

2. Select clusters as member clusters

According to input distributions

3. Choose nodes for each member clusters

GEM

Desired number of multicast groups

that follow the given distributions

Outputs

- Definition:
K clusters: C1 , C2 , … , Ci , … , CK

Prob. pi for any i in [1, K]

Joint prob. pi,jfor any i, j in [1, K]

X=(X1 ,X2 , … , Xi , … , Xk): Xiis a binary indicator

Xi = 1 if Ci is in the group

Xi = 0 if Ci is not in the group

- Objective:
Generate vectors x=(x1 , x2 , … , xk) satisfying

P(Xi = 1) = pi and P(Xi = 1 , Xj = 1) = pi,j

- To calculate the distribution of (X1,X2, …, Xk) requires O(2K) constraints
- But we only know O(K+K2) constraints
- We use Maximum Entropy Method
- Entropy is a measure of randomness
- We construct a maximum entropy distr. p*(x)
- Satisfy constraints in specified dimensions
- Keep as random as possible in unconstrained dimensions
- i.e. maximize entropy while match given constraints

Considering P(Xi=1)= pi and P(Xi=1, Xj=1)=pi,j

- Uniform distr. without correlation (easy)
pi,j = pi * pj , and pi = pj

- Non-uniform distr. without correlation (easy)
pi,j = pi * pj , but pi = pj not necessary

- Non-uniform distr. with pairwise correlation
Neither pi,j = pi * pjnor pi = pj necessary

Need to calculate the maximum entropy distr. p*(x)

Entropy decreases from case 1 to case 3

- Consider all membership properties
- Consider three cases
- Figures omitted …
- Our experiments show
- GEM can regenerate groups satisfying given distributions (from real measurement)

- Uniform random model
- Can capture net games approximately
- But not realistic for MBONE applications

- GEM: a generalized membership model
- Three cases (case 1: uniform random model)
- Realistic membership can be regenerated

- Beyond multicast
- Peer-to-peer network modeling

- Beyond wired network
- Wireless adhoc networks, sensor networks …

- Scalable Group Communications
--- Aggregated Multicast

- Systematic Group Modeling
--- GEM Model

- Research Directions

(from Jim Kurose)

Focus at the application level

- Applications
- P2P file sharing (Napster, Gnutella, Freenet, etc.)
- Application-layer multicast

- Characteristics
- each node potentially same responsibility, functionality
- logical connectivity rather than physical connectivity

- Why P2P?
- High resource utilization (bandwidth, memory, CPU)

- Challenges
- Self-organized and large scale (routing)
- Reliability and security

- Overlay multicast
- Scalability, QoS, security, pricing, …

- Multicast modeling
- Systematic multicast evaluation

- Peer-to-peer networks
- measurement & modeling, complex queries

- Wireless adhoc networks
- Mobility modeling, scalable multicast

- Sensor networks
- Sensor deployment and security
- Very large scale sensor network design

THANKS!!!

- No fixed infrastructure, instantly deployable
- Node portability, mobility
- Error-prone channel
- Limited resources
- bandwidth, energy supply, memory and CPU.

- Heterogeneous nodes
- big/small; fast/slow etc

- Heterogeneous traffic
- voice, image, video, data

- Wireless multihop connection
- to save power, overcome obstacles, enhance spatial spectrum reuse, etc

The maximum entropy distr. p*(x) is the solution for:

Subject to

and

and

Use lagrange multipliers and numerical method to construct p*(x), Then Gibbs Sampler to sample it

Participation probability distribution for IETF43-Video

Joint probability distribution for IETF43-Video