关键词: 网络能耗, 流量相关性, 流量整合, 软件定义网络, 数据中心

Abstract: 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.

Key words: network energy consumption, traffic correlation, traffic consolidation, software defined network, data center