1 / 13

Mesh Distributed Service

Mesh Distributed Service. Chandra, Erwin, Ginchereau, Ion, Kurose, Padmanabhan, Shenker, Zill. Usage Scenarios We Could Agree On. Last mile connectivity Inter-AP home networks . Challenges. Manageability Addressing & Naming QoS. #1 Manageability . Manageability very hard

ryder
Download Presentation

Mesh Distributed Service

An Image/Link below is provided (as is) to download presentation 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. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Mesh Distributed Service Chandra, Erwin, Ginchereau, Ion, Kurose, Padmanabhan, Shenker, Zill

  2. Usage Scenarios We Could Agree On • Last mile connectivity • Inter-AP home networks

  3. Challenges • Manageability • Addressing & Naming • QoS

  4. #1 Manageability • Manageability very hard • What if fixing your network requires to go to your neighbor’s house? • Manageability cost should be low enough to make MESH competitive to Cable modems/DSL • Compared to Cable modem/DSL • Better redundancy; multiple paths • Interference; other external interactions

  5. #2 Addressing & Naming • Requirements • Global reachability • Simultaneous and transparent connectivity to nodes in the community network and the Internet • Ability to switch between MESH networks (without breaking on-going connections?)

  6. #2 Addressing & Naming • How to allocate addresses in a community MESH network? • Distributed DHCP, IPv6 • Need global naming or identifier space • Is this going to be DNS or something else? • Who runs the naming services? • Peer-to-peer solution?

  7. #2 Addressing & Naming • How fast should you be able to switch to another MESH network? • Name-based routing or Mobile IP vs. name resolution and IP routing

  8. #3 “QoS” • Need to make a distinction between Internet connectivity and community networking • Last mile: you’ll compete to cable and DSL • Intra-community applications: users can have much higher requirements • What kind of applications we want to support not clear though • Disconnect between infrastructure research (e.g., connectivity and throughput), and some application scenarios (e.g., latency)

  9. #3 “QoS” • Compared to the Internet • Smaller network; can have information about the entire network • System non-linear, less controlable, open to external interferences

  10. #3 “QoS” • During this retreat only connectivity and throughput were emphasized • What about delay? • E.g., video gaming • Throughput can make QoS worse • Rate negotiation becomes worse (long latency) • Huge dynamic range may cause connections to drop

  11. #3 “QoS” • What kind of QoS do we need? • Avoid high variability in service • Fairness; what is the fairness model? • Maybe something as good as best-effort Internet will be good enough! • Improving QoS • QoS-based routing, different QoS metrics • Routing metrics needs to look at more realistic scenarios • Improving MAC, e.g., TDMA?

  12. Benchmark • Cannot differentiate between DSL and a MESH network connectivity

  13. Predictions • Deployment in development countries • Wireless to remote places • Inter AP MESH networking will be standardized and widely used • Manageability will be the hard problem

More Related