As an effective mechanism acting on the intermediate nodes to support end-to-end congestion control, active queue management (AQM) takes a trade-off between link utilization and delay experienced by data packets. Most of the existing AQM algorithms are heuristic, and a lack systematic and theoretical design and analysis approach. From the viewpoint of control theory, it is rational to regard AQM as a typical regulating system. Although the PI controller for AQM outperforms the RED algorithm, the mismatches in the simplified TCP flow model inevitably degrade the performance of a controller designed with classical control theory. In this paper, a robust SMVS controller for AQM is put forward based on sliding mode variable structure control (SMVS), its superiority is insensitive to the noise and variance of the parameters, thus it very suitable to a time-varying network system. The principle and guidelines on design of a SMVS controller are presented in detail. The integrated performance is evaluated using ns simulations. The results show that SMVS is very responsive and robust against disturbances. At the same time, a complete comparison between the SMVS controller and PI controller is made. The conclusion is that both the transient and steady performance of the SMVS controller is superior to that of the PI controller, thus the SMVS controller is in favor of the achievement of AQM objectives.