Stochastic regulation of queues in data networks

A new class of routing policies for the regulation of queue lengths at all nodes throughout a data network in the presence of congestion caused by heavy input traffic is developed. Regulation is achieved via a feedback algorithm which minimizes, over each successive control interval, the mean-square queueing error where the latter is the difference between the actual queueing vector and its desired nominal value. Implementation of the algorithm requires knowledge of the mean and covariance of the input traffic and of the queue length measurement error stochastic processes. In the case of the former process, on-line measurements can be used to calculate the required statistical parameters. For the latter process, a priori knowledge that reflects the uncertainty in measuring and transmitting queue lengths throughout the network is needed.