Timely delivery of data streams is important to time-critical applications relying on streams of dynamic data. Drastic reduction on the sending rates of data streams typically has negative impact on the operations of such applications. Effective rate adaptation is needed to make data streams adapt to network congestion through slowly varying their sending rate. This research project is motivated by the need of streaming dynamic radar data at the required rates from radars to a control center in the surveillance application using ganged ground-based radars. This application is crucial to the operation of the unmanned aerial vehicles.
In this research project, an adaptive data pulling framework is studied to support stable data streaming. This framework consists of a transport-layer congestion control scheme and an application-layer data pulling control mechanism. The application-layer data pulling control mechanism allows the application actively fetch data from sources. The transport-layer congestion control scheme adopts a new rate control method which provides weighted fairness to data streams. Weighted fairness among data streams is the desired feature for controlling the sending rates of streams carrying layered encodings. Weighted fairness means that the throughput of a stream is degraded reversely proportional to its priority when the network becomes congested. Weighted fairness brings new vision on rate control for data streaming. Stability and responsiveness to congestion indications are the two key research questions of the new rate control scheme.
