R02 ACS MPhil - Network Architectures
Third Essay (Set Nov 28, due Jan 16)

Scalability

This essay is about scalability of network architectures. 
The two papers I'd like you to write about are at two different levels, one very much at the performance modelling level, and
the other concerned with the protocol details.

First, outline the key contributions from each paper, and try to set a bit of context for the work.
Then critique the work, especially with regards the plausibility of any model or evaluation. Finally,
what do you see as the pro and con arguments for the proposals in each paper, and are there visible
complementarities?

Models for a self-managed Internet-  SMI 
http://www.statslab.cam.ac.uk/~frank/PAPERS/smi.pdf

Re-architecting datacenter networks and stacks for low latency and high performance
NDP (sigcomm 2017)
https://dl.acm.org/citation.cfm?id=3098825
or
http://www.cl.cam.ac.uk/teaching/2324/R02/papers/p29-Handley.pdf

Two possible useful background papers (to get you to the SMI paper):
Fluid-based Analysis of a Network of AQM Routers Supporting TCP Flows with an Application to RED 
https://www.cl.cam.ac.uk/teaching/2223/R02/papers/347057.347421.pdf

Analysis of DCTCP: Stability, Convergence, and Fairness, 
https://www.cl.cam.ac.uk/teaching/2223/R02/papers/11analysisof.pdf

Again, the essay can be in the form of notes, if you prefer that to long sentences/parageraphs.
tables/diagrams welcome, extracts from the papers are fine if attributed, and cite any other relevant work you read
while carrying out this assignment.