Multi-sourced data retrieval in groomed Elastic Optical Networks

Erasure coding has been widely adopted by data center networks, where the data is encoded and stored in multiple locations. Therefore, an efficient data retrieval service is needed to transfer encoded data from replicated stored nodes to a single destination. Elastic Optical Networks are a promising backbone technology for data center communication due to their capability to efficiently and flexibly allocate the huge optical bandwidth to heterogeneous traffic demands. Traffic grooming is a technique to increase the spectrum efficiency and transponder utilization of optical networks. In this paper, the traffic-grooming-enabled erasure-coded multi-sourced data retrieval routing and scheduling problem is studied for dynamic traffic in elastic optical networks. A novel heuristic is proposed. Numerical results indicate that traffic grooming decreases the blocking ratio by a factor of 3 and cost by 22% compared with a baseline algorithm.