Skip to content
This repository has been archived by the owner on Apr 16, 2020. It is now read-only.

Relevant Paper: Adaptive Peer Selection (BFLZ) #2

Open
kbala444 opened this issue Jun 5, 2015 · 1 comment
Open

Relevant Paper: Adaptive Peer Selection (BFLZ) #2

kbala444 opened this issue Jun 5, 2015 · 1 comment

Comments

@kbala444
Copy link
Contributor

kbala444 commented Jun 5, 2015

http://iptps03.cs.berkeley.edu/final-papers/adaptive_selection.pdf

This paper seems to solve a similar problem as bitswap-ml, but in the context of the Gnutella network.

The features they used were:

  • "an indication of whether all of the peer’s upload slots were currently full (busy flag)"
  • "an indication of whether the peer had successfully uploaded at least one file (uploaded flag)"
  • "an indication of whether the peer was firewalled (firewall flag)"
  • "a number representing the connection speed (speed field)"
  • "an indication of whether the speed field was measured or set by the user (measured flag)"

Using these attributes they created a decision tree to rank peers on a discrete scale from "Very Likely Slow" to "Very Likely Fast". They also found that having the busy flag set was highly correlated with poor connections, so they gave busy peers their own rating, "B", which is a rank lower than Very Likely Slow, and did not include it in the decision tree. Some interesting results they found when creating the tree were:

  • Firewalled hosts were often faster for some unknown reason
  • The upload flag and speed field were the most relevant features

Once potential peers were ranked using the decision tree, the researchers used a Markov decision process to intelligently perform partial downloads to find the best peers in minimal time.

@jbenet
Copy link
Contributor

jbenet commented Jun 5, 2015

I'll try to read this in next couple of days. but skimming it, this isn't a good paper. they collected very little data and tried very few things. compare to, for example, papers like these

i wouldn't adopt any of their conclusions, but definitely interesting to see how they modeled the problem.

Firewalled hosts were often faster for some unknown reason

probably because they were nodes likely to be in corporate or university networks, with fast connections :)

@jbenet jbenet changed the title Relevant Paper Relevant Paper: Adaptive Peer Selection (BFLZ) Jun 5, 2015
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants