Distributed Parallel VN Embedding Based on Genetic Algorithm

Abstract

Network virtualization has emerged to replace traditional network architecture since it allows multiple virtual networks to share a common substrate network. However, one of the main challenges for network virtualization is the resource allocation for each virtual network (VN), called Virtual Network Embedding Problem. The computation complexity of existing resource allocation approaches is too high to achieve an optimum within an acceptable time. Further, the provided optimum is not optimal in an online non-reconfigurable VN embedding setting because of the highly dynamic nature of user demands. Nowadays, due to lower hardware costs, distributed parallel computing can be used to deal with complex computing tasks with high efficiency. In this paper, we propose a distributed parallel Genetic Algorithm (GA) for solving VN Embedding problems. Through theoretical analysis, we compare the time saving of our distributed parallel algorithm with traditional sequential running. Results show that our algorithm achieves better performances on execution time and acceptance ratio.