Preemption algorithm with re-routing to minimize service disruption

Preemption policy is used to determine the combination of existing connections to be preempted in a heavily loaded network. Connections that are preempted will be torn down and may be re-routed after the preemption event. However, by tearing the preempted connections, end users will experience temporary service disruption. This will affect real-time applications such as streaming video and voice applications. If the preempted connections can be re-routed before being torn down, the end users will virtually unaware of the preemption process. Service disruption will be minimized. This paper will introduce the existing preemption algorithms and the modifications proposed in order to incorporate the re-routing capability. Simulation results show the ability of the proposed algorithm to reduce service disruption experienced by end users.