Heterogeneous communication networks with their variety of application demands, uncertain time-varying traffic load, and mixture of wired and wireless links pose several challenging problem in modeling and control. In this paper we focus on the round-trip time (RTT), which is a particularly important variable for efficient end-to-end congestion control, and on bandwidth estimation. Based on a simple aggregated model of the network, an algorithm combining a Kalman filter and a change detection algorithm is proposed for RTT estimation. It is illustrated on real data that this algorithm provides estimates of significantly better accuracy as compared to the RTT estimator currently used in TCP, especially in scenarios where new cross-trafficflows cause bottle-neck queues to rapidly build up which in turn induces rapid changes of the RTT.

Standard techniques for bandwidth estimation is based on measurements of inter-arrival times of packets as the bandwidth is proportional to the inverse of the inter-arrival time. Two main classes of bandwidth estimators are analyzed wrt how variations in the inter-arrival times affect the estimates. It is shown that linear time-invariant filtering of instantaneous bandwidth estimates does not change the bias. In contrast to this, smoothing the inter-arrival-time samples, does give a bias reduction which depends on the smoothing filter. Hence, with such approach, noise attenuation can be traded against tracking ability wrt changes in the actual bandwidth.