An Adaptive AQM Algorithm Based on a Novel Information Compression Model

Because the bufferbloat phenomenon has significantly degraded the quality of service of interactive applications, there is pressing need for effective active queue management (AQM) strategies to be deployed at both intermediate devices and consumer edges. Existing models and AQM design methods usually lack sufficient consideration of heterogenous round-trip times, uncertain endpoint mechanisms, and time-varying network conditions. This paper proposes an innovative information compression model purely from routers’ perspective by evaluating the average effect an accepted/dropped packet has on the aggregated packet arriving rate. The proposed model is independent of round-trip time heterogeneity and specific endpoint protocols. A customized parameter identification algorithm and corresponding control strategy are developed to scale the regulating sensitivity of dropping probability adaptively. Simulation results demonstrate the performance improvements of the proposed algorithm in providing a good tradeoff between reducing the latency and maximizing the goodput, especially in large delay environments.