Experimentation on low delay and stable congestion control for P2P video streaming

In recent years, a number of research efforts have focused on using peer-to-peer (P2P) systems in order to provide live streaming (LS) and Video-on-Demand (VoD) services. Most of them focused on the development of distributed P2P block schedulers for content exchange among the participating peers and on the architecture of the overlay graph (P2P overlay) that interconnects the set of these peers. Currently, the effort has shifted towards the combination of P2P systems with cloud infrastructures. By deploying monitoring and control architectures they use resources from the cloud in order to enhance the QoS, thus achieving an attractive trade-off between stability and low cost operation. However, there is a lack of research effort on the congestion control layer of these systems while the existing congestion control architectures in use are not suited for P2P traffic. This paper proposes a P2P congestion control protocol suitable for LS and VoD that: i) is capable to manage sequential traffic to multiple network destinations, ii) efficiently exploits the available bandwidth, iii) accurately measures the idle peers' resources, iv) it avoids network congestion, and v) is friendly to other TCP generated traffic. Our proposed algorithms and protocol have been implemented, tested and evaluated through a series of real experiments in the context of STEER [20].