Eco Models of Storage-Based Severs

Abstract

Information systems are getting scalable like cloud computing systems and Internet of Things (IoT). It is critical to reduce electric energy consumed in our society. In information systems, we have to reduce the electric energy consumed by computers, especially servers in clusters to perform application processes. Types of application processes like computation, storage, and communication processes are performed on servers in clusters. Computation processes consume CPU resource to do the computation like scientific computation. The power consumption models like simple power consumption (SPC) and multi-level power consumption (MLPC) models are already proposed for computation processes in our previous studies. In this paper, we consider storage processes which read and write files in storage devices. We newly propose a simple power consumption model for a storage of a server (SPCS model), which shows how much electric power the server consumes to perform storage and computation processes. In our macro-level approach, we first measure the electric power consumed by a whole server to perform storage and computation processes. Then, we define the SPCS model of a server to perform storage and computation processes by abstracting parameters like number of processes which dominate the electric power consumption.