A TCP-friendly congestion control scheme for real-time packet video using prediction

In order to cope with time-varying conditions in networks with no or limited QoS support like the current Internet, schemes have been proposed for real-time applications to dynamically adjust the traffic source's transmission rate. However, employing adaptive rate control may not be sufficient to prevent or handle network congestion. As most of the real-time applications are based on RTP/UDP protocols, an issue of possibly unfair sharing of bandwidth between TCP and UDP applications has been raised. In this paper, we propose a scheme called R/sup 3/CP/sup +/ that integrates several control mechanisms to maximize the delivery performance of real-time continuous media over networks without QoS support. Simulation results show that recursive least square (RLS)-based prediction makes a good use of the past measurement in forecasting the future condition that can effectively avoid and cope with network congestion. It also shows that the scheme achieves reasonably friendly resource sharing with TCP connections.