Abstract
Nowadays Internet-scale data centers are serving diverse applications, such as cloud computing, online trade, mass storage services, large-scale distributed applications, and et al. However, one issue concerned about data centers is huge energy consumption, which not only increases operational cost, but also causes environment problems. One way to reduce energy con-sumption is decreasing the scale of data centers, and another way is using well-designed resource allocation algorithm to achieve the tradeoff between energy consumption and performance. This paper belongs to the latter. In this paper, we first discuss the resource allocation problem in a heterogeneous data center, and then we propose a novel resource allocation algorithm based on fair scheduling policy and energy-aware policy to this problem, and present further discussions and conclusion at the end.