ENERGY-EFFICIENT ALGORITHM BASED ON SERVICE-AWARENESS FOR DATA CENTRE NETWORKS

摘要

The high energy consumption of data centres has been a recurring issue in recent research. In cloud environments, several techniques have been used for energy saving, including scaling the processors' frequency, switching switches to sleep mode during idle periods and consolidating virtual machines. Although these techniques realize the reduction of power consumption, they usually affect application performance and do not consider the relations among these applications. To emphasize the relations among applications, in this paper, we propose a service-aware network model which is based on the traffic pattern in the data centre. First of all, we analyse the traffic model in data centre networks. Then we use this model to make the network devices integrated and classified by software-defined network. To achieve energy efficiency optimization, we divide the hosts into different Virtual Local Area Network (VLANs) according to their interaction frequency to reduce the cross-VLAN transmission consumption. Simulation results show that the proposed scheme can greatly improve the energy consumption in the network.