Algorithmic Issues in Green Data Centers

Power consumption imposes a significant cost for data centers. Thus, it is not surprising thatoptimizing energy cost in data center is receiving increasing attention. In this thesis, we focus onthe algorithmic issues at three levels of energy optimization for data centers: server level, local datacenter level and global data center level. At the server level, we analyze the common speed scalingalgorithms in both worst-case model and stochastic model to answer some fundamental issues in thedesign of speed scaling algorithms. At the local data center level, we develop an online algorithm tomake data center more power-proportional by dynamically adapting the number of active servers tomatch the current workload. At the global data center level, we propose a framework to explore thediversity of power prices and the diversity of propagation delays given geographically distributeddata centers.