数据中心网络中相关感知流量整合算法

随着大数据、云计算不断融入人们的日常生活，作为支撑其发展的基础设施--数据中心网络的能耗也在急剧增长。为了解决这个问题，学术界提出了能量感知路由（Energy-Aware Routing，EAR）。EAR的主要思想是通过将流量需求聚集在网络链路的子集，并睡眠未使用的网络设备以节省能量。但是在流量低谷时期频繁地切换网络设备模式可能会导致网络振荡甚至网络性能下降。因此提出了一种相关感知流量整合（Correlation-Aware Traffic Consolidation，CATC）算法。提出了基于软件定义网络（Software Defined Network，SDN）的CATC模型，即在流量整合时考虑了流之间的相关性，并结合链路速率来实现更高的节能。在流量约束和链路容量约束下将CATC模型转换为一个最优流量分配问题，并提出CATC算法来求解。仿真结果显示，与现有的节能算法相比，CATC算法在仅仅增加极少网络延迟的同时可以为数据中心网络节省大约45%的能量。

Correlation-Aware Traffic Consolidation Algorithm in Data Center Networks

With big data and cloud computing continue to integrate into people’s daily lives, the energy consumption of data center networks, which are the infrastructure that underpins their development, is also rapidly increasing. To solve this problem, Energy-Aware Routing（EAR） is proposed. The main idea of EAR is that traffic demand are gathered over a subset of the network links, sleeping unused network equipment to save energy. However, during traffic peak time, network device patterns are switched frequently, which can cause network oscillation and performance degradation. Therefore, this paper proposes a Correlation-Aware Traffic Consolidation（CATC） algorithm in data center network. This paper proposes CATC model based on Software Defined Network（SDN）, which considers the correlation between traffics during traffic consolidation and the adaptive link rate to save more energy. The CATC problem is formulated as an optimal traffic allocation problem subject to flow conservation constraint and link capacity constraint. Furthermore, the optimization problem is solved by the CATC algorithm. The simulation result shows, the CATC algorithm not only saves energy upto 45% at most for the data center network, but also increases little network delay compared with general centralized solutions.