Liu Yunjie

Virtual network embedding through node connectivity

Abstract Virtual network embedding (VNE) is an essential part of network virtualization, which is considered as one of the most promising way for the future network. Its main object is to efficiently assign the nodes and links of a virtual network (VN) to a shared substrate network (SN). The NP-hard and exiting studies have put forward several heuristic algorithms. However, most of the algorithms only consider the local resource of nodes, such as CPU and bandwidth (BW), to decide the embedding, and ignore the significant impact of network attributes. Based on the attributes of entire network, a model of the connectivity between each pair of nodes was formulated to measure the resource ranking of the nodes, and a new two-stage embedding algorithm was proposed. Thereafter, the node mapping and link mapping can be jointly considered. Extensive simulation shows that the proposed algorithm improves the performance of VNE by increasing the revenue/cost ratio and acceptance ratio of VN requests while reducing the runtime.

Resource scheduling virtualization in service-oriented future Internet architecture

Abstract Service-oriented future internet architecture (SOFIA) is a clean-slate network architecture. In SOFIA, a service request is mainly processed through service resolution and network resource allocation. To realize the network resource allocation, we reference the idea of network virtualization and propose resource scheduling virtualization. In resource scheduling virtualization, a service request is abstracted as a virtual network (VN) and the network resources are allocated by mapping the VN onto the physical network. Resource scheduling virtualization provides centralized resource scheduling control within an autonomous system (AS) and achieves better controllability compared with the distributed schemes. Besides, resource scheduling virtualization supports multi-site selection as well. Meanwhile, we propose a collection of resource scheduling algorithms based on maximum resource tree (MRT) adapting to different scenarios. According to the simulation results, the proposed algorithms show good performance on the key metrics, such as acceptance ratio, revenue, cost and utilization. Moreover, the simulation results reveal that our algorithm is more efficient than the traditional ones.