Re-Provisioning of Advance Reservation Applications in Elastic Optical Networks

Driven by the development of cloud computing and mobile Internet, network-based applications have become diverse. Besides the usual immediate reservation (IR) applications, which need to be served immediately, advance reservation (AR) applications have been introduced to support initial-delay-tolerance services, such as grid computing, virtual machine backup, and so on. The provisioning mechanism of AR applications is different from that of IR applications, because AR requests don't require to be served immediately, and the network operator must decide the exact serving time in the AR service provisioning process. Based on the scheduling features of AR requests, this paper formulates a resource model and sets up a control framework for elastic optical networks to support AR services. We propose an optimization algorithm with three reprovisioning policies to dynamically reprovision the AR applications, which have already been scheduled. Both the proposed control framework and algorithm are developed on the basis of an open network operating system, which is an open-source software-defined networking controller. Also, the performance of the proposed algorithm is evaluated via software simulation. Demonstration results show the benefits of reprovisioning, and simulation results show that the reprovisioning optimization algorithm can improve the efficiency of network spectrum resource.