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

Abstract

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 RTPKJDP 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 R3Cp+ 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.

Continuous one-way available bandwidth change detection in high definition video conferencing

“…For example, equation (1) is extended to multicast applications in [12]. In [13], a prediction method is developed based on packet loss probability and is shown to be TCP-friendly. This method also uses RTT predictions.…”

“…When the i th packet arrives ( ), the difference is determined as shown in formula (12). (12) where (13) After determining the value of , we can detect network congestion easily. A sharp decline in the value of indicates a decrease in the available bandwidth and, analogously, a rise in shows an increase.…”

Joint Source-Channel Video Transmission

“…One way to perform effective congestion-control is to assume an accurate underlying model for network traffic. Network modeling is an active research field: besides the conventional Poisson model and multistate Markov chain (MSMC) model [59], there are also the wavelet multifractal model [60], a mathematical model based on partial differential equations [61], a traffic model based on M -step Kalman filter [62], and many others.…”

End-to-end QoS management for multimedia over IP

“…In [16], some design options for specifying AIMD adaptation were proposed to perform dynamic additive increase and decrease. Application level QoS on TCP-friendly video transferring was considered in [21], and the congestion control for real-time packet video using prediction was adopted in [23]. Although these schemes have their specific points, they all take into account the effects of packet loss on the bandwidth, which is usually calculated by [27]:…”