A Process Migration Approach to Energy-Efficient Computation in a Cluster of Servers

Abstract

Application processes have to be efficiently performed on servers in a cluster with respect to not only performance but also electric energy consumption. In this paper, we consider a process migration (MG) approach to energy-efficiently performing application processes on servers in a cluster. First, a client issues an application process to a server in a cluster. A process performed on a current server is migrated to another server if the server is expected to consume smaller electric energy to perform the process than the current server and the deadline constraint on the process is satisfied on the server. In the evaluation, the total electric energy consumption of servers is shown to be smaller and the average execution time of each process to be shorter in the MG algorithm than the round robin and random algorithms.