Datacenter power management in smart grids

Cloud computing is a new computing paradigm and it is gaining wide popularity due to its benefits including reduced cost, ease of management, and increased reliability. In a cloud computing environment, companies or individuals offload their computing (hardware/software/data) to the cloud, which is supported by the computing infrastructure called datacenters. Datacenters consume large amounts of electricity to operate and bring enormous electricity bills to the operators. Associated emissions also cause significant negative impact to the environment. Meanwhile, a new kind of electrical grid, called the smart grid, is emerging. Smart grids enable two way communications between the power generators and the power consumers. Smart grid technology brings many salient features to help deliver power efficiently and reliably. There are many efforts addressing either of the two tracks above. Different with them, we focus on cost-aware datacenter power management in presence of smart grids and review recent developments on this area. It involves understanding how a smart grid operates, where power goes in datacenters, and most importantly, how to reduce the power cost and/or negative environmental impact when operating datacenters. We first study new ideas of exploring spatial diversities provided by geographically distributed datacenters and show how to perform request routing. Then, we discuss the research that leverages temporal flexibilities given by delay-tolerant workload and present how to conduct workload scheduling. Thirdly, we study how to jointly optimize routing and scheduling by considering spatial diversities and temporal flexibilities together. These studies consider multiple features of smart grids, and develop different cost minimization approaches using techniques from the optimization, algorithmic, and feedback control fields. Moreover, we review studies incorporating the same solution framework with additional dimensions such as renewable and cooling.