Skip to content

Instantly share code, notes, and snippets.

@hasantahir
Last active September 13, 2022 11:55
Show Gist options
  • Save hasantahir/0eeca96c4b0c3f04eeb2a7d348cbcfcd to your computer and use it in GitHub Desktop.
Save hasantahir/0eeca96c4b0c3f04eeb2a7d348cbcfcd to your computer and use it in GitHub Desktop.
P4 - Mindmap

Abstract - Programming protocol-independent packet processors

Keywords

  • Software Defined networking
  • network function virtualisation
  • 5G networks
  • data plane programmability
  • Lower latency
  • Edge computing
  • Backhaul network

Motivation

  • Complex tasks can be performed at the network switch level (data link layer)
  • A truly distributed architecture
  • p4 is going to reduce the congestion caused at the network layer by moving some of the operations and tasks to the link layer
  • Network customisation as a result of software defined radio. As a result we get flexibility; ideal for 5G networks

Use cases

  • Most of the applications are lying in the security aspects of the 5G network
  • Work is done to improve the reliability as well as the latency of the the backhaul networks
  • Edge computing

Beamforming

  • Beamforming requires training of the network that determines the best beams within a channel. There are various algorithms such as binary search beam training over a beamforming codebook.
  • Typically this pre configuration is done at the MAC sublayer (part of the link layer) (layer 2 - OSI model). MAC protocols provide control to the physical devices such as antennas etc.
  • Currently the focus is on making the whole point to point communication effective rather than looking at elemental level such as the link or network layer.
  • What P4 can do is provide a novel way in which data traffic can be directed at the network layer rather than the MAC or physical layer.
  • This can help develop a unique edge-cloud or fog network architecture
  • Provision of network services through which a user can avail personalised services
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment