Predictive%20End-to-End%20Reservations%20via%20A%20Hierarchical%20Clearing%20House

1
Predictive End-to-End Reservations via A
Hierarchical Clearing House

• Endeavour Retreat
• June 19-21, 2000
• Chen-Nee Chuah (Advisor Professor Randy H.
  Katz)
• EECS Department, U. C. Berkeley

2
Problem Statement
H.323 Gateway
PSTN
Web surfing, emails,TCP connections
Internet
GSM
VoIP (e.g. Netmeeting)
Wireless Phones
Video conferencing,Distance learning

• How to deliver end-to-end QoS for real-time
  applications over IP-networks?

3
Why Is It Hard?
SLA
H1
H3
ISP2
SLA
ISP 3

• Lack of QoS assurance in current IP-networks
• SLAs are not precise
• Scalability issues
• Limited understanding on control/policy framework
• How to regulate resource provisioning across
  multiple domains?

4
Example Workload Real-Time Packet Audio

• Application Specific Traffic Patterns

• Wide range of audio intensive applications
• Multicast lecture, video conferencing, etc.
• Significantly different from 2-way conversations
• Traffic characteristics too diverse, cannot be
  described by one model
• Resource pre-partitioning doesnt work!

5
Proposed Solution Predictive Reservations

• Online measurement of aggregate traffic
  statistics
• Advance reservations based on local Gaussian
  predictor
• RA m Q-1(ploss).s
• Allow local admission control

H1
H2
Edge Router
LCH
Edge Router
6
Predictor Characteristics

• 1-min predictor - 0.4 Loss - 7
  Over-Prov.
• 10-min predictor - 0.7 Loss - 33
  Over-Prov.
• More BW for BE traffic than
  pre-partitioning - avg. 286 Kbps - max 857.2
  Kbps

7
Reservations Across Multiple Domains via A
Clearing House Architecture
destination
source
Edge Router
ISP n
ISP2
ISP1

• Introduce logical hierarchy
• Distributed database
• CH-nodes maintain reservation status, link
  utilization, network performance

8
Clearing House Approach

• Delivers statistical QoS
• Aggregate reservation requests
• Coordinates aggregate reservations across
  multiple domains
• Performs coarse-grained admission control in a
  hierarchical manner
• Assumptions
• Networks can support differentiated service
  levels
• Traffic and network statistics are easily
  available
• Independent monitoring system or ISPs
• Control and data paths are separate

9
Advantages

• Maintain scalability by aggregating requests
• Core routers only maintain coarse-grained network
  state information
• Provide statistical end-to end QoS
• Advance reservations admission control
• Reduce setup time
• Advance reservations allow fast admission control
  decisions
• Optimize resource utilization
• Predictive reservations achieve loss rate lt 1
  without extensive over-provisioning

10
Future Work Simulation Study

• vBNS backbone network topology (1999)

• Traffic matrix weighted by population
• Three-level Clearing House architecture- one top
  CH-node- one CH-node per city- local hierarchy
  of LCHs

• Workload models two QoS classes
• High priority packet audio
• 25 traces (conference telephone calls), 0.5 -
  113 minutes
• Best-effort data traffic