激光与光电子学进展, 2015, 52 (5): 050604, 网络出版: 2015-05-06  

面向云计算的光网络虚拟基础设施规划研究

Virtual Infrastructure Planning in Optical Networks for Cloud Computing
作者单位
中国人民解放军西安通信学院光纤通信实验室, 陕西 西安 710106
摘要
大数据云计算时代,联合光网络资源和数据中心资源的虚拟基础设施规划是解决光网络所面临挑战的最佳方法。建立了带波长转换能力和不带波长转换能力的两种虚拟基础设施规划的整数线性规划模型。采用动态业务请求,以最小联合能耗和最小网络资源使用率为目标函数,仿真比较了两种整数线性规划模型的能耗和阻塞率性能。结果表明,在轻负载情况下,最小联合能耗具有较低的能耗;在重负载情况下,最小网络资源使用率具有较低的能耗;而最小网络资源使用率始终具有较低的阻塞率。
Abstract
In the era of big data and cloud computing, the virtual infrastructure planning converged optical network resources and data center resources is the best way to solve the challenges facing optical networks. Two integer linear program models for virtual infrastructure planning are established with and without wavelength conversion capability. With dynamic service request, two objective functions of the two models: minimum joint power consumption and minimum network resource utilization rate, are simulated and compared with the power consumption and the blocking rate performance. The results show that, under light load conditions, the minimum joint power consumption has lower power consumption; under heavy loads, the minimum network resource utilization rate has lower power consumption; the minimum network resource utilization rate always has a lower blocking rate.

张引发, 李明, 任帅, 王鲸鱼, 王坤. 面向云计算的光网络虚拟基础设施规划研究[J]. 激光与光电子学进展, 2015, 52(5): 050604. Zhang Yinfa, Li Ming, Ren Shuai, Wang Jingyu, Wang Kun. Virtual Infrastructure Planning in Optical Networks for Cloud Computing[J]. Laser & Optoelectronics Progress, 2015, 52(5): 050604.

关于本站 Cookie 的使用提示

中国光学期刊网使用基于 cookie 的技术来更好地为您提供各项服务,点击此处了解我们的隐私策略。 如您需继续使用本网站,请您授权我们使用本地 cookie 来保存部分信息。
全站搜索
您最值得信赖的光电行业旗舰网络服务平台!