Currently, an increasing number of companies deploy their applications or Internet services into data centers. For better performance and lower cost, multiple heterogeneous applications concurrently run in distributed cloud data centers (CDCs). In addition, the growing deployment of applications significantly increases the operational cost (e.g., energy and bandwidth cost) of data center providers. Considering the environmental effect, many of the current cloud providers have migrated to green cloud data centers (GCDCs) and seek to reduce the usage of brown energy by partially (or entirely) adopting renewable energy sources.

This chapter mainly focuses on two highly challenging problems related to energy-efficient data centers. First, we focus on how to minimize the total cost of a CDC provider in a market where the bandwidth and energy cost show geographical diversity. To solve the problem, we present a cost-aware workload scheduling method that jointly optimizes the number of active servers in each CDC and the selection of Internet service providers for the CDC provider. Compared with several existing methods, the proposed method can greatly reduce the total cost and increase the throughput of the CDCs.

Second, we focus on how to minimize the grid energy cost of a GCDC while meeting the performance of each delay bounded request in an environment where grid price, wind speed, and solar irradiance show temporal diversity. Then, we propose a Temporal Request Scheduling algorithm (TRS) that considers the temporal diversity and long tail feature in real-life requests’ delay. TRS solves a constrained nonlinear optimization problem through a hybrid meta-heuristic in each of its iterations and provides strict delay assurance to all arriving requests by scheduling them to execute within their delay bound. Compared with some existing methods, TRS can achieve higher throughput and lower grid energy cost for a GCDC.