Discrete-Time Sliding Mode Learning Based Congestion Control for Connection-Oriented Communication Networks

In this paper, a sliding mode learning controller is developed for connection-oriented communication networks. Firstly, a networking system is modelled as discrete-time nth-order dynamic system subject to time-varying delay, the congestion control problem in communication networks is then addressed by adopting a novel sliding mode learning controller. The proposed learning controller not only suppresses the drawbacks of conventional sliding mode control, but also guarantees the stability of the closed-loop system with strong robustness against uncertainties. The paper offers the plausible application and great potential of discrete-time sliding mode learning controller in communication networks.