Placing it right! optimizing energy, processing, and transport in Edge-Fog clouds

Research output: Contribution to journalArticleScientificpeer-review

Abstract

In recent years, applications such as Internet-of-Things has proliferated the Internet to a great extent. Such applications derive data from a significant number of smart sensors sensing information from the environment. Due to an extensive data footprint, the demand for cloud services to process this data has also increased. However, traditional centralized cloud model requires offloading data from these sensors over a network which induces significant network delay on these applications. Several architectural abstractions of cloud, such as Fog and Edge, have been proposed to localize some of the processing near the sensors and away from the central cloud servers. In this paper, we propose Edge-Fog cloud which distributes task processing on the participating cloud resources in the network. We develop the Least Processing Cost First (LPCF) method for assigning the processing tasks to nodes which provide the optimal processing time and near-optimal networking costs. We further provide an energy-efficient variant of LPCF, i.e., eLPCF algorithm, which optimizes energy usage while calculating task deployment in Edge-Fog cloud. We evaluate both LPCF and eLPCF in a variety of scenarios and demonstrate its effectiveness in finding the processing task assignments.

Original languageEnglish
JournalAnnales des Telecommunications
Volume73
Issue number7-8
Pages (from-to)463-474
Number of pages12
ISSN0003-4347
DOIs
Publication statusPublished - Aug 2018
MoE publication typeA1 Journal article-refereed

Fields of Science

  • 113 Computer and information sciences
  • Cloud computing
  • Fog computing
  • Edge computing
  • Internet-of-Things
  • Task assignment

Cite this

@article{2f2055703f96439bae899753f2b1af30,
title = "Placing it right!: optimizing energy, processing, and transport in Edge-Fog clouds",
abstract = "In recent years, applications such as Internet-of-Things has proliferated the Internet to a great extent. Such applications derive data from a significant number of smart sensors sensing information from the environment. Due to an extensive data footprint, the demand for cloud services to process this data has also increased. However, traditional centralized cloud model requires offloading data from these sensors over a network which induces significant network delay on these applications. Several architectural abstractions of cloud, such as Fog and Edge, have been proposed to localize some of the processing near the sensors and away from the central cloud servers. In this paper, we propose Edge-Fog cloud which distributes task processing on the participating cloud resources in the network. We develop the Least Processing Cost First (LPCF) method for assigning the processing tasks to nodes which provide the optimal processing time and near-optimal networking costs. We further provide an energy-efficient variant of LPCF, i.e., eLPCF algorithm, which optimizes energy usage while calculating task deployment in Edge-Fog cloud. We evaluate both LPCF and eLPCF in a variety of scenarios and demonstrate its effectiveness in finding the processing task assignments.",
keywords = "113 Computer and information sciences, Cloud computing, Fog computing, Edge computing, Internet-of-Things, Task assignment",
author = "Nitinder Mohan and Jussi Kangasharju",
year = "2018",
month = "8",
doi = "10.1007/s12243-018-0649-0",
language = "English",
volume = "73",
pages = "463--474",
journal = "Annales des Telecommunications",
issn = "0003-4347",
publisher = "SPRINGER FRANCE",
number = "7-8",

}

Placing it right! optimizing energy, processing, and transport in Edge-Fog clouds. / Mohan, Nitinder; Kangasharju, Jussi.

In: Annales des Telecommunications, Vol. 73, No. 7-8, 08.2018, p. 463-474.

Research output: Contribution to journalArticleScientificpeer-review

TY - JOUR

T1 - Placing it right!

T2 - optimizing energy, processing, and transport in Edge-Fog clouds

AU - Mohan, Nitinder

AU - Kangasharju, Jussi

PY - 2018/8

Y1 - 2018/8

N2 - In recent years, applications such as Internet-of-Things has proliferated the Internet to a great extent. Such applications derive data from a significant number of smart sensors sensing information from the environment. Due to an extensive data footprint, the demand for cloud services to process this data has also increased. However, traditional centralized cloud model requires offloading data from these sensors over a network which induces significant network delay on these applications. Several architectural abstractions of cloud, such as Fog and Edge, have been proposed to localize some of the processing near the sensors and away from the central cloud servers. In this paper, we propose Edge-Fog cloud which distributes task processing on the participating cloud resources in the network. We develop the Least Processing Cost First (LPCF) method for assigning the processing tasks to nodes which provide the optimal processing time and near-optimal networking costs. We further provide an energy-efficient variant of LPCF, i.e., eLPCF algorithm, which optimizes energy usage while calculating task deployment in Edge-Fog cloud. We evaluate both LPCF and eLPCF in a variety of scenarios and demonstrate its effectiveness in finding the processing task assignments.

AB - In recent years, applications such as Internet-of-Things has proliferated the Internet to a great extent. Such applications derive data from a significant number of smart sensors sensing information from the environment. Due to an extensive data footprint, the demand for cloud services to process this data has also increased. However, traditional centralized cloud model requires offloading data from these sensors over a network which induces significant network delay on these applications. Several architectural abstractions of cloud, such as Fog and Edge, have been proposed to localize some of the processing near the sensors and away from the central cloud servers. In this paper, we propose Edge-Fog cloud which distributes task processing on the participating cloud resources in the network. We develop the Least Processing Cost First (LPCF) method for assigning the processing tasks to nodes which provide the optimal processing time and near-optimal networking costs. We further provide an energy-efficient variant of LPCF, i.e., eLPCF algorithm, which optimizes energy usage while calculating task deployment in Edge-Fog cloud. We evaluate both LPCF and eLPCF in a variety of scenarios and demonstrate its effectiveness in finding the processing task assignments.

KW - 113 Computer and information sciences

KW - Cloud computing

KW - Fog computing

KW - Edge computing

KW - Internet-of-Things

KW - Task assignment

U2 - 10.1007/s12243-018-0649-0

DO - 10.1007/s12243-018-0649-0

M3 - Article

VL - 73

SP - 463

EP - 474

JO - Annales des Telecommunications

JF - Annales des Telecommunications

SN - 0003-4347

IS - 7-8

ER -