Integrated Control in High-Speed Networks using constrained Model Predictive Control

This paper studies congestion control in high-speed communication networks using Model Predictive Control (MPC). Network traffic is assumed to consist of best-effort and priority traffic sources. An integrated controller consisting of two control parts is designed. The controller calculates the capacity for priority sources and the input rate of best-effort sources. MPC is desirable as it can take into account the constraints on the finite buffer and input rate, as well as deal very well with systems with time delays.