Virtual infrastructure mapping in software-defined elastic optical networks

Software-defined networking (SDN) enables efficient and scalable network virtualization, which allows infrastructure resources such as computing and networking resources to be abstracted and outsourced as a service. The SDN technologies can be extended to the optical transport networks to achieve an intelligent and flexible resource management, thus achieving high-capacity, low-cost, and long-reach optical transport networks. In this paper, we introduce an architecture for software-defined elastic optical networks and study the virtual infrastructure (VI) mapping problem with the objective of minimizing the blocking probability. We propose a set of efficient heuristic algorithms, among which the Network followed by Compute Load Balancing (NCLB) algorithm is a novel attempt to solve the VI mapping problem by provisioning the networking resource first followed by allocating the computing resource. Furthermore, we propose a modified version of NCLB, called Network Depth-based NCLB (ND-NCLB), which confines the VI mapping assignment in a small-range sub-network to further optimize the physical network resource consumption. Through comprehensive simulations in various scenarios, we demonstrate that the proposed ND-NCLB algorithm achieves the best performance in terms of blocking probability compared to the other algorithms in this work.