Multi-level Power Consumption and Computation Models and Energy-Efficient Server Selection Algorithms in a Scalable Cluster

It is critical to reduce the electric energy consumed in information systems, especially server clusters. In ourprevious studies, the MLPCM (multi-level power consumption with multiple CPUs) and MLCM (multi-level computation with multiple CPUs) models are proposed with server selection algorithms. I...

Full description

Saved in:
Bibliographic Details
Main Authors: Kataoka, Hiroki, Sawada, Atsuhiro, Duolikun, Dilawaer, Enokido, Tomoya, Takizawa, Makoto
Format: Conference Proceeding
Language:English
Subjects:
Clustering algorithms
Computational modeling
Energy consumption
Energy-aware server selection algorithm
Instruction sets
MLCM model
MLPCM model
PEA alogrithm
Power demand
Servers
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:It is critical to reduce the electric energy consumed in information systems, especially server clusters. In ourprevious studies, the MLPCM (multi-level power consumption with multiple CPUs) and MLCM (multi-level computation with multiple CPUs) models are proposed with server selection algorithms. In the server selection algorithms, a server is selected to perform a process issued by a client by estimating the electric energy consumption by simulating the execution of every current process. However, it takes time to collect the state of processes performed on each server and estimate the termination time of the processes. In this paper, we propose a simple energy-efficient (PEA) algorithm to select server where only state information on number of processes on each serveris used. We evaluate the PEA algorithm and show not only the total electric energy consumption of the servers but also the average execution time of processes are reduced in the PEA algorithm compared with other algorithms.
ISSN:2157-0426
DOI:10.1109/NBiS.2016.88