Flow Scheduling in Data Center Networks with Time and Energy Constraints: A Software-Defined Network Approach
Flow scheduling in Data Center Networks (DCN) is a hot topic as cloud computing and virtualization are becoming the dominant paradigm in the increasing demand of digital services. Within the cost of the DCN, the energy demands associated with the network infrastructure represent an important portion...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-02-01
|
Series: | Future Internet |
Subjects: | |
Online Access: | https://www.mdpi.com/1999-5903/14/2/65 |
_version_ | 1797480084481769472 |
---|---|
author | Martin Fraga Matías Micheletto Andrés Llinás Rodrigo Santos Paula Zabala |
author_facet | Martin Fraga Matías Micheletto Andrés Llinás Rodrigo Santos Paula Zabala |
author_sort | Martin Fraga |
collection | DOAJ |
description | Flow scheduling in Data Center Networks (DCN) is a hot topic as cloud computing and virtualization are becoming the dominant paradigm in the increasing demand of digital services. Within the cost of the DCN, the energy demands associated with the network infrastructure represent an important portion. When flows have temporal restrictions, the scheduling with path selection to reduce the number of active switching devices is a NP-hard problem as proven in the literature. In this paper, an heuristic approach to schedule real-time flows in data-centers is proposed, optimizing the temporal requirements while reducing the energy consumption in the network infrastructure via a proper selection of the paths. The experiments show good performance of the solutions found in relation to exact solution approximations based on an integer linear programming model. The possibility of programming the network switches allows the dynamic schedule of paths of flows under the software-defined network management. |
first_indexed | 2024-03-09T21:55:04Z |
format | Article |
id | doaj.art-b43df72bc9d442839a4a9812f00a7c29 |
institution | Directory Open Access Journal |
issn | 1999-5903 |
language | English |
last_indexed | 2024-03-09T21:55:04Z |
publishDate | 2022-02-01 |
publisher | MDPI AG |
record_format | Article |
series | Future Internet |
spelling | doaj.art-b43df72bc9d442839a4a9812f00a7c292023-11-23T20:00:09ZengMDPI AGFuture Internet1999-59032022-02-011426510.3390/fi14020065Flow Scheduling in Data Center Networks with Time and Energy Constraints: A Software-Defined Network ApproachMartin Fraga0Matías Micheletto1Andrés Llinás2Rodrigo Santos3Paula Zabala4Departamento de Computación, FCEN, Instituto de Investigación en Ciencias de la Computación (ICC), Universidad de Buenos Aires, UBA/CONICET, Buenos Aires C1428, ArgentinaInstituto de Ciencias e Ingeniería de Computación (ICIC), UNS/CONICET, Bahía Blanca B8000, ArgentinaInstituto de Ciencias e Ingeniería de Computación (ICIC), UNS/CONICET, Bahía Blanca B8000, ArgentinaInstituto de Ciencias e Ingeniería de Computación (ICIC), UNS/CONICET, Bahía Blanca B8000, ArgentinaDepartamento de Computación, FCEN, Instituto de Investigación en Ciencias de la Computación (ICC), Universidad de Buenos Aires, UBA/CONICET, Buenos Aires C1428, ArgentinaFlow scheduling in Data Center Networks (DCN) is a hot topic as cloud computing and virtualization are becoming the dominant paradigm in the increasing demand of digital services. Within the cost of the DCN, the energy demands associated with the network infrastructure represent an important portion. When flows have temporal restrictions, the scheduling with path selection to reduce the number of active switching devices is a NP-hard problem as proven in the literature. In this paper, an heuristic approach to schedule real-time flows in data-centers is proposed, optimizing the temporal requirements while reducing the energy consumption in the network infrastructure via a proper selection of the paths. The experiments show good performance of the solutions found in relation to exact solution approximations based on an integer linear programming model. The possibility of programming the network switches allows the dynamic schedule of paths of flows under the software-defined network management.https://www.mdpi.com/1999-5903/14/2/65energy awarereal-time schedulingsoftware define networks |
spellingShingle | Martin Fraga Matías Micheletto Andrés Llinás Rodrigo Santos Paula Zabala Flow Scheduling in Data Center Networks with Time and Energy Constraints: A Software-Defined Network Approach Future Internet energy aware real-time scheduling software define networks |
title | Flow Scheduling in Data Center Networks with Time and Energy Constraints: A Software-Defined Network Approach |
title_full | Flow Scheduling in Data Center Networks with Time and Energy Constraints: A Software-Defined Network Approach |
title_fullStr | Flow Scheduling in Data Center Networks with Time and Energy Constraints: A Software-Defined Network Approach |
title_full_unstemmed | Flow Scheduling in Data Center Networks with Time and Energy Constraints: A Software-Defined Network Approach |
title_short | Flow Scheduling in Data Center Networks with Time and Energy Constraints: A Software-Defined Network Approach |
title_sort | flow scheduling in data center networks with time and energy constraints a software defined network approach |
topic | energy aware real-time scheduling software define networks |
url | https://www.mdpi.com/1999-5903/14/2/65 |
work_keys_str_mv | AT martinfraga flowschedulingindatacenternetworkswithtimeandenergyconstraintsasoftwaredefinednetworkapproach AT matiasmicheletto flowschedulingindatacenternetworkswithtimeandenergyconstraintsasoftwaredefinednetworkapproach AT andresllinas flowschedulingindatacenternetworkswithtimeandenergyconstraintsasoftwaredefinednetworkapproach AT rodrigosantos flowschedulingindatacenternetworkswithtimeandenergyconstraintsasoftwaredefinednetworkapproach AT paulazabala flowschedulingindatacenternetworkswithtimeandenergyconstraintsasoftwaredefinednetworkapproach |