An Algorithm to Select an Energy-Efficient Server for an Application Process in a Cluster

Abstract

We have to decrease electric energy consumption of information systems, especially servers to realize green societies. Information systems are composed of servers. One server is selected to perform an application process issued by a client so as to not only increase the performance but also reduce the energy consumption of the servers. In our previous studies, the ESECS algorithm is proposed to select a host server to perform an application process. Here, only the energy consumption of each server is compared with the other servers. In this paper, we take into consideration the total energy consumption of the other servers in addition to a host server. We propose an MTES (Minimization of Total Energy consumption of Servers) algorithm to select a host server where the total energy consumption of all the servers can be minimized in this paper. In the evaluation, we show the total energy consumption of servers and the average execution time of processes can be reduced in the MTES algorithm compared with other algorithms.