摘要
【目的】随着云计算平台越来越庞大并且呈现出动态化特点,对如何满足多个用户的计算请求而进行有效资源分配,同时保障整个网络的性能进行探索。【方法】首先,提出一种集群虚拟网络(CVN)策略和动态堆排序算法。其次,将联合多个pod构建跨pod集群虚拟网络(CP-CVN),同时保障网络的性能。进而将此网络优化问题公式化为线性规划问题(LP),并提出一种近似对偶算法解决此线性规划问题。【结果】理论分析表明所提出的对偶算法是可行的,实验结果验证对偶算法解决了软件定义网络中的资源分配问题,同时保障网络性能。【结论】理论和实验分析表明所提出的对偶算法是可行的。
[Purposes]As cloud computing becomes more and more massive and dynamic,it is a great challenge to effectively allocate resource for different tenants＇ computing requests while considering the performance of the whole network.[Methods]To address this problem,they propose a clustered virtual network（CVN）abstraction strategy and a dynamical heapsort algorithm.Subsequently,they construct a crossing pod CVN（CP-CVN）and guarantee network performance.Furthermore,they formulate the network optimization problem as a Linear Programming（LP）problem.To achieve computation feasibility in massive data center networks,they propose an approximation primal-dual algorithm for solving this LP problem.[Findings]Theoretical analysis shows that the proposed primal-dual algorithm is feasible and the experiment results verify that the algorithm is suitable for solving massive computation problem in SDNs.[Conclusions]Theoretical and experimental analysis shows that the proposed primal-dual algorithm is feasible and suitable.
作者
李波
郭松涛
LI Bo GUO Songtao(College of Electronic and Information Engineering, Southwest University, Chongqing 400715, China)
出处
《重庆师范大学学报（自然科学版）》
CAS
CSCD
北大核心
2017年第5期87-93,共7页
Journal of Chongqing Normal University:Natural Science
基金
国家自然科学基金(No.61373179)
关键词
软件定义网络
虚拟网络
网络性能
software defined networking
virtual network
network performance
