Power consumption and processing models of servers in computation and storage based applications

The electric power consumption of information systems has to be reduced in addition to increasing the performance and fault tolerance in order to realize green societies. Here, servers mainly consume electric power to perform processes requested by clients compared with clients. We consider computation (CP) and storage (ST) types of application processes on servers. In CP processes, CPU is mainly consumed as in scientific computation. In ST processes, files in storage drives are mainly manipulated. First, we present the storage and computation based power consumption (SCBPC) model of a server to perform ST and CP processes. In the SCBPC model, the power consumption rate of a server depends on the types of processes concurrently performed and is independent of the number of processes. Then, we discuss the storage and computation based processing (SCBP) model to perform CP and ST processes on a server. Here, the execution times of a CP process and an ST process depend on the number of CP processes and the number of CP and ST processes concurrently performed, respectively. By using the SCBPC and SCBP models, we discuss an energy-aware (EA) algorithm to select a server for a process so that not only the execution time but also the power consumption can be reduced. We evaluate the EA algorithm in terms of total power consumption of servers and total execution time of processes. We show not only the total power consumption but also the total execution time can be reduced in the EA algorithm.