Deployment of backup core switch in scalable distributed data center networks

摘要

Data Center Network (DCN) is the supporting platform for various applications in cloud services. As optical switch offers high bandwidth, low latency and reduced energy consumption, it becomes a promising switching solution for scalable DCN. Recently, a new DCN architecture with distributed component sets (racks and optical core switches) in a given optical network has been proposed to simplify the DCN internal connection and make the DCN fully scalable. Because the core switches play an important role in both external service access and inter-node traffic switching, a single core switch failure may lead to traffic congestion or collapse of a DCN. Based on an existing distributed DCN, in this paper we consider how to deploy a backup core switch to fight against an arbitrary single core switch failure while minimizing the total protection cost. Upon a core switch failure, all unaffected traffics keep their original routes unchanged, and predefined protection strategy (rerouting and switching) will take effect for the affected traffics. To solve this problem, we formulate an integer linear program (ILP) to place the backup core switch at a proper node and determine the fast traffic recovery mechanism. We validate the proposed design by extensive simulation studies.