Evaluation of an Energy-Aware Selection Algorithm for Computation and Storage-Based Applications

The electric power consumption of information systems has to be reduced in addition to increasing the performance and fault-tolerancy in order to realize green societies. In information systems, servers mainly consume the electric power to perform processes requested by clients. We consider computation (CP) and storage (ST) types of application processes on servers. In CP and ST processes, CPU and storage drives are mainly consumed, respectively. First, we present the storage-based power consumption (SBPC) model of a server st to perform ST and CP processes. The SBPC model is a four state model, where the power consumption rate of a server is one of four rates minE_t, ST_t, C_t, and STC_t. Here, the power consumption rate E_t( τ) of a server s_t at time is minimum minEt if no process is performed. The power consumption rate Et(τ) is STt if only and at least one ST process is performed Et(τ) in a server st. Et(t) is Ct if only and at least one CP process is performed on the server st. If both ST and CP processes ar concurrently performed, Et(τ) is STC_t. Here, minE_t <; ST_t<;C_t<;STC_t. The more number of processes are concurrently performed on a server, the longer it takes to perform each of the processes. The average execution times of a CP process and an ST process depend on the numbers of CP and ST processes concurrently performed, respectively. We discuss the computation model to perform CP and ST processes on a server. By using the SBPC model, we discuss an algorithm for selecting a server so that not only the execution time but also the power consumption can be reduced.