We target the problem of managing server power states in a Cloud Data Center (CDC) to jointly minimize electricity consumption and maintenance costs arising from the variation of power (and consequently temperature) on the server’s CPU. An Approach to Balance Maintenance Costs and Electricity Consumption in Cloud Data Centers We look in more detail at a set of virtual machines (VMs) and their CPU and memory requirements across a set of Time Slot (TSs).

An Approach to Balance Maintenance Costs and Electricity Consumption in Cloud Data Centers We then model the electricity consumed by taking into account the costs of processing VMs on the servers, the costs of transferring data between VMs, and the costs of migrating VMs across the servers. We also use a material-based fatigue model to calculate the maintenance costs needed to repair the CPU as a result of the server power state variation over time.