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 traffic sources' data sending 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 an application-level control protocol called Real-time Rate and Retransmission Control Protocol Plus in which several control mechanisms are used and integrated to maximize the delivery performance of UDP-based real-time continuous media over the Internet while friendly sharing network bandwidth with TCP connections. Here we propose to use adaptive filters in network state characterization and inference. Both simulation and actual implementation performance results show that recursive least square-based adaptive prediction makes good use of past measurement in forecasting future condition and effectively avoids network congestion. It also shows that the scheme achieves reasonably friendly resource sharing with TCP connections.

Author Keywords: Flow/congestion control; End-to-end real-time video; Prediction; TCP-friendly

Article Outline

1. Introduction

2. Characterization and recursive prediction of network state

2.1. Prediction of packet loss probability

2.2. Prediction of round-trip time for the flow control period

3. Adaptive flow control—take receiving buffer as a reserve bank

3.1. Receiver's desired sending rate and target queue length

3.1.1. Target queue length

3.1.2. Virtual queue length

3.2. Requested sending rate—storing extra data during unloaded state and avoiding congestion otherwise

4. Performance evaluation

4.1. Playback performance

4.2. Responsiveness and stability

4.3. Fairness with real-time sessions

4.4. Fairness with TCP traffic

4.5. Internet experiment results

5. Conclusions

References

¹ Tel.: +886-2236-35251x554; fax: +886-2236-38247.

² Tel.: +886-2278-83799x1802; fax: +886-2278-24814.

Corresponding author. Tel.: +886-2236-30231; fax: +886-2362-1327; email: sunny@im.ntu.edu.tw