Presentation is loading. Please wait.

Presentation is loading. Please wait.

Predictive End-to-End Reservations via A Hierarchical Clearing House Endeavour Retreat June 19-21, 2000 Chen-Nee Chuah (Advisor: Professor Randy H. Katz)

Similar presentations


Presentation on theme: "Predictive End-to-End Reservations via A Hierarchical Clearing House Endeavour Retreat June 19-21, 2000 Chen-Nee Chuah (Advisor: Professor Randy H. Katz)"— Presentation transcript:

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  How to deliver end-to-end QoS for real-time applications over IP-networks? Video conferencing, Distance learning Web surfing, emails, TCP connections Internet PSTN VoIP (e.g. Netmeeting) H.323 Gateway GSM Wireless Phones

3 Why Is It Hard?  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? ISP1 ISP 3 ISP2 H3 ?? SLA H1

4 Example Workload: Real-Time Packet Audio  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 doesn’t work!  Application Specific Traffic Patterns

5 Proposed Solution: Predictive Reservations H1 H2 LCH Edge Router  Online measurement of aggregate traffic statistics  Advance reservations based on local Gaussian predictor –R A = m + Q -1 (p loss ).   Allow local admission control Advance Reservation Dynamic Reservation

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  Introduce logical hierarchy  Distributed database –CH-nodes maintain reservation status, link utilization, network performance source ISP1 ISP n destination Edge Router LCH CH 2 ISP2 CH 1

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 < 1% without extensive over-provisioning

10 Future Work: Simulation Study  vBNS backbone network topology (1999) Houston Seattle SF LA Orlando Atlanta DC NY Denver St. Louise Chicago Boston !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


Download ppt "Predictive End-to-End Reservations via A Hierarchical Clearing House Endeavour Retreat June 19-21, 2000 Chen-Nee Chuah (Advisor: Professor Randy H. Katz)"

Similar presentations


Ads by Google