Minimally Intrusive Server Policies for Background Data Transfers

We consider the problem of designing access control protocols for servers distributing background data, such as software and database updates, so that they cause the least possible disruption to flows carrying delay-sensitive data. Using a Markov decision process formulation we obtain the optimal policy analytically, which is not easy to implement in practice. A mean-field argument is employed to show that another policy, which is easier to implement and is based on water-filling, converges to the optimal as the number of bottleneck links increases. Using simulations we compare the performance of this policy with the standard case where no control is exercised by the server.