Real-time feedback control of computer networks based on predicted state estimation

We present a real-time feedback control strategy to optimize the dynamic performance of a computer communication network. In previous studies closely related to this topic, feedback delay, arising from communication delay, was shown to degrade system performance. Considering this negative impact of delay, we propose a new control law which predicts the traffic in advance and exercises control based on the predicted traffic. We demonstrate through simulation experiments that the predictive feedback control law substantially improves the system performance.