An Algorithm to Select a Server to Minimize the Total Energy Consumption of a Cluster

Abstract

We have to decrease electric energy consumption of information systems, especially servers to reduce carbon dioxide emission. In this paper, we discuss how to select a server to perform a new application process issued by a client so as to reduce the total energy consumption of servers in a cluster. Here, we have to estimate the execution time of application processes on a server and the energy consumption of the server to perform the new process and current active processes. In this paper, we newly propose an ESEC (EStimation of Energy Consumption) algorithm to estimate the execution time of current active processes and the energy consumption of a server by considering not only current active processes but also possible processes to be issued after the current time. By using the ESEC model, we also propose an ESECS (ESEC Selection) algorithm to select a server to perform an application process. In the evaluation, we show the total energy consumption of servers and the average execution time of processes can be reduced in the ESEC algorithm in compared with the previous estimation algorithm.