ICN Dynamic Adaptive Streaming

Streaming of video content over the Internet, both to and from mobile devices, is experiencing an unprecedented growth, with emerging formats such as 4K and beyond. While video permeates every applications, is also puts tremendous pressure in the network — to support users having heterogeneous access with high quality of experience, in a furthermore cost-effective manner. It this context, Future Internet (FI) paradigms such as Information Centric Networks (ICN) are particularly well suited to not only enhance video delivery at the client (as in the current DASH approach), but to also naturally and seamlessy extend video support deeper in the network functions.

In this context, we are working to compare ICN and TCP/IP with an experimental approach, where we employ several state-of-the art DASH controllers (PANDA, AdapTech and BOLA) on an ICN vs a TCP/IP network stacks.  Our campaign, based on tools which we developed and that make available as open-source software, includes multiple videos (up to 4K resolution), channels (e.g., DASH profiles, emulated WiFi and LTE) and levels of integration with an ICN network (i.e., vanilla NDN; wireless loss detection and recovery at the acces point; load balancing).

In this page, you can find

  • The technical report  that clearly illustrate, as well as quantitatively assess, sizeable benefits of the ICN paradigm for video streaming, as well as warns about potential pitfalls that are however easy to avoid. A companion technical report describes instead the framework we used to instantiate the experiments and that we now released as vICN under the linux foundation project FD.io  
  • A readily available Linux Container (LXC) image equipped with open-source software and videos (that can act as either client or server)  for the performance evaluation of several state-of-the-art dynamic adaptive streaming strategies over TCP/IP and ICN.
  • The instructions to reproduce experiments in the technical report, based on these scripts  which greatly reduces the bootstrap time and to hopefully promote cross-comparison in the community.
  • To reduce the experimental bootstrap time even further, we plan to open part of our Testbed as a Service (TaaS), to the scientific community — in the meanwhile, if interested contact us by email !