QoS-Aware Congestion Control with Online Learning

In emerging applications such as industrial control and autonomous driving, end-to-end determin-istic quality of service (QoS) transmission guarantee has become an urgent problem to be solved. Inter-net congestion control algorithms are essential to the performance of applications. However, existing con-gestion control schemes follow the best-effort prin-ciple of data transmission without the perception of application QoS requirements. To enable data de-livery within application QoS constraints, we lever-age an online learning mechanism to design Crimson, a novel congestion control algorithm in which each sender continuously observes the gap between cur-rent performance and pre-defined QoS. Crimson can change rates adaptively that satisfy application QoS requirements as a result. Across many emulation en-vironments and real-world experiments, our proposed scheme can efficiently balance the different trade-offs between throughput, delay and loss rate. Crimson also achieves consistent performance over a wide range of QoS constraints under diverse network scenarios.