Simple and Eective Dynamic Provisioning for Power-proportional Data Centers

Energy consumption represents a signicant cost in data center operation. A large fraction of the energy, however, is used to power idle servers when the workload is low. Dynamic provision-ing techniques aim at saving this portion of the energy, by turning o unnecessary servers. In this thesis, we explore how much gain knowing future workload information can bring to dynamic pro-visioning. In particular, we develop online dynamic provisioning solutions with and without future workload information available. We rst reveal an elegant structure of the oine dynamic pro-visioning problem, which allows us to characterize the optimal solution in a divide-and-conquer manner. We then exploit this insight to design two online algorithms with competitive ratios 2 − α and e / (e − 1 + α), respectively, where 0 ≤ α ≤ 1 is the normalized size of a look-ahead window in which future workload information is available. A fundamental observation is that fu