NPi-Cluster: A Low Power Energy-Proportional Computing Cluster Architecture

This paper presents the NPi-Cluster, an energy proportional computing cluster that automatically powers ON or OFF the number of running machines according to the actual processing demand. A theoretical model is proposed, discussed, and implemented on a cluster composed of Raspberry Pi computer board...

Full description

Bibliographic Details
Main Authors: Sebastiao Emidio Alves Filho, Aquiles Medeiros Filgueira Burlamaqui, Rafael Vidal Aroca, Luiz Marcos Garcia Goncalves
Format: Article
Language:English
Published: IEEE 2017-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/8004443/
id doaj-90685a9c687b4357b09dac6f435df4c2
record_format Article
spelling doaj-90685a9c687b4357b09dac6f435df4c22021-03-29T20:05:44ZengIEEEIEEE Access2169-35362017-01-015162971631310.1109/ACCESS.2017.27287208004443NPi-Cluster: A Low Power Energy-Proportional Computing Cluster ArchitectureSebastiao Emidio Alves Filho0https://orcid.org/0000-0002-2029-4726Aquiles Medeiros Filgueira Burlamaqui1Rafael Vidal Aroca2Luiz Marcos Garcia Goncalves3Departamento de Informática, Universidade do Estado do Rio Grande do Norte, Mossoró, BrazilUniversidade Federal do Rio Grande do Norte, Natal, BrazilUniversidade Federal de São Carlos, São Carlos, BrazilUniversidade Federal do Rio Grande do Norte, Natal, BrazilThis paper presents the NPi-Cluster, an energy proportional computing cluster that automatically powers ON or OFF the number of running machines according to the actual processing demand. A theoretical model is proposed, discussed, and implemented on a cluster composed of Raspberry Pi computer boards designed and built in order to test the proposed system architecture. Experimental results show adequate performance of the proposed platform when compared with other web servers running on traditional server architectures, but with considerably less power consumption. The power consumption of the entire cluster is about 14 W when running at maximum performance. In this situation, the system is able to handle more than 450 simultaneous requests, with about 1000 transactions per second, making it possible to be used as a server capable of handling real web workloads with acceptable quality of service. When the requests demand is reduced to a minimum, the power consumption is dynamically reduced until less than 2 W. Additionally, the proposed cluster architecture also provides high availability by reducing single points of failure on the system.https://ieeexplore.ieee.org/document/8004443/Energy efficiencyscalabilityquality of servicedistributed computinglow power electronics
collection DOAJ
language English
format Article
sources DOAJ
author Sebastiao Emidio Alves Filho
Aquiles Medeiros Filgueira Burlamaqui
Rafael Vidal Aroca
Luiz Marcos Garcia Goncalves
spellingShingle Sebastiao Emidio Alves Filho
Aquiles Medeiros Filgueira Burlamaqui
Rafael Vidal Aroca
Luiz Marcos Garcia Goncalves
NPi-Cluster: A Low Power Energy-Proportional Computing Cluster Architecture
IEEE Access
Energy efficiency
scalability
quality of service
distributed computing
low power electronics
author_facet Sebastiao Emidio Alves Filho
Aquiles Medeiros Filgueira Burlamaqui
Rafael Vidal Aroca
Luiz Marcos Garcia Goncalves
author_sort Sebastiao Emidio Alves Filho
title NPi-Cluster: A Low Power Energy-Proportional Computing Cluster Architecture
title_short NPi-Cluster: A Low Power Energy-Proportional Computing Cluster Architecture
title_full NPi-Cluster: A Low Power Energy-Proportional Computing Cluster Architecture
title_fullStr NPi-Cluster: A Low Power Energy-Proportional Computing Cluster Architecture
title_full_unstemmed NPi-Cluster: A Low Power Energy-Proportional Computing Cluster Architecture
title_sort npi-cluster: a low power energy-proportional computing cluster architecture
publisher IEEE
series IEEE Access
issn 2169-3536
publishDate 2017-01-01
description This paper presents the NPi-Cluster, an energy proportional computing cluster that automatically powers ON or OFF the number of running machines according to the actual processing demand. A theoretical model is proposed, discussed, and implemented on a cluster composed of Raspberry Pi computer boards designed and built in order to test the proposed system architecture. Experimental results show adequate performance of the proposed platform when compared with other web servers running on traditional server architectures, but with considerably less power consumption. The power consumption of the entire cluster is about 14 W when running at maximum performance. In this situation, the system is able to handle more than 450 simultaneous requests, with about 1000 transactions per second, making it possible to be used as a server capable of handling real web workloads with acceptable quality of service. When the requests demand is reduced to a minimum, the power consumption is dynamically reduced until less than 2 W. Additionally, the proposed cluster architecture also provides high availability by reducing single points of failure on the system.
topic Energy efficiency
scalability
quality of service
distributed computing
low power electronics
url https://ieeexplore.ieee.org/document/8004443/
work_keys_str_mv AT sebastiaoemidioalvesfilho npiclusteralowpowerenergyproportionalcomputingclusterarchitecture
AT aquilesmedeirosfilgueiraburlamaqui npiclusteralowpowerenergyproportionalcomputingclusterarchitecture
AT rafaelvidalaroca npiclusteralowpowerenergyproportionalcomputingclusterarchitecture
AT luizmarcosgarciagoncalves npiclusteralowpowerenergyproportionalcomputingclusterarchitecture
_version_ 1724195323169996800