Optimal Server Provisioning and Frequency Adjustment in Server Clusters

Abstract

Green computing is a hot topic that received a great amount of interest in the past few years. This paper explores the benefits of Dynamic Voltage/Frequency Scaling (DV/FS) and server number controlling Vary-On Vary-Off (VOVF) for power management in a server cluster. Previous work mostly addressed the DV/FS and VOVF separately. In this paper, an optimization problem is formulated to achieve energy savings while ensure performance. DV/FS and VOVF mechanisms are combined to obtain an optimal power management tactics. The presented optimization model provides controllable and predictable quantitative control of power consumption with theoretically guaranteed service performance. We further study overhead of the proposed scheme and provide a Double Control Periods (DCP) model to compensate the transition overhead. The power optimization model and DCP model are evaluated via extensive simulations, they are also justified by the real workload data trace. The results prove the effectiveness and efficiency of the proposed models.