Realization of congestion-aware energy-aware virtual link embedding

Abstract

Network virtualization is an inherent component of future internets. Network resources are virtualized and provisioned to users on demand. The virtual network embedding entails two processes: node mapping and link mapping. However, efficient and practical solutions to the link mapping problem in software-defined networks (SDN) and data centers are still lacking. This paper proposes a solution to the link mapping (LiM) process that can dynamically interact with the routing protocols of the substrate network to allocate virtual link requests to the underlying substrate links, satisfies optimizing cost, minimizing energy consumption, and avoiding congestion (CEVNE) concurrently. CEVNE LiM is realized as a composite application on top of the SDN controller running the Segment Routing (SR) application. The performance of the CEVNE LiM algorithm is compared with the k-shortest path link mapping algorithm and shows its superior performance in terms of the overall runtime, the average path length, the average node stress, the average link stress, and the overall energy consumption.