基于资源区域聚集度的虚拟网映射算法

摘要

Virtual network embedding is a critical issue in network virtualization. To overcome the ignorance of network local topology information in existing literatures, a Virtual Network Embedding (VNE) algorithm based on regional Resource Clustering Index (RCI-VNE), is proposed. In embedding preprocessing stage, a node regional resource clustering index evaluation algorithm is proposed, which considers local topology information and resource aggregation extent. In node embedding stage, a 2-adjacent aggregation node embedding algorithm based on the regional resource clustering index is also proposed. The algorithm embeds virtual nodes intensively to the location of abundant resources in substrate network and decreases embedding cost. Simulation results show that the algorithm improves virtual network request acceptance ratio, long-time average revenue and benefit-cost ratio compared with the existing embedding algorithms.%虚拟网映射是网络虚拟化研究中亟待解决的问题，针对已有映射算法中存在的对于网络拓扑信息利用不足的现状，该文提出了基于资源区域聚集度的虚拟网映射算法(RCI-VNE)。在映射预处理阶段，根据局部拓扑信息和区域资源聚集度提出节点区域资源聚集评价算法。在节点映射阶段，提出一种基于节点区域资源聚集排名的2-近邻聚集映射算法，该算法将虚拟网节点集中映射到底层网络中可用资源丰富的区域，减小承载链路的长度。实验结果表明，该算法降低了虚拟网映射开销，且具有较高的虚拟网请求接受率和较低的平均执行时间。