Software Defined Data Center Research Articles

Global Resources Integrated Resilience for Software Defined Data Center Interconnection Based on IP Over Elastic Optical Network

We propose a novel global resources integrated resilience (GRIR) algorithm for a software defined data center interconnection architecture based on IP over elastic optical network (EON). The proposed algorithm provides resilience using the multiple stratums resources and enhances the data center service resilience responsiveness to the dynamic end-to-end recovery demands in case of the converged optical node failure. Our simulation results indicate that GRIR achieves significant improvements in terms of path blocking probability, resilience latency and resource occupation rate, compared with other resilience algorithms.

Service-aware resources integrated resilience for software defined data center networking based on IP over Flexi-Grid optical networks

Due to the performance guarantee of low delay, huge bandwidth and high reliability at a low cost, IP over Flexi-Grid optical network is a very promising networking architecture applied to the interconnection of geographically distributed data centers. It can enable efficient resource utilization and support heterogeneous bandwidth demands in cost-effective, highly-available and energy-effective manner. In case of edge Flexi-Grid optical network node failure, to ensure a high-level quality of service (QoS) for user request after the failure becomes a research focus. In this paper, we propose a novel service-aware resources integrated resilience (SA-RIR) scheme for data center services in software defined data center networking architecture based on IP over Flexi-Grid optical networks. Different from previous works which restore the services just exploiting the optical stratum, the proposed scheme provides the resilience using the multiple stratums resources in case of the edge optical node failure. We quantitatively evaluate the feasibility and performances through the simulation under heavy traffic load scenario in terms of path blocking probability, path resilience latency and resource occupation rate with different failure rates. Simulation results show that, the SA-RIR scheme can enable joint optimization of IP network, Flexi-Grid optical network and data center application stratum resources, and enhance the data center service resilience responsiveness to the dynamic end-to-end demands.

Multi-stratum resources resilience in software defined data center interconnection based on IP over elastic optical networks

IP over elastic optical network is a very promising networking architecture to interconnect data centers. It can enable efficient resource utilization and support heterogeneous bandwidth demands in cost-effective, highly available, and energy-effective manner. In case of aggregation elastic optical network node failure, to ensure a high-level quality of service for user request after the failure becomes a research focus. In this paper, we present a novel multi-stratum resources resilience (MSRR) architecture for the data center services in software defined data center interconnection based on IP over elastic optical networks. The MSRR can enable joint optimization of IP network, elastic optical network, and application stratum resources, and enhance the service resilience and the data center responsiveness to the dynamic end-to-end service demands. Additionally, a service-aware resource collaborative resilience strategy for MSRR is introduced based on the proposed architecture, which can provide the restoration using the multiple stratums resources in case of failure. The overall feasibility and efficiency of the proposed architecture are experimentally verified on our testbed. Moreover, the network performances are quantitatively evaluated through the simulation under heavy traffic load scenario in terms of path blocking probability, resource occupation rate, and path resilience latency.

A Unified Unicast and Multicast Routing and Forwarding Algorithm for Software-Defined Datacenter Networks

In this article, we consider a scalability problem associated with software-defined datacenter, of which the unicast/multicast routing states is proven to be NP-complete. We introduce an efficient multiple membership query algorithm, called Scalar-pair Vectors Routing and Forwarding (SVRF), based on the prime theory such as Chinese Remainder Theorem (CRT). Our proposed algorithm simply calculates corresponding output ports of each multicast group by dividing a common scalar-pair with a group-specific key, within pseudo-polynomial time. The result is then used to make a forwarding decision within few cycles through a hardware accelerator. Compared to Bloom filter, our algorithm can achieve remarkable performance in terms of memory consumption, processing time, hardware cost, and 100% delivery accuracy, while applying for a large number of large-scale distinct flows (including unicast and multicast) in a large-scale datacenter networks. Our work may be applied to various research areas of computer science and networking.