Multi-stratum resource integration for OpenFlow-based data center interconnect [invited]

Nowadays, most service providers offer their services and support their applications through federated sets of data centers that need to be interconnected using high-capacity telecom transport networks. To provide such high-capacity network channels, data center interconnection is typically based on IP and optical transport networks that ensure certain end-to-end connectivity performance guarantees. However, in the current mode of operation, the control of IP networks, optical networks, and data centers is separately deployed. Enabling even a limited interworking among these separated control systems requires the adoption of complex and inelastic interfaces among the various networks, and this solution is not efficient enough to provide the required quality of service. In this paper, we propose a multi-stratum resource integration (MSRI) architecture for OpenFlow-based data center interconnection using IP and optical transport networks. The control of the architecture is implemented through multiple OpenFlow controllers' cooperation. By exchanging information among multiple controllers, the MSRI can effectively overcome the interworking limitations of a multi-stratum architecture, enable joint optimization of data center and network resources, and enhance the data center responsiveness to end-to-end service demands. Additionally, a service-aware flow estimation strategy for MSRI is introduced based on the proposed architecture. The overall feasibility and efficiency of the proposed architecture are experimentally demonstrated on our optical as a service testbed in terms of blocking probability, resource occupation rate, and path provisioning latency.